KeyError: 'operator_codes' about tflite2tensorflow HOT 4 CLOSED

If it is difficult for you to make your model public, you can share the tflite file with me via DM. I have no idea what the problem is with the information you have provided.

from tflite2tensorflow.

There were three reasons why you failed to convert tflite.

1. It is expected that the Docker environment is not used and all necessary modules are not installed.
2. Due to the special nature of AutoML's Reshape operation, it is not possible to identify the shape that needs to be changed.
3. Cannot convert to blob because sort_result_descending of NMS is true.

All of the above issues have been resolved in v1.13.4. However, the AutoML model is so complex that I had to wait 2 hours and 30 minutes for it to convert to Myriad Blob. The converted blobs have already been shared with you via DM. If everything is ok, close the issue.

from tflite2tensorflow.

I am unsure about #1. I have downloaded the latest docker v1.13.4, but when I run, I get the same error.

sh-5.0$ tflite2tensorflow \

--model_path model.tflite
--flatc_path ../flatc
--schema_path ../schema.fbs
--output_pb
--optimizing_for_openvino_and_myriad
Traceback (most recent call last):
File "/usr/local/bin/tflite2tensorflow", line 6220, in
main()
File "/usr/local/bin/tflite2tensorflow", line 5598, in main
ops, json_tensor_details, op_types, full_json = parse_json(jsonfile_path)
File "/usr/local/bin/tflite2tensorflow", line 265, in parse_json
op_types = [v['builtin_code'] for v in j['operator_codes']]
KeyError: 'operator_codes'.

Thanks again.

from tflite2tensorflow.

I think the only issue was permissions. It ran under sudo no problem.

from tflite2tensorflow.