Convert palm_detection_lite.tflite : ValueError: Tensor data is null. Run allocate_tensors() first

[geaxgx]

Issue Type

Bug

OS

Ubuntu

OS architecture

x86_64

Programming Language

Python

Framework

OpenVINO

Download URL for tflite file

https://github.com/google/mediapipe/blob/master/mediapipe/modules/palm_detection/palm_detection_lite.tflite
https://github.com/google/mediapipe/blob/master/mediapipe/modules/palm_detection/palm_detection_full.tflite

Description

Hi @PINTO0309 !
I have just noticed that Goggle has updated the palm detection model a few weeks ago (I missed them because does not appear in release notes). Now there are 2 models (lite and full). Naturally I would like to test them :-)
So after running docker pull ghcr.io/pinto0309/tflite2tensorflow:latest ,
when running:
tflite2tensorflow --model_path palm_detection_lite.tflite --model_output_path palm_detection_lite --flatc_path ../../flatc --schema_path ../../schema.fbs --output_pb --optimizing_for_openvino_and_myriad --rigorous_optimization_for_myriad
I get : ValueError: Tensor data is null. Run allocate_tensors() first

Relevant Log Output

...
@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ op: DEQUANTIZE
{'builtin_options_type': 'NONE',
 'custom_options_format': 'FLEXBUFFERS',
 'inputs': [68],
 'opcode_index': 9,
 'outputs': [319]}
@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@@ op: PRELU
{'builtin_options_type': 'NONE',
 'custom_options_format': 'FLEXBUFFERS',
 'inputs': [121, 319],
 'opcode_index': 1,
 'outputs': [122]}
Traceback (most recent call last):
  File "/usr/local/bin/tflite2tensorflow", line 6402, in <module>
    main()
  File "/usr/local/bin/tflite2tensorflow", line 5759, in main
    TFLite_Detection_PostProcess_flg = make_graph(
  File "/usr/local/bin/tflite2tensorflow", line 877, in make_graph
    alpha_array = interpreter.get_tensor(alpha_detail['index'])
  File "/usr/local/lib/python3.8/dist-packages/tensorflow/lite/python/interpreter.py", line 858, in get_tensor
    return self._interpreter.GetTensor(tensor_index)
ValueError: Tensor data is null. Run allocate_tensors() first

Source code for simple inference testing code

No response

[PINTO0309]

Fixes. PyPI has been updated, but the Docker container will take the remaining 20 minutes to complete the GitHub Action CI.
https://github.com/PINTO0309/tflite2tensorflow/releases/tag/v1.16.2

[PINTO0309]

Commited. 😄 Thank you!
https://github.com/PINTO0309/PINTO_model_zoo/tree/main/033_Hand_Detection_and_Tracking/21_new_full_lite

[geaxgx]

Thanks @PINTO0309 !
A quick feedback: the new models work on a 192x192 image vs 128x128 for the older version.
They are significantly slower. On MyriadX (depthai):

• older: 25ms
• lite: 44ms
• full: 52ms

Difficult to judge accuracy on only one test, but this what I get on this image:

• older:
  

• lite :
  

-full:

Strangely, full is worse than lite on this image. I am not sure yet I will update my hand tracker repo with these models (I am a bit disappointed :-).