Tf-record issue

Accelerated Computing Intelligent Video Analytics TAO Toolkit
1

Traceback (most recent call last):
File “/usr/local/bin/tlt-dataset-convert”, line 8, in
sys.exit(main())
File “./detectnet_v2/scripts/dataset_convert.py”, line 64, in main
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 74, in convert
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 108, in _write_partitions
File “./detectnet_v2/dataio/dataset_converter_lib.py”, line 149, in _write_shard
File “./detectnet_v2/dataio/kitti_converter_lib.py”, line 169, in _create_example_proto
File “./detectnet_v2/dataio/kitti_converter_lib.py”, line 265, in _add_targets
UnicodeEncodeError: ‘ascii’ codec can’t encode characters in position 0-12: ordinal not in range(128)

What parameter out of the 15 columns is causing this issue? Is there a way to figure out what it is and fix the issue.

2

Can you share one of the label files?

3

face 0.0 0 0.0 242.0 51.0 338.0 175.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0
face 0.0 0 0.0 128.0 85.0 204.0 193.0 0.0 0.0 0.0 0.0 0.0 0.0 0.0

4

Refer to similar topic.

There should be something wrong in parts of your labels. Please narrow down step by step.
Reference: python - UnicodeEncodeError: 'ascii' codec can't encode character u'\xa0' in position 20: ordinal not in range(128) - Stack Overflow

5

This topic was automatically closed 14 days after the last reply. New replies are no longer allowed.