parameters of deep learning for STFT and DWT input data

Question

I create CNN model on STFT data and Discrete wavelet transform data. I want to get the number of the weights and biases of my deep learning model on the 2 input data in python . How to do that ??

Any help would be appreciated.

code:

def createModel():
   with tf.device("cpu"):
        input_shape=(1, 22, 5, 3844)
        model = Sequential()
        model.add(Conv3D(16, (22, 5, 5), strides=(1, 2, 2), padding='same',activation='relu',data_format= "channels_first", input_shape=input_shape))

        model.add(keras.layers.MaxPooling3D(pool_size=(1, 2, 2),data_format= "channels_first",  padding='same'))

        model.add(BatchNormalization())
        model.add(Conv3D(32, (1, 3, 3), strides=(1, 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding

        model.add(keras.layers.MaxPooling3D(pool_size=(1,2, 2),data_format= "channels_first", ))
        model.add(BatchNormalization())
        model.add(Conv3D(64, (1,3, 3), strides=(1, 1,1), padding='same',data_format= "channels_first",  activation='relu'))#incertezza se togliere padding
        model.add(keras.layers.MaxPooling3D(pool_size=(1,2, 2),data_format= "channels_first",padding='same' ))
        model.add(BatchNormalization())
        model.add(Dense(64, input_dim=64,kernel_regularizer=regularizers.l2(0.0001), activity_regularizer=regularizers.l1(0.0001)))
        model.add(Flatten())
        model.add(Dropout(0.5))
        model.add(Dense(256, activation='sigmoid'))
        model.add(Dropout(0.5))
        model.add(Dense(2, activation='softmax'))
        opt_adam = keras.optimizers.Adam(lr=0.001, beta_1=0.9, beta_2=0.999, epsilon=1e-08, decay=0.0)
        model.compile(loss='categorical_crossentropy', optimizer=opt_adam, metrics=['accuracy'])
    return model

Answer 1

First thing you should do is installing h5py

pip install h5py

And then you can explore keras model inside this file

import h5py
f = h5py.File('mytestfile.hdf5', 'r')
# layer names of your model
list(f.keys())
# you can use this layers as index
d = f['dense']['dense_1']['kernel:0']