The sparseinst_tensorrt's discuss from leandro-svg

leandro-svg / sparseinst_tensorrt Goto Github PK

View Code? Open in Web Editor NEW

The real-time Instance Segmentation Algorithm SparseInst running on TensoRT and ONNX

License: MIT License

Python 99.62% Shell 0.29% PureBasic 0.08%

sparseinst_tensorrt's Issues

ONNX Inferencing Error

Hello,
Thank you for this great project to properly convert SparseInst to Onnx/TensorRT.

I started training through your updated implementation using a customized version of configs/sparse_inst_r50_giam_aug.yaml and 10 classes

I converted to onnx successfully

python3 convert_onnx.py --config-file configs/sparse_inst_r50_giam_aug.yaml --output on2/myonnx2.onnx --image assets/figures/t1.jpg --opts MODEL.WEIGHTS output/checkpoints/model_0001999.pth

Then when trying to inference using

python3 eval_tensorrt_onnx.py  -c 0.2 --width_resized 640 --height_resized 640 --input assets/figures/* --use_onnx --onnx_engine on2/myonnx2.onnx --output_onnx on2/ --save_image

I'm receiving the below error!

onnxruntime.capi.onnxruntime_pybind11_state.Fail: [ONNXRuntimeError] : 1 : FAIL : Load model from on2/myonnx2.onnx failed:Type 
Error: Type parameter (T) of Optype (Add) bound to different types (tensor(float) and tensor(double) in node (Add_398).

Hello! I am confused with the onnx model I exported. I wonder whether the 'masks' node's loss the first dimension or not. As far as I am concerned, it should be [1, 100, 160, 160], but not [100, 160, 160], which means it loss the batch dim.

Recommend Projects