Skip to main content
Associate
February 11, 2024
Question

stm32ai INTERNAL ERROR: list index out of range

  • February 11, 2024
  • 2 replies
  • 2205 views

I have a DB (Differentiable Binarization) model exported to ONNX, and I quantized it with onnxruntime using the code below:

```

dr = DetDataReader(
calibration_dataset_path, input_model_path
) # Fake images as I'm just attempting to measure the memory usage.

conf = StaticQuantConfig(
calibration_data_reader=dr,
quant_format=QuantFormat.QDQ,
calibrate_method=CalibrationMethod.MinMax,
# optimize_model=True,
activation_type=QuantType.QInt8,
weight_type=QuantType.QInt8,
# nodes_to_exclude=['resnetv17_dense0_fwd', ..],
# nodes_to_quantize=['resnetv17_dense0_fwd', ..],
per_channel=False) # I tried True as well.
 
quantize(input_model_path, output_model_path, conf)
```
 
Then I tried to analyze it with the stm32ai tool, but I got the following error
$ stm32ai \
analyze --model model-quant.onnx \
--type onnx \
--name det \
--compression high \
--no-onnx-optimizer \
--output output \
--allocate-inputs --allocate-outputs \
--with-report \
--series stm32f4 --target stm32f4 --workspace workspace

Neural Network Tools for STM32 family v1.7.0 (stm.ai v8.1.0-19520)
INTERNAL ERROR: list index out of range
 
I attach my model below (Archive.rar)  in case someone can help me. Thanks in advance. Regards!

2 replies

fauvarque.daniel
ST Employee
February 12, 2024

Issue reproduced with our latest development version, internal bug opened

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.
Visitor II
March 6, 2024

2023.3.6 版本 8.1
内部错误:列表索引超出范围 问题仍然存在 什么时候解决?

Visitor II
April 3, 2024

Hi , any news with that issue? or a way to overcome this?

fauvarque.daniel
ST Employee
April 3, 2024

The issue is in our ONNX importer of the ConvTranspose.

This issue is not fixed yet. 

Regards

​In order to give better visibility on the answered topics, please click on 'Accept as Solution' on the reply which solved your issue or answered your question.