CODEWITHSUNDEEP
pythontensorflowkerastypeerrorlstm
Desiigner
Desiigner

Reputation: 69

Keras LSTM: Getting TypeError : 'list' object cannot be interpreted as an integer on train_on_batch

I am trying to write my first LSTM with Keras and i'm stucking. That are my training data structure: x_data = [1265, 12] y_data = [1265, 3]

x_data example: [102.7, 100.69, 103.39, 99.6, 319037.0, 365230.0, 1767412, 102.86, 13.98]

My Model looks like the following: 

    self.model = Sequential()
    self._opt_cells = 12

    self.model.add(LSTM(units = self._opt_cells, return_sequences = True, input_shape = (1265, 12)))
    self.model.add(Dropout(0.2))

    self.model.add(LSTM(units = self._opt_cells, return_sequences = True))
    self.model.add(Dropout(0.2))

    self.model.add(LSTM(units = self._opt_cells, return_sequences = True))
    self.model.add(Dropout(0.2))

    self.model.add(LSTM(units = self._opt_cells))
    self.model.add(Dropout(0.2))

    self.model.add(Dense(3, activation = 'softmax'))

    self.model.compile(loss='categorical_crossentropy', optimizer='Adam', metrics=['accuracy'])

This line throwing the error: 

        cost = self.model.train_on_batch(np.reshape(x_data, [x_data[0], x_data[1], 1]), np.reshape(y_data, [y_data[0], y_data[1], 1]))

I have no idea why i am receiving the error: TypeError : 'list' object cannot be interpreted as an integer

Thanks for help

Upvotes: 0

Views: 291

Answers (1)

Charlie
Charlie

Reputation: 21

Look at the np.reshape function here: https://docs.scipy.org/doc/numpy/reference/generated/numpy.reshape.html

It says: numpy.reshape(a, newshape, order='C')

The second argument ('newshape') is the shape you wish to convert your array to. In your case, the shape you are converting to is 'x_data[1]' and 'y_data[1]', which is probably a float. As I don't know how your data set looks like, I can not tell you more than this. So, take a closer look at the documentation of the np.reshape function()

Upvotes: 2

Related Questions