I’m getting the error below when calling flatten_parameters on a lstm inside script_method inside a ScriptModule
RuntimeError:
attribute 'flatten_parameters' of type 'NoneType' is not usable in a script method (did you forget to add it __constants__?):
@torch.jit.script_method
def inference(self, x):
for conv in self.convolutions:
x = F.dropout(F.relu(conv(x)), 0.5, False)
x = x.transpose(1, 2)
self.lstm.flatten_parameters()
~~~~~~~~~~~~~~~~~ <--- HERE