[GitHub] [beam] AnandInguva commented on a diff in pull request #21738: Inference benchmark tests

[GitBox <gi...@apache.org>]

AnandInguva commented on code in PR #21738:
URL: https://github.com/apache/beam/pull/21738#discussion_r904440977


##########
sdks/python/apache_beam/examples/inference/pytorch_image_classification.py:
##########
@@ -72,6 +73,7 @@ def parse_known_args(argv):
   """Parses args for the workflow."""
   parser = argparse.ArgumentParser()
   parser.add_argument(
+      '--input_file',

Review Comment:
   Yes. but you can only access both of them using args.input in the code



##########
sdks/python/apache_beam/examples/inference/pytorch_image_classification.py:
##########
@@ -33,9 +33,10 @@
 from apache_beam.ml.inference.pytorch_inference import PytorchModelHandlerTensor
 from apache_beam.options.pipeline_options import PipelineOptions
 from apache_beam.options.pipeline_options import SetupOptions
+from apache_beam.runners.runner import PipelineResult
 from PIL import Image
+from torchvision import models
 from torchvision import transforms
-from torchvision.models.mobilenetv2 import MobileNetV2
 

Review Comment:
   We provide the documentation on what to expect on the `model_class`. I think that would be enough?
   
   Mobilenet is just a placeholder if the user doesn't provide a model to run on this example



-- 
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: github-unsubscribe@beam.apache.org

For queries about this service, please contact Infrastructure at:
users@infra.apache.org