Closed Jilin22 closed 11 months ago
If the network is not trained, the final output of the model is a tensor with an average value of 0.5. Thus, I am curious if you just output the initialized weights. Is the output normal with our provided checkpoint?
The losses converged as expected and the results of validation during training also appear as normal images. But the outputs of the retrained weights are all gray images, while the provided checkpoint produces normal results.
How many iterations have you trained? Besides, can you share me your checkpoint? I have no idea just with your description.
Thank you for sending me the checkpoint. I have checked it. There is no problem for this checkpoint and I can output normal
flare-removed results. Are you using the command python test.py --input test_data/real/input --output result/test_real/other_model/ --model_path experiments/net_g_850000.pth
for inference ?
Hello, I'm trying to reproduce the training process of
Uformer
with the source code provided in this repository. During thetraining process
, thevisualization
results of the validation are the expectednormal images
. But when the trained weights are saved and loaded again to performinference
, the results generated by the model are allgray images
. By debugging the code, I found that forany input
, the final output of the model is a tensor withan average value of 0.5
for each element. What could be the cause of this problem, thank you!