-
Notifications
You must be signed in to change notification settings - Fork 279
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
about load model #2
Comments
Hello, |
#8 and this one are related. It's a bug that frustratingly keeps on reappearing in all of the versions of this codebase, and moreover conceals another bug in GetImag/GetReal/GetAbs. Let me patch things. |
@CedricChing Can you confirm that with the latest push, a freshly-started run that is checkpointed and then killed can be reloaded? You can speed this up by using the minimum number of blocks, |
@obilaniu I've solved the problem. The "sqrt_init" initializer of "gamma_diag_initializer" in file "conv.py" is a bug. And the bug (Missing Layer) about GetReal/GetImag confused me for a long time. Luckily, I solved the bug in my way. I've read the latest code. Your solution is much better than mine. THANKS ANYWAY for your reply and your open source code. ^_^ |
@CedricChing Should we close this and the other issue? |
Fixes for Python3 and Keras-2.3.1
how to solve this problem: 'ValueError: Unknown initializer: sqrt_init'
The text was updated successfully, but these errors were encountered: