ONNX-ImageNet-1K-Object-Detector icon indicating copy to clipboard operation
ONNX-ImageNet-1K-Object-Detector copied to clipboard

ONNXRuntimeError

Open hf62580 opened this issue 1 year ago • 1 comments

Hello Author, I encountered the following error during inference. Could this be an issue with the ONNXRuntime version? I am using ONNXRuntime version 1.7.1.

/root/anaconda3/envs/oln/bin/python /mnt/myDisk/deepLearn/ONNX-ImageNet-1K-Object-Detector-main/main/image_object_detection.py Traceback (most recent call last): File "/mnt/myDisk/deepLearn/ONNX-ImageNet-1K-Object-Detector-main/main/image_object_detection.py", line 36, in detections = detector(image) File "/mnt/myDisk/deepLearn/ONNX-ImageNet-1K-Object-Detector-main/main/detector1K/detector1K.py", line 33, in call return self.detect_objects(image) File "/mnt/myDisk/deepLearn/ONNX-ImageNet-1K-Object-Detector-main/main/detector1K/detector1K.py", line 48, in detect_objects outputs = self.inference(input_tensor) File "/mnt/myDisk/deepLearn/ONNX-ImageNet-1K-Object-Detector-main/main/detector1K/detector1K.py", line 74, in inference outputs = self.session.run(self.output_names, {self.input_name: input_tensor}) File "/root/anaconda3/envs/oln/lib/python3.7/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 188, in run return self._sess.run(output_names, input_feed, run_options) onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: (tensor(float)) , expected: (tensor(uint8))

hf62580 avatar Aug 15 '24 10:08 hf62580