Vincent Albouy

class RNN2(nn.Module): def __init__(self, input_size, hidden_size,output_size): super(RNN2, self).__init__() self.hidden_size = hidden_size self.i2h = nn.Linear(n_categories + input_size + hidden_size, hidden_size) self.i2o = nn.Linear(n_categories + input_size + hidden_size, output_size) self.o2o = nn.Linear(hidden_size...

You have an operator in you model that ONNX does not recognize. That is why you get this error message. Adding this operator is feasible but quite a tricky process....

Because X is a tensor, the classic way to visualize should work for you ( get_trace -> get graph from trace -> send graph to tensorboard ) . This method...