WJJ1995 61634caf28 [Bug Fix] Fixed for CI (#499) ...

* add paddle_trt in benchmark

* update benchmark in device

* update benchmark

* update result doc

* fixed for CI

2022-11-04 15:49:28 +08:00

..

backends

[Backend] Enable TensorRT BatchedNMSDynamic_TRT plugin (#449)

2022-11-04 11:46:29 +08:00

core

[Backend] Add RKNPU2 backend support (#456)

2022-11-01 11:14:05 +08:00

function

[Backend] TRT cast GPU input from int64 to int32, output from int32 to int64, and Windows support building CUDA files (#426)

2022-10-28 13:38:06 +08:00

pipeline

[Model] Add tinypose single && pipeline model (#177)

2022-10-21 09:28:23 +08:00

pybind

[Backend] Add RKNPU2 backend support (#456)

2022-11-01 11:14:05 +08:00

text

[Model] Upgrade uie (#458)

2022-10-30 17:04:05 +08:00

utils

[Backend] Add collect shape for pp-trt backend (#372)

2022-10-20 17:02:56 +08:00

vision

[Bug Fix] Fixed for CI (#499)

2022-11-04 15:49:28 +08:00

CMakeLists.txt

Modify file structure to separate python and cpp code (#223)

2022-09-14 15:44:13 +08:00

fastdeploy_model.cc

[Model] yolo use external stream, avoid reallocating output tensors (#447)

2022-11-02 09:52:27 +08:00

fastdeploy_model.h

[Model] yolo use external stream, avoid reallocating output tensors (#447)

2022-11-02 09:52:27 +08:00

pipeline.h

[Model] Add tinypose single && pipeline model (#177)

2022-10-21 09:28:23 +08:00

runtime.cc

[Backend] Enable TensorRT BatchedNMSDynamic_TRT plugin (#449)

2022-11-04 11:46:29 +08:00

runtime.h

[Backend] Enable TensorRT BatchedNMSDynamic_TRT plugin (#449)

2022-11-04 11:46:29 +08:00

text.h

Modify file structure to separate python and cpp code (#223)

2022-09-14 15:44:13 +08:00

vision.h

[Model] Add FSANet model (#448)

2022-11-04 11:00:35 +08:00