I made input for the CNN, However I am getting error
TypeError: model() got an unexpected keyword argument 'batch_size'
Let me paste all the function here:
def model(x_train, num_labels, LSTM_units, num_conv_filters, batch_size, F, D):
"""
The proposed model with CNN layer, LSTM RNN layer and self attention layers.
Inputs:
- x_train: required for creating input shape for RNN layer in Keras
- num_labels: number of output classes (int)
- LSTM_units: number of RNN units (int)
- num_conv_filters: number of CNN filters (int)
- batch_size: number of samples to be processed in each batch
- F: the attention length (int)
- D: the length of the output (int)
Returns
- model: A Keras model
"""
cnn_inputs = Input(shape=(x_train.shape[1], x_train.shape[2], 1), batch_size=batch_size, name='rnn_inputs') # Getting error on this line
cnn_layer = Conv2D(num_conv_filters, kernel_size = (1, x_train.shape[2]), strides=(1, 1), padding='valid', data_format="channels_last")
cnn_out = cnn_layer(cnn_inputs)
sq_layer = Lambda(lambda x: K.squeeze(x, axis = 2))
sq_layer_out = sq_layer(cnn_out)
rnn_layer = LSTM(LSTM_units, return_sequences=True, name='lstm', return_state=True) #return_state=True
rnn_layer_output, _, _ = rnn_layer(sq_layer_out)
encoder_output, attention_weights = SelfAttention(size=F, num_hops=D, use_penalization=False, batch_size = batch_size)(rnn_layer_output)
dense_layer = Dense(num_labels, activation = 'softmax')
dense_layer_output = dense_layer(encoder_output)
model = Model(inputs=cnn_inputs, outputs=dense_layer_output)
print (model.summary())
return model
I have put the comment on the line where I am "Getting Error". Here is the track back: Traceback (most recent call last):
File "C:\Program Files\JetBrains\PyCharm 2020.2.1\plugins\python\helpers\pydev\pydevd.py", line 1448, in _exec
pydev_imports.execfile(file, globals, locals) # execute the script
File "C:\Program Files\JetBrains\PyCharm 2020.2.1\plugins\python\helpers\pydev\_pydev_imps\_pydev_execfile.py", line 18, in execfile
exec(compile(contents+"\n", file, 'exec'), glob, loc)
File "C:/Users/Nafees Ahmed/PycharmProjects/encodingHumanActivity-master/codes/model_proposed/model_with_self_attn.py", line 133, in <module>
rnn_model = model(x_train = X_train_, num_labels = NUM_LABELS, LSTM_units = LSTM_UNITS, \
TypeError: model() got an unexpected keyword argument 'batch_size'
python-BaseException
The batch_size parameter needs to be declared in the model.fit() function, not as part of the input definition.