yeandy commented on code in PR #22974:
URL: https://github.com/apache/beam/pull/22974#discussion_r973122888
##########
sdks/python/apache_beam/ml/inference/pytorch_inference.py:
##########
@@ -186,6 +189,9 @@ def __init__(
device: the device on which you wish to run the model. If
``device = GPU`` then a GPU device will be used if it is available.
Otherwise, it will be CPU.
+
+ **Supported Versions:** PyTorch 1.9 and 1.10 are currently supported for
+ Python 3.7, 3.8, and 3.9
Review Comment:
```suggestion
**Supported Versions:** PyTorch versions 1.9 and 1.10 have been tested
in Apache Beam.
```
##########
sdks/python/apache_beam/ml/inference/pytorch_inference.py:
##########
@@ -84,8 +87,8 @@ def __init__(
``device = GPU`` then a GPU device will be used if it is available.
Otherwise, it will be CPU.
- See https://pytorch.org/tutorials/beginner/saving_loading_models.html
- for details
+ **Supported Versions:** PyTorch 1.9 and 1.10 are currently supported for
+ Python 3.7, 3.8, and 3.9
Review Comment:
```suggestion
**Supported Versions:** PyTorch versions 1.9 and 1.10 have been tested
in Apache Beam.
```
--
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]
