manupa-arm commented on a change in pull request #6560: URL: https://github.com/apache/incubator-tvm/pull/6560#discussion_r496564570
########## File path: tests/python/contrib/test_ethosn/test_networks.py ########## @@ -104,17 +96,16 @@ def test_mobilenet_v1(): # codegen, which could come about from either a change in Support Library # version or a change in the Ethos-N codegen. To update this requires running # on hardware that isn't available in CI. - hw = ethosn_available() _test_image_network( model_url="https://storage.googleapis.com/download.tensorflow.org/" "models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224_quant.tgz", model_sub_path="mobilenet_v1_1.0_224_quant.tflite", input_dict={"input": (1, 224, 224, 3)}, compile_hash="81637c89339201a07dc96e3b5dbf836a", output_count=1, - run=(hw == Available.SW_AND_HW), host_ops=3, npu_partitions=1, + run=True, Review comment: I think its worth mentioning the functionality of inference_result as registered as ""relay.ethos-n.test.infra.inference_result" has two faces :) -- based on the availability of the hardware, in the tei. Otherwise, its hard to understand what's this "run" really means and the need for the assert_lib_hash. ---------------------------------------------------------------- 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. For queries about this service, please contact Infrastructure at: us...@infra.apache.org