Using Dense(activation=softmax) is computationally equivalent to first add Dense and then add Activation(softmax). However there is one advantage of the second approach – you could retrieve the outputs of the last layer (before activation) out of such defined model. In the first approach – it’s impossible.
Model.fit_generator is deprecated starting from tensorflow 2.1.0 which is currently is in rc1. You can find the documentation for tf-2.1.0-rc1 here: https://www.tensorflow.org/versions/r2.1/api_docs/python/tf/keras/Model#fit As you can see the first argument of the Model.fit can take a generator so just pass it your generator.
LSTM is a recurrent layer LSTMCell is an object (which happens to be a layer too) used by the LSTM layer that contains the calculation logic for one step. A recurrent layer contains a cell object. The cell contains the core code for the calculations of each step, while the recurrent layer commands the cell … Read more
UPDATE – 1/15/2020: the current best practice for small batch sizes should be to feed inputs to the model directly – i.e. preds = model(x), and if layers behave differently at train / inference, model(x, training=False). Per latest commit, this is now documented. I haven’t benchmarked these, but per the Git discussion, it’s also worth … Read more
The predict_classes method is only available for the Sequential class (which is the class of your first model) but not for the Model class (the class of your second model). With the Model class, you can use the predict method which will give you a vector of probabilities and then get the argmax of this … Read more
Regularizers that’ll work best will depend on your specific architecture, data, and problem; as usual, there isn’t a single cut to rule all, but there are do’s and (especially) don’t’s, as well as systematic means of determining what’ll work best – via careful introspection and evaluation. How does RNN regularization work? Perhaps the best approach … Read more
After spending a lot of time, this is how I fixed it. I still don’t know why but when the code is modified as follows, it works fine. I got the idea after seeing this solution for a similar but slightly different issue. class_weights = compute_class_weight( class_weight = “balanced”, classes = np.unique(train_classes), y = train_classes … Read more
Quoting an answer mentioned in github, you need to specify the dimension ordering: Keras is a wrapper over Theano or Tensorflow libraries. Keras uses the setting variable image_dim_ordering to decide if the input layer is Theano or Tensorflow format. This setting can be specified in 2 ways – specify ‘tf’ or ‘th’ in ~/.keras/keras.json like … Read more
Your first one consists of a 100 neurons input layer connected to one single output neuron Your second one consists of a 100 neurons input layer, one hidden layer of 32 neurons and one output layer of one single neuron. You have to think of your first layer as your input layer (with the same … Read more
TLDR: It depends on your function and whether you are in production or development. Don’t use tf.function if you want to be able to debug your function easily, or if it falls under the limitations of AutoGraph or tf.v1 code compatibility. I would highly recommend watching the Inside TensorFlow talks about AutoGraph and Functions, not … Read more