tensorflow
CenterNet MobileNetV2 FPN 512x512 erroneously configured for keypoint outputs
Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [ x] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [ x] I am reporting the issue to the correct repository. (Model Garden official or research directory)
- [ x] I checked to make sure that this issue has not already been filed.
1. The entire URL of the file you are using
https://github.com/tensorflow/models/blob/master/research/object_detection/g3doc/tf2_detection_zoo.md http://download.tensorflow.org/models/object_detection/tf2/20210210/centernet_mobilenetv2fpn_512x512_coco17_od.tar.gz
2. Describe the bug
Model "CenterNet MobileNetV2 FPN 512x512" is documented to use "boxes" as Outputs but pipeline.config file uses keypoints instead. Check line 120 and 137.
3. Steps to reproduce
Checkout pipeline.config at lines 120 and 137.
4. Expected behavior
Expect no num_keypoints to be present in this config.
5. Additional context
When training "CenterNet MobileNetV2 FPN 512x512" with given pipeline.config we see this error: raise core._status_to_exception(e) from None # pylint: disable=protected-access tensorflow.python.framework.errors_impl.InvalidArgumentError: {{function_node _wrappedIteratorGetNext_output_types_19_device/job:localhost/replica:0/task:0/device:GPU:0}} indices[0] = 0 is not in [0, 0) [[{{node GatherV2_8}}]] [[MultiDeviceIteratorGetNextFromShard]] [[RemoteCall]] [Op:IteratorGetNext]
