Official code for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021

Hi,

I reproduced all your steps and got the following output from the console:

`------------ Options ------------- batchSize: 1 data_type: 32 dataroot: dataset/ display_winsize: 512 fineSize: 512 gen_checkpoint: checkpoints/PFAFN/gen_model_final.pth gpu_ids: [0] input_nc: 3 isTrain: False loadSize: 512 max_dataset_size: inf nThreads: 1 name: demo no_flip: False norm: instance output_nc: 3 phase: test resize_or_crop: None serial_batches: False tf_log: False use_dropout: False verbose: False warp_checkpoint: checkpoints/PFAFN/warp_model_final.pth -------------- End ---------------- CustomDatasetDataLoader dataset [AlignedDataset] was created 6 AFWM( (image_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (cond_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (image_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (cond_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (aflow_net): AFlowNet( (netMain): ModuleList( (0): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (netRefine): ModuleList( (0): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) ) ) ResUnetGenerator( (model): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(7, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): Upsample(scale_factor=2.0, mode=nearest) (5): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (6): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (7): ReLU(inplace) (8): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (9): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(256, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (5): Upsample(scale_factor=2.0, mode=nearest) (6): Conv2d(128, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) )------------ Options ------------- batchSize: 1 data_type: 32 dataroot: dataset/ display_winsize: 512 fineSize: 512 gen_checkpoint: checkpoints/PFAFN/gen_model_final.pth gpu_ids: [0] input_nc: 3 isTrain: False loadSize: 512 max_dataset_size: inf nThreads: 1 name: demo no_flip: False norm: instance output_nc: 3 phase: test resize_or_crop: None serial_batches: False tf_log: False use_dropout: False verbose: False warp_checkpoint: checkpoints/PFAFN/warp_model_final.pth -------------- End ---------------- CustomDatasetDataLoader dataset [AlignedDataset] was created 6 AFWM( (image_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (cond_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (image_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (cond_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (aflow_net): AFlowNet( (netMain): ModuleList( (0): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (netRefine): ModuleList( (0): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) ) ) ResUnetGenerator( (model): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(7, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): Upsample(scale_factor=2.0, mode=nearest) (5): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (6): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (7): ReLU(inplace) (8): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (9): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(256, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (5): Upsample(scale_factor=2.0, mode=nearest) (6): Conv2d(128, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) )

Traceback (most recent call last): File "", line 1, in File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 114, in _main prepare(preparation_data) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 225, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path run_name="mp_main") File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 263, in run_path pkg_name=pkg_name, script_name=fname) File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 96, in _run_module_code mod_name, mod_spec, pkg_name, script_name) File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Users\JONY-\PF-AFN\PF-AFN_test\test.py", line 40, in for i, data in enumerate(dataset, start=epoch_iter): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 193, in iter return _DataLoaderIter(self) File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 469, in init w.start() File "D:\ANACONDA\envs\tryon\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\popen_spawn_win32.py", line 33, in init prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 143, in get_preparation_data _check_not_importing_main() File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 136, in _check_not_importing_main is not going to be frozen to produce an executable.''') RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

    This probably means that you are not using fork to start your
    child processes and you have forgotten to use the proper idiom
    in the main module:

        if __name__ == '__main__':
            freeze_support()
            ...

    The "freeze_support()" line can be omitted if the program
    is not going to be frozen to produce an executable.

Traceback (most recent call last): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 511, in _try_get_batch data = self.data_queue.get(timeout=timeout) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\queues.py", line 105, in get raise Empty queue.Empty

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "test.py", line 40, in for i, data in enumerate(dataset, start=epoch_iter): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 576, in next idx, batch = self._get_batch() File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 553, in _get_batch success, data = self._try_get_batch() File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 519, in _try_get_batch raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) RuntimeError: DataLoader worker (pid(s) 3220) exited unexpectedly`

If you could offer a solution, It'll be really helpful. I'm trying to reproduce your results against CP-VTON+ and so far I have not been able.

Cannot quite replicate the results. [Solved]

First of all, thank you very much for your contribution. This work seems to work considerably better than ACGPN and other approaches tackling this task.

I wanted to issue that even if I followed the steps to run it, the results I got from running the test.sh are quite different from the ones you showcase. Here is an example:

Has anyone encountered similar misaligments? Do you believe that those are caused by mismatching of the dependency versions? I am aware that you comment about it in the markdown, but I would like to ask how slight differences impacts final output.

Thank you very much for your time and congratulations for your publication.

Edit: typo

opened by PLXIV 9
How to do the test in colab

I tried running the code in Colab, but the results weren't the same as yours. I think it is because of the environment issue. How can I create the same environment in Colab

opened by Ammar-Ahmad-Khan 4
Train image warping issues

When I was training, I found that most of the pictures were not properly extracted, some could and some could not, and most of them could not be extracted correctly Can you help me?

opened by wang674 3
Image extracting problem with Training

Thank you for the amazing work!

I am currently training PB-AFN stage 1 on Google Golab, and I have trouble with displaying "person_clothes" on the 2nd column. I am certain that I have upload the train_label folder on google drive and the root is correct, and I have check the code but cannot find where the problem is.

Could anyone help me with this issue?

opened by Rerorerororo 3
Edges Extraction

Could you share your code/setup for edge/mask extraction?

I simply obtained similar results using opencv canny edge detection and contours filling, but wanted to be sure to match your setup as closely as possible for reproducibility and quality comparison.

opened by 5agado 3
Type Error while loading data from train_dense pose

@geyuying Hello, This is a wonderful repository you have provided us. I'm trying to train the Network on google colab, I was able to do the necessary modifications in code to bring it down to a single GPU. But there's a type mismatch while it runs iteration through .npy file formats. It's being perceived as int object. I request you to help me resolve the issue

/usr/local/lib/python3.7/site-packages/torchvision/transforms/transforms.py:281: UserWarning: Argument interpolation should be of type InterpolationMode instead of int. Please, use InterpolationMode enum. "Argument interpolation should be of type InterpolationMode instead of int. " Traceback (most recent call last): File "train_PBAFN_stage1.py", line 79, in for i, data in enumerate(train_loader): File "/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 521, in next data = self._next_data() File "/usr/local/lib/python3.7/site-packages/torch/utils/data/dataloader.py", line 561, in _next_data data = self._dataset_fetcher.fetch(index) # may raise StopIteration File "/usr/local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in fetch data = [self.dataset[idx] for idx in possibly_batched_index] File "/usr/local/lib/python3.7/site-packages/torch/utils/data/_utils/fetch.py", line 44, in data = [self.dataset[idx] for idx in possibly_batched_index] File "/content/PF-AFN/PF-AFN_train/data/aligned_dataset.py", line 108, in getitem dense_mask = transform_A(dense_mask) File "/usr/local/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 60, in call img = t(img) File "/usr/local/lib/python3.7/site-packages/torchvision/transforms/transforms.py", line 430, in call return self.lambd(img) File "/content/PF-AFN/PF-AFN_train/data/base_dataset.py", line 64, in transform_list.append(transforms.Lambda(lambda img: __scale_width(img, opt.loadSize, method))) File "/content/PF-AFN/PF-AFN_train/data/base_dataset.py", line 98, in __scale_width ow, oh = img.size TypeError: cannot unpack non-iterable int object

** Thank You**

opened by SumanthJain2998 2
train_PBAFN_stage1 failed

I use this wonderful project with another CV project,whitch require the core ENV bellow: torch 1.8.0+cu111
torchaudio 0.8.0
torchvision 0.9.0+cu111 cuda 0.0.1
cudatoolkit 11.1.1
cupy-cuda111 8.6.0 cupy 9.0.0
cupy-cuda111 8.6.0 The script [scripts/train_PBAFN_stage1.sh] return this error " RuntimeError: Given input size: (512x2x1). Calculated output size: (512x1x0). Output size is too small", can anyone help me,thank you!

opened by crinai 2
About running training code on a GPU

I only have one GPU, and now I have successfully run test.py. But when I try to run train***.py, it will report this error: So I added some parameters by searching for information, and then running, it will report this error.

I don’t know how to solve this error so far.How can I solve this problem?

opened by Zibin-Z 2
Testing

Thank you so much for implementing this research paper in such a convenient format for us! I just needed a little help! I have a custom dataset with a directory for "clothes", "clothes-masks", "test-images", how do I go about testing it? My approach, from what I understood in the code, was to add the images in the folders and then edit the demo.txt to form pairs accordingly? Is there an easier/more automated method for doing this? Thank you for your help!

opened by dhananjay1710 2
Demo not working
Hi,

I reproduced all your steps and got the following output from the console:

`------------ Options ------------- batchSize: 1 data_type: 32 dataroot: dataset/ display_winsize: 512 fineSize: 512 gen_checkpoint: checkpoints/PFAFN/gen_model_final.pth gpu_ids: [0] input_nc: 3 isTrain: False loadSize: 512 max_dataset_size: inf nThreads: 1 name: demo no_flip: False norm: instance output_nc: 3 phase: test resize_or_crop: None serial_batches: False tf_log: False use_dropout: False verbose: False warp_checkpoint: checkpoints/PFAFN/warp_model_final.pth -------------- End ---------------- CustomDatasetDataLoader dataset [AlignedDataset] was created 6 AFWM( (image_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (cond_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (image_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (cond_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (aflow_net): AFlowNet( (netMain): ModuleList( (0): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (netRefine): ModuleList( (0): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) ) ) ResUnetGenerator( (model): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(7, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): Upsample(scale_factor=2.0, mode=nearest) (5): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (6): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (7): ReLU(inplace) (8): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (9): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(256, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (5): Upsample(scale_factor=2.0, mode=nearest) (6): Conv2d(128, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) )------------ Options ------------- batchSize: 1 data_type: 32 dataroot: dataset/ display_winsize: 512 fineSize: 512 gen_checkpoint: checkpoints/PFAFN/gen_model_final.pth gpu_ids: [0] input_nc: 3 isTrain: False loadSize: 512 max_dataset_size: inf nThreads: 1 name: demo no_flip: False norm: instance output_nc: 3 phase: test resize_or_crop: None serial_batches: False tf_log: False use_dropout: False verbose: False warp_checkpoint: checkpoints/PFAFN/warp_model_final.pth -------------- End ---------------- CustomDatasetDataLoader dataset [AlignedDataset] was created 6 AFWM( (image_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (cond_features): FeatureEncoder( (encoders): ModuleList( (0): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(3, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(3, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (1): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (2): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (3): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) (4): Sequential( (0): DownSample( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) ) ) (1): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) (2): ResBlock( (block): Sequential( (0): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (1): ReLU(inplace) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (3): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (4): ReLU(inplace) (5): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) ) ) ) (image_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (cond_FPN): RefinePyramid( (adaptive): ModuleList( (0): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (1): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (2): Conv2d(256, 256, kernel_size=(1, 1), stride=(1, 1)) (3): Conv2d(128, 256, kernel_size=(1, 1), stride=(1, 1)) (4): Conv2d(64, 256, kernel_size=(1, 1), stride=(1, 1)) ) (smooth): ModuleList( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (2): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (4): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (aflow_net): AFlowNet( (netMain): ModuleList( (0): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(49, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) (netRefine): ModuleList( (0): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (1): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (2): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (3): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) (4): Sequential( (0): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (1): LeakyReLU(negative_slope=0.1) (2): Conv2d(128, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (3): LeakyReLU(negative_slope=0.1) (4): Conv2d(64, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) (5): LeakyReLU(negative_slope=0.1) (6): Conv2d(32, 2, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1)) ) ) ) ) ResUnetGenerator( (model): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(7, 64, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(64, 128, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(128, 256, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(256, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (5): ResUnetSkipConnectionBlock( (model): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(2, 2), padding=(1, 1), bias=False) (1): ReLU(inplace) (2): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (3): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (4): Upsample(scale_factor=2.0, mode=nearest) (5): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (6): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (7): ReLU(inplace) (8): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (9): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(512, 512, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(1024, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(256, 256, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(512, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(128, 128, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (6): Upsample(scale_factor=2.0, mode=nearest) (7): Conv2d(256, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (8): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (9): ReLU(inplace) (10): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) (11): ResidualBlock( (relu): ReLU(inplace) (block): Sequential( (0): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) (2): ReLU(inplace) (3): Conv2d(64, 64, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) (4): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True) ) ) ) ) (5): Upsample(scale_factor=2.0, mode=nearest) (6): Conv2d(128, 4, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False) ) ) )

Traceback (most recent call last): File "", line 1, in File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 105, in spawn_main exitcode = _main(fd) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 114, in _main prepare(preparation_data) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 225, in prepare _fixup_main_from_path(data['init_main_from_path']) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 277, in _fixup_main_from_path run_name="mp_main") File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 263, in run_path pkg_name=pkg_name, script_name=fname) File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 96, in _run_module_code mod_name, mod_spec, pkg_name, script_name) File "D:\ANACONDA\envs\tryon\lib\runpy.py", line 85, in _run_code exec(code, run_globals) File "C:\Users\JONY-\PF-AFN\PF-AFN_test\test.py", line 40, in for i, data in enumerate(dataset, start=epoch_iter): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 193, in iter return _DataLoaderIter(self) File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 469, in init w.start() File "D:\ANACONDA\envs\tryon\lib\multiprocessing\process.py", line 105, in start self._popen = self._Popen(self) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\context.py", line 223, in _Popen return _default_context.get_context().Process._Popen(process_obj) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\context.py", line 322, in _Popen return Popen(process_obj) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\popen_spawn_win32.py", line 33, in init prep_data = spawn.get_preparation_data(process_obj._name) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 143, in get_preparation_data _check_not_importing_main() File "D:\ANACONDA\envs\tryon\lib\multiprocessing\spawn.py", line 136, in _check_not_importing_main is not going to be frozen to produce an executable.''') RuntimeError: An attempt has been made to start a new process before the current process has finished its bootstrapping phase.

This probably means that you are not using fork to start your child processes and you have forgotten to use the proper idiom in the main module: if __name__ == '__main__': freeze_support() ... The "freeze_support()" line can be omitted if the program is not going to be frozen to produce an executable.

Traceback (most recent call last): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 511, in _try_get_batch data = self.data_queue.get(timeout=timeout) File "D:\ANACONDA\envs\tryon\lib\multiprocessing\queues.py", line 105, in get raise Empty queue.Empty

During handling of the above exception, another exception occurred:

Traceback (most recent call last): File "test.py", line 40, in for i, data in enumerate(dataset, start=epoch_iter): File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 576, in next idx, batch = self._get_batch() File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 553, in _get_batch success, data = self._try_get_batch() File "D:\ANACONDA\envs\tryon\lib\site-packages\torch\utils\data\dataloader.py", line 519, in _try_get_batch raise RuntimeError('DataLoader worker (pid(s) {}) exited unexpectedly'.format(pids_str)) RuntimeError: DataLoader worker (pid(s) 3220) exited unexpectedly`

If you could offer a solution, It'll be really helpful. I'm trying to reproduce your results against CP-VTON+ and so far I have not been able.
opened by JonathanMortes 2
problem with training

Hi! Thanks for your efforts. Now I want to train the model with my own dataset, and I have 2 questions. First, is if the custom image with different size (like 800*800) ,do i need to change the network architecture? and how? Another one is the train label number is 14,but the number of CIHP_PGN label is 20.How can I solve it. thanks

opened by amandazw 2
Issues on continuing training

I see there is argument passing as --continue_train and --which_epoch. But I can't identify where and how to use it?

So my question is, how you are continuing the training?

opened by ansarker 0
train_ densepose

Thank you very much for your great work. Which model does Densepose use and how to convert it into an npy file? I use the train generated by train_ densepose is different from yours，can you help me? @geyuying

opened by wang674 1
About batch norm

Hi! I'm studying deep learning. Your work is astonishing. It's very helpful for my study.

I wonder about using batch normalization.

I can find that default option for normalization is instance normalization and there is no declaration of it in shell scripts.

May I ask you for any result of using batch normalization?

Thank you.

opened by snaiws 0
Which dataset should we use to calculate FID score?

I read on some resources that the FID score should be calculated using the dataset of generated outputs and the dataset that was used to train the generator. This feels a bit counter-intuitive since also have the testing dataset (test_pairs) as well in our case. Which datasets should we use to get the FID score? It seems that comparing with the training dataset (which is much larger) I usually get a better FID score for CP-VTON.

opened by mesllo 0
The pretrained model only returns noise

First of all, thanks for your useful repo. When I run your demo with the pre-trained model you provided, the final try-on result only returned some noise images. It seems that the pre-trained weight is not loaded correctly, but I'm sure I put your pre-train models under the folder "VITON_traindata".
Here are the results:

I have no idea why this is happening. Any suggestions?

opened by ml1652 0

Official code for "Parser-Free Virtual Try-on via Distilling Appearance Flows", CVPR 2021

Related tags

Overview

Parser-Free Virtual Try-on via Distilling Appearance Flows, CVPR 2021

Our Test Envirenment

Installation

Run the demo

Dataset

License

Citation

Comments

Owner

This repository will contain the code for the CVPR 2021 paper "GIRAFFE: Representing Scenes as Compositional Generative Neural Feature Fields"

Official code of our work, Unified Pre-training for Program Understanding and Generation [NAACL 2021].

Pytorch implementation of winner from VQA Chllange Workshop in CVPR'17

Global Tracking Transformers, CVPR 2022

Official PyTorch code for ClipBERT, an efficient framework for end-to-end learning on image-text and video-text tasks

This repository contains the official release of the model "BanglaBERT" and associated downstream finetuning code and datasets introduced in the paper titled "BanglaBERT: Combating Embedding Barrier in Multilingual Models for Low-Resource Language Understanding".

Repository to hold code for the cap-bot varient that is being presented at the SIIC Defence Hackathon 2021.

Code for ACL 2021 main conference paper "Conversations are not Flat: Modeling the Intrinsic Information Flow between Dialogue Utterances".

Code for our paper "Mask-Align: Self-Supervised Neural Word Alignment" in ACL 2021

Code for our ACL 2021 paper - ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfer

Code for our ACL 2021 (Findings) Paper - Fingerprinting Fine-tuned Language Models in the wild .

Code for our paper "Transfer Learning for Sequence Generation: from Single-source to Multi-source" in ACL 2021.

Code for papers "Generation-Augmented Retrieval for Open-Domain Question Answering" and "Reader-Guided Passage Reranking for Open-Domain Question Answering", ACL 2021

This repository contains the code, data, and models of the paper titled "XL-Sum: Large-Scale Multilingual Abstractive Summarization for 44 Languages" published in Findings of the Association for Computational Linguistics: ACL 2021.

This is the code for the EMNLP 2021 paper AEDA: An Easier Data Augmentation Technique for Text Classification

This repository contains the code for EMNLP-2021 paper "Word-Level Coreference Resolution"

Code for EMNLP 2021 main conference paper "Text AutoAugment: Learning Compositional Augmentation Policy for Text Classification"

The training code for the 4th place model at MDX 2021 leaderboard A.

Code for the paper in Findings of EMNLP 2021: "EfficientBERT: Progressively Searching Multilayer Perceptron via Warm-up Knowledge Distillation".