when i use : python tools/train.py configs/recognition/swin/swin_base_patch244_window877_kinetics400_22k.py

an error occurred:

Traceback (most recent call last): File "tools/train.py", line 199, in main() File "tools/train.py", line 154, in main model = build_model( File "/home/pytorch/lib/python3/site-packages/mmaction/models/builder.py", line 70, in build_model return build_localizer(cfg) File "/home/pytorch/lib/python3/site-packages/mmaction/models/builder.py", line 62, in build_localizer return LOCALIZERS.build(cfg) File "/home/pytorch/lib/python3/site-packages/mmcv/utils/registry.py", line 210, in build return self.build_func(*args, **kwargs, registry=self) File "/home/pytorch/lib/python3/site-packages/mmcv/cnn/builder.py", line 26, in build_model_from_cfg return build_from_cfg(cfg, registry, default_args) File "/home/pytorch/lib/python3/site-packages/mmcv/utils/registry.py", line 54, in build_from_cfg raise type(e)(f'{obj_cls.name}: {e}') KeyError: "Recognizer3D: 'SwinTransformer3D is not in the models registry'"

How to solve it?

I was trying to train swin transformer on HMDB51 dataset.

While I referred to "https://github.com/SwinTransformer/Video-Swin-Transformer/blob/master/configs/recognition/tsn/tsn_r50_1x1x8_50e_hmdb51_imagenet_rgb.py" configuration file and "README" files, what I got was an error message.

Here is my configuration file. `base = [ '../../base/models/swin/swin_base.py', '../../base/default_runtime.py' ] model=dict(backbone=dict(patch_size=(2,4,4), drop_path_rate=0.3), test_cfg=dict(max_testing_views=4), cls_head=dict(num_classes=174))

dataset settings

dataset_type = 'RawframeDataset' data_root = 'data/hmdb51/rawframes' data_root_val = 'data/hmdb51/rawframes' ann_file_train = 'data/hmdb51/hmdb51_train_split_1_rawframes.txt' ann_file_val = 'data/hmdb51/hmdb51_val_split_1_rawframes.txt' ann_file_test = 'data/hmdb51/hmdb51_val_split_1_rawframes.txt' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) train_pipeline = [ dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='RandomResizedCrop'), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict(type='Flip', flip_ratio=0.5), dict(type='Normalize', **img_norm_cfg), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs', 'label']) ] val_pipeline = [ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict(type='Normalize', **img_norm_cfg), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] test_pipeline = [ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict(type='Normalize', **img_norm_cfg), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] data = dict( videos_per_gpu=2, workers_per_gpu=1, val_dataloader=dict( videos_per_gpu=1, workers_per_gpu=1 ), test_dataloader=dict( videos_per_gpu=1, workers_per_gpu=1 ), train=dict( type=dataset_type, ann_file=ann_file_train, data_prefix=data_root, pipeline=train_pipeline), val=dict( type=dataset_type, ann_file=ann_file_val, data_prefix=data_root_val, pipeline=val_pipeline), test=dict( type=dataset_type, ann_file=ann_file_test, data_prefix=data_root_val, pipeline=test_pipeline)) evaluation = dict( interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy'])

optimizer

optimizer = dict(type='AdamW', lr=1e-3, betas=(0.9, 0.999), weight_decay=0.05, paramwise_cfg=dict(custom_keys={'absolute_pos_embed': dict(decay_mult=0.), 'relative_position_bias_table': dict(decay_mult=0.), 'norm': dict(decay_mult=0.), 'backbone': dict(lr_mult=0.1)}))

learning policy

lr_config = dict( policy='CosineAnnealing', min_lr=0, warmup='linear', warmup_by_epoch=True, warmup_iters=2.5 ) total_epochs = 30

runtime settings

checkpoint_config = dict(interval=1) work_dir = './work_dirs/hmdb51_swin_base_patch244_window877.py' find_unused_parameters = False

do not use mmdet version fp16

fp16 = None

optimizer_config = dict(

type="DistOptimizerHook",

update_interval=8,

grad_clip=None,

coalesce=True,

bucket_size_mb=-1,

use_fp16=True,

)

`

I tried to execute code by "python tools/train.py configs/recognition/swin/swin_base_patch244_window877_hmdb51.py" failed.

And following error log is given.

• root@c265ec69239e:/home/Video-Swin-Transformer# python tools/train.py configs/recognition/swin/swin_base_patch244_window877_hmdb51.py 2022-07-07 05:46:41,569 - mmaction - INFO - Environment info:

sys.platform: linux Python: 3.7.7 (default, Mar 26 2020, 15:48:22) [GCC 7.3.0] CUDA available: True GPU 0: Tesla V100-PCIE-32GB CUDA_HOME: /usr/local/cuda NVCC: Build cuda_11.0_bu.TC445_37.28845127_0 GCC: gcc (Ubuntu 5.4.0-6ubuntu1~16.04.12) 5.4.0 20160609 PyTorch: 1.7.1 PyTorch compiling details: PyTorch built with:

• GCC 7.3
• C++ Version: 201402
• Intel(R) oneAPI Math Kernel Library Version 2021.2-Product Build 20210312 for Intel(R) 64 architecture applications
• Intel(R) MKL-DNN v1.6.0 (Git Hash 5ef631a030a6f73131c77892041042805a06064f)
• OpenMP 201511 (a.k.a. OpenMP 4.5)
• NNPACK is enabled
• CPU capability usage: AVX2
• CUDA Runtime 11.0
• NVCC architecture flags: -gencode;arch=compute_37,code=sm_37;-gencode;arch=compute_50,code=sm_50;-gencode;arch=compute_60,code=sm_60;-gencode;arch=compute_61,code=sm_61;-gencode;arch=compute_70,code=sm_70;-gencode;arch=compute_75,code=sm_75;-gencode;arch=compute_80,code=sm_80;-gencode;arch=compute_37,code=compute_37
• CuDNN 8.0.5
• Magma 2.5.2
• Build settings: BLAS=MKL, BUILD_TYPE=Release, CXX_FLAGS= -Wno-deprecated -fvisibility-inlines-hidden -DUSE_PTHREADPOOL -fopenmp -DNDEBUG -DUSE_FBGEMM -DUSE_QNNPACK -DUSE_PYTORCH_QNNPACK -DUSE_XNNPACK -DUSE_VULKAN_WRAPPER -O2 -fPIC -Wno-narrowing -Wall -Wextra -Werror=return-type -Wno-missing-field-initializers -Wno-type-limits -Wno-array-bounds -Wno-unknown-pragmas -Wno-sign-compare -Wno-unused-parameter -Wno-unused-variable -Wno-unused-function -Wno-unused-result -Wno-unused-local-typedefs -Wno-strict-overflow -Wno-strict-aliasing -Wno-error=deprecated-declarations -Wno-stringop-overflow -Wno-psabi -Wno-error=pedantic -Wno-error=redundant-decls -Wno-error=old-style-cast -fdiagnostics-color=always -faligned-new -Wno-unused-but-set-variable -Wno-maybe-uninitialized -fno-math-errno -fno-trapping-math -Werror=format -Wno-stringop-overflow, PERF_WITH_AVX=1, PERF_WITH_AVX2=1, PERF_WITH_AVX512=1, USE_CUDA=ON, USE_EXCEPTION_PTR=1, USE_GFLAGS=OFF, USE_GLOG=OFF, USE_MKL=ON, USE_MKLDNN=ON, USE_MPI=OFF, USE_NCCL=ON, USE_NNPACK=ON, USE_OPENMP=ON,

TorchVision: 0.8.2 OpenCV: 3.4.2 MMCV: 1.3.3 MMCV Compiler: GCC 5.4 MMCV CUDA Compiler: not available MMAction2: 0.15.0+db018fb

2022-07-07 05:46:41,570 - mmaction - INFO - Distributed training: False 2022-07-07 05:46:42,085 - mmaction - INFO - Config: model = dict( type='Recognizer3D', backbone=dict( type='SwinTransformer3D', patch_size=(2, 4, 4), embed_dim=128, depths=[2, 2, 18, 2], num_heads=[4, 8, 16, 32], window_size=(8, 7, 7), mlp_ratio=4.0, qkv_bias=True, qk_scale=None, drop_rate=0.0, attn_drop_rate=0.0, drop_path_rate=0.3, patch_norm=True), cls_head=dict( type='I3DHead', in_channels=1024, num_classes=174, spatial_type='avg', dropout_ratio=0.5), test_cfg=dict(average_clips='prob', max_testing_views=4)) checkpoint_config = dict(interval=1) log_config = dict(interval=20, hooks=[dict(type='TextLoggerHook')]) dist_params = dict(backend='nccl') log_level = 'INFO' load_from = None resume_from = None workflow = [('train', 1)] dataset_type = 'RawframeDataset' data_root = 'data/hmdb51/rawframes' data_root_val = 'data/hmdb51/rawframes' ann_file_train = 'data/hmdb51/hmdb51_train_split_1_rawframes.txt' ann_file_val = 'data/hmdb51/hmdb51_val_split_1_rawframes.txt' ann_file_test = 'data/hmdb51/hmdb51_val_split_1_rawframes.txt' img_norm_cfg = dict( mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False) train_pipeline = [ dict(type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='RandomResizedCrop'), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs', 'label']) ] val_pipeline = [ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] test_pipeline = [ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ] data = dict( videos_per_gpu=2, workers_per_gpu=1, val_dataloader=dict(videos_per_gpu=1, workers_per_gpu=1), test_dataloader=dict(videos_per_gpu=1, workers_per_gpu=1), train=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_train_split_1_rawframes.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='RandomResizedCrop'), dict(type='Resize', scale=(224, 224), keep_ratio=False), dict(type='Flip', flip_ratio=0.5), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs', 'label']) ]), val=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_val_split_1_rawframes.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ]), test=dict( type='RawframeDataset', ann_file='data/hmdb51/hmdb51_val_split_1_rawframes.txt', data_prefix='data/hmdb51/rawframes', pipeline=[ dict( type='SampleFrames', clip_len=1, frame_interval=1, num_clips=8, test_mode=True), dict(type='RawFrameDecode'), dict(type='Resize', scale=(-1, 256)), dict(type='CenterCrop', crop_size=256), dict(type='Flip', flip_ratio=0), dict( type='Normalize', mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_bgr=False), dict(type='FormatShape', input_format='NCHW'), dict(type='Collect', keys=['imgs', 'label'], meta_keys=[]), dict(type='ToTensor', keys=['imgs']) ])) evaluation = dict( interval=5, metrics=['top_k_accuracy', 'mean_class_accuracy']) optimizer = dict( type='AdamW', lr=0.001, betas=(0.9, 0.999), weight_decay=0.05, paramwise_cfg=dict( custom_keys=dict( absolute_pos_embed=dict(decay_mult=0.0), relative_position_bias_table=dict(decay_mult=0.0), norm=dict(decay_mult=0.0), backbone=dict(lr_mult=0.1)))) lr_config = dict( policy='CosineAnnealing', min_lr=0, warmup='linear', warmup_by_epoch=True, warmup_iters=2.5) total_epochs = 30 work_dir = './work_dirs/hmdb51_swin_base_patch244_window877.py' find_unused_parameters = False gpu_ids = range(0, 1) omnisource = False module_hooks = []

2022-07-07 05:46:49,300 - mmaction - INFO - Start running, host: root@c265ec69239e, work_dir: /home/Video-Swin-Transformer/work_dirs/hmdb51_swin_base_patch244_window877.py 2022-07-07 05:46:49,300 - mmaction - INFO - workflow: [('train', 1)], max: 30 epochs Traceback (most recent call last): File "tools/train.py", line 200, in main() File "tools/train.py", line 196, in main meta=meta) File "/home/Video-Swin-Transformer/mmaction/apis/train.py", line 195, in train_model runner.run(data_loaders, cfg.workflow, cfg.total_epochs, **runner_kwargs) File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 125, in run epoch_runner(data_loaders[i], **kwargs) File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 50, in train self.run_iter(data_batch, train_mode=True, **kwargs) File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/epoch_based_runner.py", line 30, in run_iter **kwargs) File "/opt/conda/lib/python3.7/site-packages/mmcv/parallel/data_parallel.py", line 67, in train_step return self.module.train_step(*inputs[0], **kwargs[0]) File "/home/Video-Swin-Transformer/mmaction/models/recognizers/base.py", line 294, in train_step losses = self(imgs, label, return_loss=True, **aux_info) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/Video-Swin-Transformer/mmaction/models/recognizers/base.py", line 256, in forward return self.forward_train(imgs, label, **kwargs) File "/home/Video-Swin-Transformer/mmaction/models/recognizers/recognizer3d.py", line 19, in forward_train x = self.extract_feat(imgs) File "/opt/conda/lib/python3.7/site-packages/mmcv/runner/fp16_utils.py", line 95, in new_func return old_func(*args, **kwargs) File "/home/Video-Swin-Transformer/mmaction/models/recognizers/base.py", line 157, in extract_feat x = self.backbone(imgs) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/Video-Swin-Transformer/mmaction/models/backbones/swin_transformer.py", line 652, in forward x = self.patch_embed(x) File "/opt/conda/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl result = self.forward(*input, **kwargs) File "/home/Video-Swin-Transformer/mmaction/models/backbones/swin_transformer.py", line 441, in forward _, _, D, H, W = x.size() ValueError: not enough values to unpack (expected 5, got 4)

PLEASE SOMEBODY HELP ME!!!

Hi, thanks for this fascinating work! I want to follow the instructions bash tools/dist_train.sh <CONFIG_FILE> <GPU_NUM> --cfg-options load_from=<PRETRAIN_MODEL> [model.backbone.use_checkpoint=True] [other optional arguments] to run the program, but I don't know where I can find the pretrain model. So, I need some help, thanks all of you!

I get the image shape from dataloader, the image shape is torch.Size([1, 12, 3, 32, 224, 224]). I know it's [batch_size, ?, RGB, frames, H, W], but I don't know why it has "12" in a video data. Does anyone know that dimension is?

In ./tools/test.py: data_loader = build_dataloader(dataset, **dataloader_setting) for i in data_loader: print("img shape: ", i['imgs'].size())

Thank you.

For the original configuration file, is it all 8 GPU configurations?

Specifically, is the base_22k model on 8 GPUs with a batch size of 8 and a learning rate of 3e-4? For others, is the model on 8 GPUs with a batch size of 8 and a learning rate of 1e-3?

I used 4 gpus(2080ti) to train swin_small with config swin_small_patch244_window877_kinetics400_1k.py. The dataset I used is hacs(50w videos). The following is some of my training log:

I find that the train iteration is abnormally large based on my config(dataset size(50w) and batch_size(8)), which leads to the long training time. Is that normal?

The download links for Kinetics 400 pretrained models are on pan.baid.com. Many people are not able to download these at all because you need to create an account (with a phone number) to download files from that site. If you are in germany or the UK, like me, it is not possible to create an account to download these. Please host them somewhere else to make them available to the general public.

In the subsection 3D relative position bias of your paper, a bias is added in the self-attention computaion. I don't fully understand it.

According to your description, Q,K,V are all matrices with P*M^2 rows and d columns, so QK^T will be a square matrix with P*M^2 rows and P*M^2 columns. To make the summation valid, the 3D relative position bias B should also be a square matrix wtih P*M^2 rows and P*M^2 columns. So how are the values in B are set? Specifically, how the member B(i,j) of B is set ? I can't get any link between B and

I got to the end of the installation and was running the script to do the check to see if installation was done correctly.

In the open_mmlab environment, the very last line of the script inference_recognizer(model, 'demo/demo.mp4', 'demo/label_map_k400.txt') received an error AttributeError: 'Recognizer2D' object has no attribute 'demo/label_map_k400'

How to proceed?

Thank You Tom

Hello. Thank you for providing a good paper with a good code.

I had a question while experimenting with video swin transformer.

Input sizes (1, 3, 8, 384, 384) swintransformer3D( patch_size=(2,4,4), all of rest is default settings)

The output size per layer was measured in the forward section. The result is : after 1 layer output shape : torch.Size([1, 192, 4, 48, 48]) after 2 layer output shape : torch.Size([1, 384, 4, 24, 24]) after 3 layer output shape : torch.Size([1, 768, 4, 12, 12]) after 4 layer output shape : torch.Size([1, 768, 4, 12, 12])

As the paper illustrates, after 1 layer output shape : torch.Size([1, 96, 4, 96, 96]) after 2 layer output shape : torch.Size([1, 192, 4, 48, 48]) after 3 layer output shape : torch.Size([1, 384, 4, 24, 24]) after 4 layer output shape : torch.Size([1, 768, 4, 12, 12]) I think this is right.

I know it's hard work, but can I ask you to check it out?

I used swin-B to train on the epic-kitchens dataset, but it takes me almost 27 hours for one epoch training (mixed precision was already applied). I used 4 V100 GPUs, batch_size=8. Is this the normal time for training?

This command python3 tools/deployment/pytorch2onnx.py configs/recognition/swin/swin_tiny_patch244_window877_kinetics400_1k.py swin_tiny_patch244_window877_kinetics400_1k.pth outputs this error :

/opt/conda/lib/python3.8/site-packages/torch/functional.py:478: UserWarning: torch.meshgrid: in an upcoming release, it will be required to pass the indexing argument. (Triggered internally at /opt/pytorch/pytorch/aten/src/ATen/native/TensorShape.cpp:2966.)
  return _VF.meshgrid(tensors, **kwargs)  # type: ignore[attr-defined]
Use load_from_local loader
Traceback (most recent call last):
  File "tools/deployment/pytorch2onnx.py", line 163, in <module>
    pytorch2onnx(
  File "tools/deployment/pytorch2onnx.py", line 67, in pytorch2onnx
    torch.onnx.export(
  File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 479, in export
    _export(
  File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 1411, in _export
    graph, params_dict, torch_out = _model_to_graph(
  File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 1050, in _model_to_graph
    graph, params, torch_out, module = _create_jit_graph(model, args)
  File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 925, in _create_jit_graph
    graph, torch_out = _trace_and_get_graph_from_model(model, args)
  File "/opt/conda/lib/python3.8/site-packages/torch/onnx/utils.py", line 833, in _trace_and_get_graph_from_model
    trace_graph, torch_out, inputs_states = torch.jit._get_trace_graph(
  File "/opt/conda/lib/python3.8/site-packages/torch/jit/_trace.py", line 1175, in _get_trace_graph
    outs = ONNXTracedModule(f, strict, _force_outplace, return_inputs, _return_inputs_states)(*args, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1186, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/torch/jit/_trace.py", line 127, in forward
    graph, out = torch._C._create_graph_by_tracing(
  File "/opt/conda/lib/python3.8/site-packages/torch/jit/_trace.py", line 118, in wrapper
    outs.append(self.inner(*trace_inputs))
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1186, in _call_impl
    return forward_call(*input, **kwargs)
  File "/opt/conda/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1174, in _slow_forward
    result = self.forward(*input, **kwargs)
TypeError: forward_dummy() got multiple values for argument 'softmax'

Dear researchers,

Thank you for this very nice piece of of work.

Can you also provide the weight of the Swin-L as described in the paper ?

Best regards,

你好,我在使用的时候遇到一个问题, 参考 infer 的代码构造 data_loader ,加载视频文件,但是在处理到某个视频的时候报错了 decord._ffi.base.DECORDError: [16:51:53] /io/decord/src/video/video_reader.cc:432: Error: av_read_frame failed with 1094995529

定位到的错误应该是这个 mmaction/datasets/pipelines/loading.py", line 966, in __call__ container = decord.VideoReader(file_obj, num_threads=self.num_threads) 我对提示错误的视频进行测试,可以正常播放以及单独使用 decord.VideoReader 加载都是没有问题的, 现在就觉得很奇怪,不知道是否有空可以解答一下, 谢谢啦

Hello, I want to know how I can call the output tensor of an intermediate layer like the last FC. Through the OutputHook function, how should the name of the layer be passed?

inference_recognizer(model, video,labels,outputs ='fc1')?

Hello, I have noticed that the swin transformer V2 paper has been published. There are experiments on video action classification in the paper, and the results are better than those in V1. Is there any plan to release video swin transformer code and pre-trained models based on V2?

Your work is very valuable and helpful to me. I look forward to your reply. Thank you very much!