Hi, something interesting here:
https://github.com/zabir-nabil/text-image-denoiser/blob/master/infer_demo.py

When we tried to use your code, we noticed that you plot y. I guess it should be output, right?

cnt = 0
t = 0
for i, data in enumerate(dataloader, 0):
# get the inputs; data is a list of [inputs, labels]
X, y = data
t1 = time.time()
X = X.cuda()
y = y.cuda()
outputs = model(X)
t2 = time.time()

t += (t2-t1)

plot_save(X[0,:,:,:].cpu(), **y[0,:,:,:].cpu()**, 'unet_demo/', cnt)

cnt += 1

if cnt == 100:
    break

print(f'Time average: {t/100.}')

Hi, do you have pre-trained data that I can use on the fly?

The given link for the pre-trained model is not working can you please provide the new one