shunping commented on code in PR #34612:
URL: https://github.com/apache/beam/pull/34612#discussion_r2205060894
##########
sdks/python/apache_beam/ml/inference/tensorflow_inference_test.py:
##########
@@ -128,7 +128,8 @@ def test_predict_tensor_with_batch_size(self):
model = _create_mult2_model()
model_path = os.path.join(self.tmpdir, f'mult2_{uuid.uuid4()}.keras')
tf.keras.models.save_model(model, model_path)
- with TestPipeline() as pipeline:
+ # FnApiRunner guarantees large batches, which this pipeline assumes
Review Comment:
This could be due to the fact that prism is using accelerated processing
time by default. The processing-time timer in BatchElements may not work as
expected.
PR #35202 adds an experimental flag for using real-time processing time,
which may help to resolve this problem.
--
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]
