New answers tagged

2 votes

What may cause the CNN layer weight regularizer to reduce the model accuracy

In general, I stumbled across voices in literature that we shouldn't use dropout with such a big parameter for shallow networks, as it can violate their capabilities. Example: Piotrowski, A. P., ...
Tomasz Witkowski's user avatar
0 votes

Scikit-learn and TensorFlow with very different MLP models

I know that your question was asked almost a year ago, but still maybe someone will find it useful. There are two problems: The first is you are using softmax activation, yet only have one output ...
Martinez's user avatar
1 vote
Accepted

How do I best approach a multiple-target binary classification in Tensorflow/Keras?

The term you would use for that is "multilabel classification". It is certainly possible to do so in Tensorflow, although I would say it is more frequent to see it in examples of image ...
noe's user avatar
  • 23.8k
0 votes

Is there a way to make keras custom test_step aware of the call being made from model.fit and model.evaluate

There is a nice keras.backend.in_train_phase() function for that. It is not documented (intentionally) but its signature is: ...
bio's user avatar
  • 111
2 votes
Accepted

activation=tf.keras.activations.relu vs activation='relu'

Your results were probably result of the randomness in the training. Both activation=tf.keras.activations.relu and ...
noe's user avatar
  • 23.8k
2 votes
Accepted

Confusion with tensorflow's Sequential Dense Layers

Keras expects the inputs $X$ to be batched, i.e., of shape $B\times D$ in your case (for a feed-forward NN), where $B$ is the batch size (by default is 32, which can be assigned in ...
Luca Anzalone's user avatar
0 votes

Binary classification using RNN not going beyond 50% accuracy

Found the issue. The y were not correct to the corresponding X.
Prabhjot Singh Rai's user avatar
0 votes

Binary classification using RNN not going beyond 50% accuracy

To split your dataset try this : ...
aRedDish's user avatar

Top 50 recent answers are included