valueerror

I use pickle to dump a file on python 3, and I use pickle to load the file on python 2, the ValueError appears. So, python 2 pickle can not load the file dumped by python 3 pickle? If I want it? How to do? You should write the pickled data with a lower protocol number in Python 3. Python 3 introduced a new protocol with the number 3 (and uses it as default), so switch back to a value of 2 which can be read by Python 2. Check the protocol parameter in pickle.dump . Your resulting code will look like this. pickle.dump(your_object, your_file, protocol=2) There is no protocol parameter in pickle

My input is simply a csv file with 339732 rows and two columns : the first being 29 feature values, i.e. X the second being a binary label value, i.e. Y I am trying to train my data on a stacked LSTM model: data_dim = 29 timesteps = 8 num_classes = 2 model = Sequential() model.add(LSTM(30, return_sequences=True, input_shape=(timesteps, data_dim))) # returns a sequence of vectors of dimension 30 model.add(LSTM(30, return_sequences=True)) # returns a sequence of vectors of dimension 30 model.add(LSTM(30)) # return a single vector of dimension 30 model.add(Dense(1, activation='softmax')) model