CODEWITHSUNDEEP
tensorflow
siby
siby

Reputation: 777

Weights and biases in tf.layers module in TensorFlow 1.0

How do you access the weights and biases when using tf.layers module in TensorFlow 1.0? The advantage of tf.layers module is that you don't have to separately create the variables when making a fully connected layer or convolution layer.

I couldn't not find anything in the documentation regarding accessing them or adding them in summaries after they are created.

Upvotes: 1

Views: 844

Answers (1)

ruoho ruotsi
ruoho ruotsi

Reputation: 1313

I don't think tf.layers (i.e. TF core) support summaries yet. Rather you have to use what's in contrib ...knowing that stuff in contrib, may eventually move into core but that the current API may change:

The layers module defines convenience functions summarize_variables, summarize_weights and summarize_biases, which set the collection argument of summarize_collection to VARIABLES, WEIGHTS and BIASES, respectively.

Checkout:

Upvotes: 2

Related Questions