Closed seanavery closed 3 years ago
I am unable to build the TensorRT engine from the onnx export in the yolov5 repo. It looks like I have a different output shape network.get_output(0).
network.get_output(0)
The output shape I am seeing is (1, 3, 80, 80, 85), while in your code it is expecting a three dimensions (bs, boxes, _). https://github.com/TrojanXu/yolov5-tensorrt/blob/master/main.py#L184
(1, 3, 80, 80, 85)
(bs, boxes, _)
The onnx simplification step runs just fine, but wondering how to get to the output shape required by the build_engine function.
Did you use main.py to export onnx model? It's different from the onnx_export script in yolov5 repo.
Thanks @TrojanXu
I am unable to build the TensorRT engine from the onnx export in the yolov5 repo. It looks like I have a different output shape
network.get_output(0)
.The output shape I am seeing is
(1, 3, 80, 80, 85)
, while in your code it is expecting a three dimensions(bs, boxes, _)
. https://github.com/TrojanXu/yolov5-tensorrt/blob/master/main.py#L184The onnx simplification step runs just fine, but wondering how to get to the output shape required by the build_engine function.