PyTorch Implement of Context Encoders: Feature Learning by Inpainting

Last update: Dec 25, 2022

Related tags

Deep Learning context_encoder_pytorch

Overview

Context Encoders: Feature Learning by Inpainting

This is the Pytorch implement of CVPR 2016 paper on Context Encoders

1) Semantic Inpainting Demo

Install PyTorch http://pytorch.org/
Clone the repository

git clone https://github.com/BoyuanJiang/context_encoder_pytorch.git

Demo

Download pre-trained model on Paris Streetview from Google Drive OR BaiduNetdisk

cp netG_streetview.pth context_encoder_pytorch/model/
cd context_encoder_pytorch/model/
# Inpainting a batch iamges
python test.py --netG model/netG_streetview.pth --dataroot dataset/val --batchSize 100
# Inpainting one image 
python test_one.py --netG model/netG_streetview.pth --test_image result/test/cropped/065_im.png

2) Train on your own dataset

Build dataset

Put your images under dataset/train,all images should under subdirectory

dataset/train/subdirectory1/some_images

dataset/train/subdirectory2/some_images

...

Note:For Google Policy,Paris StreetView Dataset is not public data,for research using please contact with pathak22. You can also use The Paris Dataset to train your model
Train

python train.py --cuda --wtl2 0.999 --niter 200

Test

This step is similar to Semantic Inpainting Demo

Comments

problem about torchvision

hi, I was install torchvision from pip, and it worked. but when I install torchvision from source, it occured a problem as:

Traceback (most recent call last):
  File "test.py", line 79, in <module>
    real_cpu, _ = dataiter.next()
  File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 212, in __next__
    return self._process_next_batch(batch)
  File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 239, in _process_next_batch
    raise batch.exc_type(batch.exc_msg)
AttributeError: Traceback (most recent call last):
  File "/usr/local/lib/python2.7/dist-packages/torch/utils/data/dataloader.py", line 41, in _worker_loop
    samples = collate_fn([dataset[i] for i in batch_indices])
  File "build/bdist.linux-x86_64/egg/torchvision/datasets/folder.py", line 116, in __getitem__
    img = self.loader(path)
  File "build/bdist.linux-x86_64/egg/torchvision/datasets/folder.py", line 63, in default_loader
    return pil_loader(path)
  File "build/bdist.linux-x86_64/egg/torchvision/datasets/folder.py", line 45, in pil_loader
    with Image.open(f) as img:
  File "/usr/lib/python2.7/dist-packages/PIL/Image.py", line 528, in __getattr__
    raise AttributeError(name)
AttributeError: __exit__

It is there anything wrong? Thanks

opened by GumpCode 3

Unable to change the input size

I think a larger input size will utilize the GPU source better, but I failed to change the input size, could give me some guidance on which operation leads to a fixed size of imageSize 128, is this size a must?

opened by zhou-rui1 0
can't train on the pretrained model

I wanted to train on the pretrained model, but after using this command, the program prints the model structure and ends. What seems to be the problem? python train.py --cuda --netG model/netG_streetview.pth --wtl2 0.999 --niter 200

opened by moonpieeee 0
Black Boxes in reconstructed Images on CIFAR-10 dataset

I have been running the training.py file on CIFAR-10 dataset without any modifications from the original code. I have been getting black translucent boxes in reconstructed images. Any idea how to fix that?

opened by ankush18194 0
argument 'size' must be tuple of ints, but found element of type float at pos 3

This is what I am getting when I run test.py

Traceback (most recent call last): File "test.py", line 64, in real_center = torch.FloatTensor(opt.batchSize, 3, opt.imageSize/2, opt.imageSize/2) TypeError: new(): argument 'size' must be tuple of ints, but found element of type float at pos 3

any ideas?

opened by caruofc 3
images during training are too dark

Hi, thanks for sharing your great work! I follow your recommendation that use the The Paris Dataset to train the network. After training, when I check the result/train/real or result/train/cropped or result/train/recon folder, I found that all the images are too dark, such as this: real image: cropped image: recon image:

The result of inpainting is effective, but why all the image are so dark?

ps: I do not change anything of the code except dataset/train folder.

opened by liminn 4

PyTorch Implement of Context Encoders: Feature Learning by Inpainting

Related tags

Overview

Context Encoders: Feature Learning by Inpainting

1) Semantic Inpainting Demo

2) Train on your own dataset

Comments

problem about torchvision

Unable to change the input size

can't train on the pretrained model

Black Boxes in reconstructed Images on CIFAR-10 dataset

argument 'size' must be tuple of ints, but found element of type float at pos 3

images during training are too dark

Owner

AOT-GAN for High-Resolution Image Inpainting (codebase for image inpainting)

GAN encoders in PyTorch that could match PGGAN, StyleGAN v1/v2, and BigGAN. Code also integrates the implementation of these GANs.

IAUnet: Global Context-Aware Feature Learning for Person Re-Identification

This repo holds code for TransUNet: Transformers Make Strong Encoders for Medical Image Segmentation

TSP: Temporally-Sensitive Pretraining of Video Encoders for Localization Tasks

RE3: State Entropy Maximization with Random Encoders for Efficient Exploration

Final project code: Implementing MAE with downscaled encoders and datasets, for ESE546 FA21 at University of Pennsylvania

[ICLR 2022] Pretraining Text Encoders with Adversarial Mixture of Training Signal Generators

The pytorch implementation of the paper "text-guided neural image inpainting" at MM'2020

official Pytorch implementation of ICCV 2021 paper FuseFormer: Fusing Fine-Grained Information in Transformers for Video Inpainting.

Unofficial pytorch implementation of 'Image Inpainting for Irregular Holes Using Partial Convolutions'

codes for Image Inpainting with External-internal Learning and Monochromic Bottleneck

CVPR 2021: "Generating Diverse Structure for Image Inpainting With Hierarchical VQ-VAE"

Implementation for "Seamless Manga Inpainting with Semantics Awareness" (SIGGRAPH 2021 issue)

Probabilistic Tracklet Scoring and Inpainting for Multiple Object Tracking

Implementation for our ICCV2021 paper: Internal Video Inpainting by Implicit Long-range Propagation

[ICCV'2021] Image Inpainting via Conditional Texture and Structure Dual Generation