tensorflow / tensorflow/models
Fail to convert to tflite
@pkulzc is already working on this.
Since Dec 23, 2020.
- Dominant language
- Python
- Stars
- 77.7k
- Forks
- 44.8k
- PR merge metrics
- No merged PRs in 30d
Description
Hi
I got problem:
Traceback (most recent call last):
File "/content/models/research/object_detection/export_tflite_graph_tf2.py", line 126, in
app.run(main)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 300, in run
_run_main(main, args)
File "/usr/local/lib/python3.6/dist-packages/absl/app.py", line 251, in _run_main
sys.exit(main(argv))
File "/content/models/research/object_detection/export_tflite_graph_tf2.py", line 122, in main
FLAGS.ssd_use_regular_nms)
File "/content/models/research/object_detection/export_tflite_graph_lib_tf2.py", line 231, in export_tflite_model
pipeline_config.model, is_training=False)
File "/content/models/research/object_detection/builders/model_builder.py", line 1090, in build
add_summaries)
File "/content/models/research/object_detection/builders/model_builder.py", line 380, in _build_ssd_model
is_training=is_training)
File "/content/models/research/object_detection/builders/model_builder.py", line 293, in _build_ssd_feature_extractor
feature_extractor_class = SSD_KERAS_FEATURE_EXTRACTOR_CLASS_MAP[
NameError: name 'SSD_KERAS_FEATURE_EXTRACTOR_CLASS_MAP' is not defined
After run below command, can show me how to fix this one
!python /content/models/research/object_detection/export_tflite_graph_tf2.py
--pipeline_config_path /content/data/pipeline.config
--trained_checkpoint_dir /content/output/checkpoint
--output_directory /content/model_android
Contributor guide
First steps
- Read the whole issue, then the project's contributing guide.
- Comment on the issue to say you are picking it up — it saves two people doing the same work.
- Fork the repository and make your change on a branch.
- Open a pull request that references the issue number.
Assessment
This issue has not been assessed yet.