hpc203/detic-onnxrun-cpp-py

使用ONNXRuntime部署Detic检测2万1千种类别的物体，包含C++和Python两个版本的程序

深度学习推理部署，真好玩😄😄😄

detic-onnxrun-cpp-py's Issues

thx my hero

而你我的朋友 你是真正的英雄

转换成onnx用c++会报错

我自己转换模型，然后用c++实现前向会报错：
Non-zero status code returned while running Split node. Name:'/roi_heads/Split_3' Status Message: Cannot split using values in 'split' attribute. Axis=0 Input shape={240,7} NumOutputs=1 Num entries in 'split' (must equal number of outputs) was 1 Sum of sizes in 'split' (must equal size of selected axis) was 256
Traceback (most recent call last):
File "/home/yujl/train_projects/Detic/demo_onnx.py", line 166, in
preds = mynet.detect(srcimg)
File "/home/yujl/train_projects/Detic/demo_onnx.py", line 143, in detect
pred_boxes, pred_classes, scores, _ = self.session.run(None, {self.input_name: input_image})
File "/home/yujl/anaconda3/envs/yujl_envs/lib/python3.10/site-packages/onnxruntime/capi/onnxruntime_inference_collection.py", line 220, in run
return self._sess.run(output_names, input_feed, run_options)
onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Split node. Name:'/roi_heads/Split_3' Status Message: Cannot split using values in 'split' attribute. Axis=0 Input shape={240,7} NumOutputs=1 Num entries in 'split' (must equal number of outputs) was 1 Sum of sizes in 'split' (must equal size of selected axis) was 256

onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Non-zero status code returned while running Split node. Name:'/roi_heads/Split_3' Status Message: Cannot split using values in 'split' attribute. Axis=0 Input shape={240,7} NumOutputs=1 Num entries in 'split' (must equal number of outputs) was 1 Sum of sizes in 'split' (must equal size of selected axis) was 256

请问下你这是怎么转的？
谢谢

Could you release the code of converting the onnx model?