tensorflow / tensorflow/tflite-support

Error occurred when initializing ObjectDetector: AllocateTensors() failed.

Open
#900 1 comment 1 reaction 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
C++
Stars
441
Forks
146
PR merge metrics
No merged PRs in 30d

Description

I used the PT file trained by yolov5, converted it to tflite file, and ran it with the official android code. An error was reported

java.lang.IllegalStateException: Error occurred when initializing ObjectDetector: AllocateTensors() failed. at org.tensorflow.lite.task.vision.detector.ObjectDetector.initJniWithModelFdAndOptions(Native Method)

the tflite added metadata by https://github.com/ultralytics/yolov5
tflite file see attach files: assets.zip

image

the command:
cd yolov5 dir; python3 export.py --weight runs/train/exp4/weights/best.pt --include tflite --int8 --nms --agnostic-nms --data /mnt/yolov5-beev2/bee-linux.yaml --imgsz 320

the android code, like ImageClassifier https://github.com/tensorflow/examples/tree/master/lite/examples/image_classification/android_java

image

But when I run it, I get an error
assets.zip

Can someone help me with this problem? !! 3q
I'll show you the source code.
android_java.zip

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the YOLOv5 export.py command and the Android ImageClassifier example referenced in the issue. Inspect assets.zip and android_java.zip, then reproduce the AllocateTensors() failure with the supplied TFLite model. Done means the exported model initializes successfully through the official Android ObjectDetector code.

Written by the indexing model from the issue text.

Assessment

Tech stack
android, java, python
Domain
machine-learning, mobile-dev
Issue type
Bug
Difficulty
4/5
Estimated time
3-5 days
Activity status
Stale
Clarity
Mostly clear
Newbie friendliness
32/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.