Commit Graph

10 Commits (2dc0a219c1f4268448e6dd733db34e8da5c5e9b5)

Author SHA1 Message Date
q.yao 004c00675f
[Feature]: add modulated deformable conv TensorRT support (#1078)
* add modulated dcn, better dcn plugin

* clangformat

* update documentation
2021-06-16 21:38:07 +08:00
SemyonBevzuk bf2c9fa8d2
[Feature] NMS update (#957)
* Add score_threshold and max_num to NMS

* Fix codestyle

* Fix codestyle

* Fix inds in nms

* Update nms docstring

* Move score_threshold and max_num arguments

* Fix args order in docstring

* fix lint of c++ file

* Remove torch.onnx.is_in_onnx_export() and add max_num to batched_nms for separate classes.

* Rewrote max_num handling in NMSop.symbolic

* Added processing max_output_boxes_per_class when exporting to TensorRT

* Added score_threshold and max_num for NMS in test_onnx.py and test_tensorrt.py

* Remove _is_value(max_num)

* fix ci errors with torch==1.3.1

* Update test_batched_nms in test_nms.py

* Added tests for preprocess_onnx

* Moved 'test_tensorrt_preprocess.py' and 'preprocess', updated 'remove_tmp_file'.

* Update mmcv/tensorrt/__init__.py

* Fix segfault torch==1.3.1 (remove onnx.checker.check_model)

* Returned 'onnx.checker.check_model' with torch version check

* Changed torch version from 1.3.1 to 1.4.0

* update version check

* remove check for onnx

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-05-31 23:42:26 +08:00
RunningLeon 4d42365ac2
[Feature]: add TensorRT InstanceNormalization plugin (#1034)
* add instancenorm plugin

* resolve comments

* fix lint

* fix typo
2021-05-25 20:03:57 +08:00
q.yao 9d1436fb6c
[Feature] add cummax/cummin tensorrt plugin (#1031)
* add cummax/cummin tensorrt plugin

* fix isort

* fix with clang-format

* fix with clang-format again

* add document
2021-05-24 13:55:21 +08:00
q.yao 9d80f56ae8
[Feature] : Add grid_sampler TensorRT Plugin (#865)
* add grid sample trt support

* fix align_corners=True

* change 'intep' to 'interp', fix bugs of grid sampler, better test script

* remove unused import

* move source comment to the top of trt_grid_sampler_kernel.cu
2021-03-31 00:28:08 +08:00
q.yao 9ba1f76005
[Feature] : Add Deformable Conv2d TensorRT Plugin (#858)
* add dcn tensorrt plugin

* prepare for fp16 support

* fix for lint

* limit column buffer

* add docstring to memcpyPermute
2021-03-11 15:41:47 +08:00
RunningLeon 3dd98daaa2
fix test unit of nms and batched_nms for tensorrt (#872) 2021-03-08 16:57:19 +08:00
q.yao 1ee5315ea2
[Feature] : Add NonMaxSuppression TensorRT Plugin (#787)
* start trt plugin prototype

* Add test module, modify roialign convertor

* finish roi_align trt plugin

* fix conflict of RoiAlign and MMCVRoiAlign

* fix for lint

* fix test tensorrt module

* test_tensorrt move import to test func

* add except error type

* add tensorrt to setup.cfg

* code format with yapf

* fix for clang-format

* move tensorrt_utils to mmcv/tensorrt, add comments, better test module

* fix line endings, docformatter

* isort init, remove trailing whitespace

* add except type

* fix setup.py

* put import extension inside trt setup

* change c++ guard, update pytest script, better setup, etc

* sort import with isort

* sort import with isort

* move init of plugin lib to init_plugins.py

* add scatternd, nms plugin (WIP)

* fix bugs of trt_nms

* add trt nms test module

* fix bugs of scatternd

* code optimize, add comment about nms kernel

* fix transform_if bug of trt_nms_kernel

* fix struct name

* default nms offset=0, fix bugs of batched input

* format with clang-format

* onnx preprocess

* much better nms implementation, no need to transfer memory between host and device

* update preprocess_onnx

* parse constant tensor from initializer in preprocess_onnx

* update nms

* remove unnecessary codes

* workspace aligned address

* format trt_plugin_helper.hpp

* fix index memory bugs

* set alignment to 16 by default

* fix lint

* fix nms offset

* fix bugs of preprocess onnx

* update test for nms

* tensorrt only accept int32, not int64

* update nms comments

* fix indexing for scores in nms

* update trt temp

* make trt-nms compatiable to #803

* fix lint

* add docstring to trt_nms_kernel.cuda, add description to preprocess_onnx

* add comment to score indexing

* fix bugs of max output boxes

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-02-23 15:09:49 +08:00
q.yao 2ab544fc29
[Feature] : Add ScatterND TensorRT Plugin (#786)
* add scatter plugin

* fix bugs of scatternd

* add trt scatternd plugin

* format code with clang-format

* add test for scatternd

* skip test_tensorrt in CI

* remove unused variable

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-01-20 11:15:07 +08:00
q.yao 0de9e149c0
[Feature]: Add custom operators support for TensorRT in mmcv (#686)
* start trt plugin prototype

* Add test module, modify roialign convertor

* finish roi_align trt plugin

* fix conflict of RoiAlign and MMCVRoiAlign

* fix for lint

* fix test tensorrt module

* test_tensorrt move import to test func

* add except error type

* add tensorrt to setup.cfg

* code format with yapf

* fix for clang-format

* move tensorrt_utils to mmcv/tensorrt, add comments, better test module

* fix line endings, docformatter

* isort init, remove trailing whitespace

* add except type

* fix setup.py

* put import extension inside trt setup

* change c++ guard, update pytest script, better setup, etc

* sort import with isort

* sort import with isort

* move init of plugin lib to init_plugins.py

* resolve format and add test dependency: tensorrt

* tensorrt should be installed from source not from pypi

* update naming style and input check

* resolve lint error

Co-authored-by: maningsheng <maningsheng@sensetime.com>
2021-01-06 11:05:19 +08:00