This repository was archived by the owner on Dec 16, 2022. It is now read-only.
This repository was archived by the owner on Dec 16, 2022. It is now read-only.
Closed
Description
Describe the bug
bug in allennlp.nn.initializers.uniform_unit_scaling
To Reproduce
Using the latest version of allennlp and pytorch(0.4.1), initialize parameters of LSTM/GRU via uniform_unit_scaling function
Expected behavior
Exception throw:
RuntimeError: a leaf Variable that requires grad has been used in an in-place operation
Potential Solution
Fix the line to return tensor.data.uniform_(-max_value, max_value) link
Metadata
Metadata
Assignees
Labels
No labels