Can someone please help me understand what the names and shapes of the following tensorboard histogram outputs mean about an LSTM model I coded? Thank you!

I understand the terms in the names like bias, gradients, LSTM etc. I do not understand what they are saying about the LSTM model with 3 cells. The LSTM model trains really well with no underfitting or overfitting.

Happy to provide any additional information, please ask!

Model Summary:

Layer (type) Output Shape Param #

lstm_2 (LSTM) (None, 3) 408

LSTM Model in keras: model = Sequential() model.add(LSTM(3, input_shape=(1,30))) model.add(Dense(1, activation='sigmoid'))

Tensorboard output of histograms: dense_1-bias_0 dense_1-bias_0_grad dense_1-kernel_0 dense_1-kernel_gradient dense_1-out lstm_1-bias_0 lstm_1-bias_0-grad lstm_1-kernel_0

Any help is much appreciated.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.