Hi, all
- convert tensorflow model ssd_mobilenet_v2_coco to onnx
- convert command
python -m tf2onnx.convert \
--input $MODEL_DIR/frozen_inference_graph.pb \
--inputs 'image_tensor:0[1,640,640,3]' \
--outputs 'detection_boxes:0,detection_scores:0,num_detections:0,detection_classes:0' \
--opset 11 \
--fold_const \
--output $MODEL_DIR/frozen_inference_graph.onnx
- inference in onnxruntime successfully,
- inference in tensorrt error.
----------------------------------------------------------------
Input filename: frozen_inference_graph.onnx
ONNX IR version: 0.0.6
Opset version: 11
Producer name: tf2onnx
Producer version: 1.9.1
Domain:
Model version: 0
Doc string:
----------------------------------------------------------------
Unsupported ONNX data type: UINT8 (2)
ERROR: image_tensor:0:188 In function importInput:
[8] Assertion failed: convertDtype(onnxDtype.elem_type(), &trtDtype)
parse model error
Feel free to message me if you cannot reproduce.