Skip to content
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

Recognize InputLayer #4

Closed
mnijh opened this issue May 18, 2020 · 1 comment
Closed

Recognize InputLayer #4

mnijh opened this issue May 18, 2020 · 1 comment

Comments

@mnijh
Copy link

mnijh commented May 18, 2020

Hi congratulation for the great work!

A minor thing I realized during initial testing.
If the input layer of the model is given by

model.add(keras.models.InputLayer(input_shape=5))

instead of

model.add(Dense(8, input_dim=5, activation='relu'))

then this results in the error:

Traceback (most recent call last):
  File "convert_weights.py", line 353, in <module>
    h5_to_txt(
  File "convert_weights.py", line 183, in h5_to_txt
    info = model_config['config']['layers'][0]['config']['batch_input_shape'][1]
@jordanott
Copy link
Contributor

Thanks for pointing this out. A number of people have run into this issue with the input layers. I'll see about incorporating it in.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

2 participants