I trained a char-LSTM model for generating text. I saved it using torch.save(). And loading it using torch.load(). But when using the loaded model for prediction, I am getting the following error:
AttributeError: 'LSTM' object has no attribute '_flat_weights'
My model is defined as:
class charGen(nn.Module):
def __init__(self, n_letters, lstm_size, lstm_layers=3, lstm_dropout=0, dropout=0, hidden_dim=128):
super(charGen, self).__init__()
self.n_letters = n_letters
self.lstm_size = lstm_size
self.lstm_layers = lstm_layers
self.lstm_dropout = lstm_dropout
self.dropout = dropout
self.hidden_dim = hidden_dim
self.lstm = nn.LSTM(n_letters,
lstm_size,
num_layers=lstm_layers,
batch_first=False,
dropout=lstm_dropout)
self.dropout = nn.Dropout(p=dropout)
self.relu = nn.ReLU()
self.fc = nn.Sequential(
nn.Linear(self.lstm_size, self.hidden_dim),
self.relu,
self.dropout,
nn.Linear(self.hidden_dim, self.hidden_dim),
self.relu,
self.dropout,
nn.Linear(self.hidden_dim, self.hidden_dim),
self.relu,
self.dropout,
nn.Linear(self.hidden_dim, self.n_letters)
)
def forward(self, x, prev_states):
out, state = self.lstm(x, prev_states)
fc_in = out.view(-1, out.size(2))
fc_out = self.fc(fc_in)
return fc_out, state
def zero_state(self, batch_size):
return [torch.zeros(self.lstm_layers, batch_size, self.lstm_size),
torch.zeros(self.lstm_layers, batch_size, self.lstm_size)]
I can’t understand what’s going wrong. Need help.
EDIT: I am running the training and model saving code on a different machine (on my university’s server) with pytorch version ‘1.0.1’ while the code the load and use it for inference is done on my system. with pytorch version ‘1.4.0’. Can that be a reason?