-
Notifications
You must be signed in to change notification settings - Fork 31
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Why the FCN needs a pre-trained weight? #5
Comments
Thank you for your question.
The pre-trained weights are used in order to make the training of the network stable.
Maybe yes, but the training will be unstable especially at the beginning. |
@rfuruta I have an idea of my paper to use your code, but the reward is only a scalar value for the whole image, rather than the pixel-wise rewards. Can I use PixelRL? Maybe the difficult is that many agent & action has to determine one reward. |
I do not think PixelRL will work in such a situation. Training PixelRL with one reward is a remaining problem. |
@rfuruta Why doesn't work? Does it because that so many actions have to be made to obtain one reward? |
I guessed it would not work because the reward value is determined by many actions. |
@machanic Hi, can you share us your code of PyTorch version of PixelRL? Thank you very much. |
|
I notice that you use
chainer.serializers.load_npz('../denoise_with_convGRU/model/pretrained_15.npz', net)
to load a pre-trained FCN weight? Why needs the pre-trained FCN weight?I currently translate the code into PyTorch version, Can I train the FCN directly without loading pretrained weights?
Thank you!
The text was updated successfully, but these errors were encountered: