Murari G

Running YOLOv5 ONNX model with onnx parser of armnn fails with unsupported operation

2

Traceback (most recent call last): File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/yolov5_onnx_parser.py", line 114, in main(args) File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/yolov5_onnx_parser.py", line 55, in main executor = NetworkExecutor(*exec_input_args) ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^ File "/home/sl-rpi-5/Downloads/armnn/python/pyarmnn/examples/object_detection/network_executor.py", line 22, in __init__ self.network_id, self.runtime, self.input_binding_info,...

The torch.operator "onnx.QLinearAdd" operation is marked as illegal and fails during legalization when compiling torch-mlir generated MLIR with IREE. This occurs when processing a ResNet18 INT8 quantized model. [resnet18_int8.zip](https://github.com/user-attachments/files/23184045/resnet18_int8.zip) ```...