AnandInguva commented on code in PR #26683:
URL: https://github.com/apache/beam/pull/26683#discussion_r1194411598
##########
sdks/python/apache_beam/ml/inference/pytorch_inference.py:
##########
@@ -222,6 +225,8 @@ def __init__(
batch will be fed into the inference_fn as a Sequence of Tensors.
max_batch_size: the maximum batch size to use when batching inputs. This
batch will be fed into the inference_fn as a Sequence of Tensors.
+ load_model_args: a dictionary of parameters passed to the torch.load
+ function of to specify custom config for loading models.
Review Comment:
nit:
```suggestion
function to specify custom config for loading models.
```
Same below
--
This is an automated message from the Apache Git Service.
To respond to the message, please log on to GitHub and use the
URL above to go to the specific comment.
To unsubscribe, e-mail: [email protected]
For queries about this service, please contact Infrastructure at:
[email protected]
