[Crash] onnxruntime.quantization.quantize_static the segment-anything model crashed with no error reported #23005
Labels
model:transformer
issues related to a transformer model: BERT, GPT2, Hugging Face, Longformer, T5, etc.
quantization
issues related to quantization
Describe the issue
When I quantize the SAM model by onnxruntime.quantization.quantize_static interface, the program crashed.
In wondows11 pycharm, got this message: Process finished with exit code -1073741819 (0xC0000005)
In ubuntu22.04 terminal , got this: Killed Process
But My machines have enough memory (Windows 32G, Ubuntu 48G)
Then I got an message from oonxruntime_doc
Said that tranformer model should be specific optimized before quantization, but this Tool doesn't support SAM model, i have no idea yet
To reproduce
quantize code and calibrate data as below:
test.zip
model link:
sam_model
Urgency
If could, i hope you can give me an answer in two weeks, thanks
Platform
Windows
OS Version
Windows 11 Pro 23H2 22631.4460
ONNX Runtime Installation
Released Package
ONNX Runtime Version or Commit ID
1.18.0
ONNX Runtime API
Python
Architecture
X64
Execution Provider
Default CPU
Execution Provider Library Version
Ubuntu22.04_x86_64 same error happened(same ort version)
The text was updated successfully, but these errors were encountered: