-
Notifications
You must be signed in to change notification settings - Fork 211
ValueError: unrecognized program format #42
Comments
This code was originally developed on an earlier version of PyTorch (0.3) that made a distinction between Tensor and Variable; these two types were merged in PyTorch 0.4. This repo will need some updating to run on PyTorch 1.0; as a quick fix you can try running it with PyTorch 0.3 instead. |
Hi,when i try pytorch 0.3,it will shows: AttributeError: module 'torch.nn.init' has no attribute 'kaiming_normal_' |
Please, I am getting problem with Reinforce() in seq2seq.py was removing is there any one have been facing this issues? NOTE: categorical is equivalent to what used to be called multinomialm = torch.distributions.Categorical(probs) |
In run_model.py, line 161, The type of ' predicted_program' is torch.Tensor.
However, in iep/module/module_net.py, the type of this parameter is restricted to list, tuple and Viarable (dim=2).
I tried to convert predicted_program form torch.Tensor to list or Variable, but failed.
The text was updated successfully, but these errors were encountered: