Restormer
Restormer copied to clipboard
swz30
[CVPR 2022--Oral] Restormer: Efficient Transformer for High-Resolution Image Restoration. SOTA for motion deblurring, image deraining, denoising (Gaussian/real data), and defocus deblurring.
Deraining: python test.py: /root/miniconda3/lib/python3.8/site-packages/torchvision/transforms/functional_tensor.py:5: UserWarning: The torchvision.transforms.functional_tensor module is deprecated in 0.15 and will be **removed in 0.17**. Please don't rely on it. You probably just need to use APIs...
ImportError: cannot import name 'create_dataloader' from 'basicsr.data' As far i have seen basicsr package i never seen a function called create_dataloader, create_dataset where do you import all these? Is it...
GoPro Training Data! Authentication needed Go to the following url in your browser: https://accounts.google.com/o/oauth2/auth?access_type=offline&client_id=367116221053-7n0vf5akeru7on6o2fjinrecpdoe99eg.apps.googleusercontent.com&redirect_uri=urn%3Aietf%3Awg%3Aoauth%3A2.0%3Aoob&response_type=code&scope=https%3A%2F%2Fwww.googleapis.com%2Fauth%2Fdrive&state=state Enter verification code: how to solve this?
I've already run Restormer on V100 32GB with image 512 x 512. VRAM significantly increases after attention layers and out of memory at `out_dec_level1 = self.decoder_level1(inp_dec_level1)`. I checked Torch 2.0.1,...
size mismatch for patch_embed.proj.weight: copying a param with shape torch.Size([48, 6, 3, 3]) from checkpoint, the shape in current model is torch.Size([48, 3, 3, 3]). {'inp_channels': 3, 'out_channels': 3, 'dim':...
Since it work well on a range of image restoration tasks, it should also work for SR.
python setup.py develop --no_cuda_ext安装不上是什么原因
训练时会卡在INFO: Saving models and training states.有没有大佬知道怎么解决？
Dear author, Very impressive works for image resolution task. I have a question about DPDD dual-view indoor and outdoor image index, which is not avaliable, could you share with us,...
Thanks for your excellent work! I have two questions about your implementations. 1). It seems that I did not find any implementations about positional embedding in your code. Why the...
