Chen-cyw

In some classes(not all) ,the scores of infrerence results become low(eg from 0.8 to 0.25) after transform to tensorrt model, test by the same object in the same picture. the...

int8 model convert error

4

env: GPU:tesla t4 nvidia-diver:450.51.6 cuda:11.03 cudnn:8.04 tensorrt:7.1.3.4 pytorch:1.6/1.7 torchvision:0.7/0.8 mmdetection:2.7 ```C++ Warning: Encountered known unsupported method torch.Tensor.new_tensor Warning: Encountered known unsupported method torch.Tensor.new_tensor Warning: Encountered known unsupported method torch.Tensor.new_tensor Warning:...

Mask rcnn can not use int8 calib?

1

while i set (enable_mask=True) and (int8_mode=True, int8_calib_dataset=calib_dataset, int8_calib_alg="entropy"), the model can be convert to int8 model, but the calib will not work.

set_calibration_profile not exist

1

the tensorrt(7.0.0.11) do not have the function " set_calibration_profile()", if use int8 mode ,error will out 

load libtorch2trt_dynamic.so error

5

I export the libtorch2trt_dynamic.so by "sudo python setup.py develop --plugins" and configure the trt and cuda path, but when I use the .so , it always get the error "OSError:...

deploy instance-seg_dynamic with export_postprocess_mask=True error

10

**Describe the bug** 2022-08-30 06:01:25,337 - mmdeploy - INFO - Execute onnx optimize passes. 2022-08-30 06:01:26,701 - mmdeploy - INFO - Finish pipeline mmdeploy.apis.pytorch2onnx.torch2onnx [2022-08-30 06:01:29.267] [mmdeploy] [info] [model.cpp:95] Register...