mbarrett97 commented on a change in pull request #4543: [FRONTEND][TFLITE] Add
support for TFLite_Detection_PostProcess
URL: https://github.com/apache/incubator-tvm/pull/4543#discussion_r371170921
##########
File path: tests/python/frontend/tflite/test_forward.py
##########
@@ -1113,6 +1113,49 @@ def test_forward_fully_connected():
_test_fully_connected([5, 1, 1, 150], [150, 100], [100])
+#######################################################################
+# Custom Operators
+# -------
+
+def test_detection_postprocess():
+ tf_model_file = tf_testing.get_workload_official(
+ "http://download.tensorflow.org/models/object_detection/"
+ "ssd_mobilenet_v2_quantized_300x300_coco_2019_01_03.tar.gz",
Review comment:
Apologies for the delayed response. Yes, that's probably the source of the
error. Normally that could be worked around just by increasing the error
tolerances. But that doesn't work in this case because of the sorting and
clipping that occurs.
----------------------------------------------------------------
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:
[email protected]
With regards,
Apache Git Services