Zero Zeng comments

Results 581 comments of


                                            Zero Zeng

convert onnx to trt, onnxparser fail, but trtexec success

Can you provide a reproduce sample here? also it would be good to try our latest release.

result verify failure of TensorRT 8.5.10 when converting onnx model to trt model

Could you please check the onnx accuracy first? e.g. with onnxruntime.

result verify failure of TensorRT 8.5.10 when converting onnx model to trt model

Or it can be quickly checked with polygraphy: `polygraphy run model.onnx --trt --onnxrt` to see if the accuracy is matched between onnxruntime and TRT. Sometimes it's caused by exporting.

[Question]:How to add a Dropout layer

Dropout is disabled during inference so I don't think you need it.

poetry install failure of TensorRT 8.6.1 when installing

I don't know much about it, @pranavm-nvidia could you please kindly help :-)

poetry install failure of TensorRT 8.6.1 when installing

Could you please try version `8.6.1.post1`?

poetry install failure of TensorRT 8.6.1 when installing

Checking further internally.

poetry install failure of TensorRT 8.6.1 when installing

Hi all, is it possible that you can provide a minimal reproduce steps so that I can reproduce and file internal bug.

i have some problems about my work, when i use tensorRT to convert file pt to file.wts and this step $ sudo ./yolov7 -s yolov7-tiny.wts yolov7-tiny.engine t, i meet this problems, can i help me, please....

> [02/24/2023-13:22:21] [E] [TRT] (Unnamed Layer* 187) [Convolution]: kernel weights has count 648 but 5760 was expected > [02/24/2023-13:22:21] [E] [TRT] (Unnamed Layer* 187) [Convolution]: count of 32640 weights in...

i have some problems about my work, when i use tensorRT to convert file pt to file.wts and this step $ sudo ./yolov7 -s yolov7-tiny.wts yolov7-tiny.engine t, i meet this problems, can i help me, please....

How about just export the model to onnx and use our onnx parser?