What’s the correct way to handle
num_outputs in a custom model?
- it seems that the action space should be used to get the correct output size, so
num_outputsseems redundant in that case.
- It’s not passed in to the model initializer in some cases (and the last layer is just the flattened features in the examples), so I’m wondering what’s the logic behind that and in what scenarios the
if num_outputscheck is needed.
- Wrappers change
num_outputsin a somewhat confusing way, but I assume the
num_outputsof the wrapper should be separate from the wrapped class’ one, e.g. from
# Add prev-action/reward nodes to input to LSTM. if self.use_prev_action: self.num_outputs += self.action_dim if self.use_prev_reward: self.num_outputs += 1 self.lstm = nn.LSTM( self.num_outputs, self.cell_size, batch_first=not self.time_major) self.num_outputs = num_outputs