DeblurGAN-tf

DeblurGAN-tf copied to clipboard

Sorry to disturb you. I just use your code and released pretrained model on the 1111 testing images (1280*720) of GOPRO, but the PSNR and SSIM are 25.7 and 0.74...

ChefLiutao

It helps to install packages using pip install

Nilay-marsoniya

InvalidArgumentError (see above for traceback): Incompatible shapes: [1,176,160,3] vs. [1,175,160,3]

1

Do you encounter thre issue? How to solve it? Thanks!

lovepiano

hello,I'd like to ask,why resize the image to 640*360???

lenalinyajing

Q1：Why D-loss is negative and G-loss is very big？ Q2：Why did the training seem to have ended in an epoch, and it took many hours to start training again. Then...

Nakupenda-7

when my train my own data with the deblurGAN, I meet error like this , could you help me. 

yanmenglu

Does it only test the input size (1280, 720) ?

3

When I test a small image, it occure this error. InvalidArgumentError (see above for traceback): Incompatible shapes: [1,48,44,3] vs. [1,47,41,3] [[node generator/add_32 (defined at /home/ares2/workspace/DeblurGAN-tf/Deblur_Net.py:79) = Add[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:GPU:0"](generator/Tanh-0-0-TransposeNCHWToNHWC-LayoutOptimizer, sub)]] Does...

chenyuqing

Intermediate results during training

1

Can you provide some intermediate deblurring results during training, eg, epoch 1,30,150 etc?

unlugi

processing data set

1

Thank you for providing the TF code! But I have another question and I look forward to your help. I want to replace the data set with GOPRO_Large and generate...

lookway