mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity
587 Commits 11 Branches 5 Tags
ef564f134d1a7cf46a19aa0391865fa0004f08a4
Commit Graph

587 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
Harshvardhan Chandirasekar ef564f134d Merge pull request #6 from perseusdg/depth 
Merge - build fixes
 2022-01-24 21:55:06 +05:30
perseusdg f996659845 Merge remote-tracking branch 'origin/depth' into depth 2022-01-24 21:48:35 +05:30
Harshvardhan Chandirasekar afdad8e661 Moved batchnorm and test_monodepth2_new_format layer to dev 
Signed-off-by: perseusdg <harshvardhan.chandira@gmail.com>
 2022-01-24 21:48:21 +05:30
Harshvardhan Chandirasekar 71366befc2 Merge pull request #5 from perseusdg/depth 
Merge tensorrt8 and depth
 2022-01-24 21:44:37 +05:30
Harshvardhan Chandirasekar 3e86671c50 Moved batchnorm and test_monodepth2_new_format layer to dev 
Signed-off-by: perseusdg <harshvardhan.chandira@gmail.com>
 2022-01-24 21:41:59 +05:30
Harshvardhan Chandirasekar 00f06f7bcc Merge branch 'tensorrt8-rds' into depth 2022-01-20 22:05:54 +05:30
Harshvardhan Chandirasekar 53725c88a9 Merge pull request #3 from perseusdg/tensorrt8 
push tensorrt8 commits to the rds branch
 2022-01-20 21:12:49 +05:30
Harshvardhan Chandirasekar 6a133d8dec -Replaced ISliceLayer based paddings(reflection,constant and zero) with the IPluginV2 version for TensorRT >= 8.2.0 
-Fixed demo build issue on Windows

Signed-off-by: perseusdg <harshvardhan.chandira@gmail.com>
 2022-01-20 00:52:22 +05:30
Micaela Verucchi decd73d298 Fix saving result video in demoDepth, add automatic download for monodepth2 weights 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2022-01-19 10:22:06 -08:00
Micaela Verucchi 907df27e07 Fix monodepth2, add demoDepth: 
- Fix monodepth2 network, now works with both cuDNN and tensorRT
- Substitute cuDNN ELU with tkDNN one
- add DepthNN class
- add demoDepth demo, now only works with monodepth2 net

Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
               Francesco Gatti <gattifrancesco@hotmail.it>
 2022-01-18 21:34:16 -08:00
perseusdg 19e41a8b99 monodepth2 new format (test) conv + independent batch norm 2022-01-11 12:38:36 +05:30
perseusdg 061bc79a69 Added BatchNorm to NetworkRT (conver_layer) 2022-01-10 22:48:16 +05:30
perseusdg bcf0c4eab3 Added BatchNorm Layer (Testing still needs to be done) 2022-01-10 22:48:06 +05:30
perseusdg e1eac2d42a Added a seperate layer file for batchnorm,to support an independent batchnorm class in order to pass necessary parameters read from the bin file. 2022-01-10 22:47:59 +05:30
perseusdg 3023926695 fix constantpadding commit 2022-01-09 22:17:43 +05:30
perseusdg 4d8f99b441 depth->tensorrt8 patches 2022-01-09 19:24:38 +05:30
perseusdg cabebc95a2 added individual layer names in monodepth2 2022-01-09 13:45:44 +05:30
perseusdg 3b58fbcb82 Added ConstantPadding plugin for TensorRT < 8.2 2022-01-07 13:05:09 +05:30
perseusdg f189efcbb1 Reflection Padding native plugin fix ,forgot to added input_dim.c in the plugin creator 2022-01-07 05:41:26 +00:00
perseusdg 7298dcfb2f Added monodepth2.cpp 2022-01-06 16:30:11 +00:00
perseusdg b75cecb105 Added constant and zero padding with ISliceLayer,need to add them for tensorrt versions less than 8.2 using IPluginV2Ext instead of ISliceLayer since they dont seem to support reflect and zero 2022-01-04 09:03:04 +05:30
perseusdg ba022663f1 completed padding migrations from github 2022-01-03 19:49:32 +05:30
perseusdg 6837644eb2 add reflection padding from github 2022-01-03 18:58:13 +05:30
perseusdg dcf4054bc6 performance improvements for yolo based networks,significant reduction in inference time can be seen yolo4tiny ,yolo4 and minor reduction in inference time can be seen in yolo4_berkeley_f1 and yolo4_berkeley - tested with a batchsize of 1 and 2 and on gtx 1070,it is possible that the performance improvement is more signficant in newer hardware 2022-01-03 13:52:16 +05:30
Micaela Verucchi a4781244f4 Fix merge problem 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-11-24 18:16:15 +01:00
Micaela Verucchi bbae618118 Update README and add print in demo 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-11-24 18:08:41 +01:00
Micaela Verucchi 0707c26bbd Merge of perseusdg-tensorrt8 inside tkDNN 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-11-24 17:59:27 +01:00
perseusdg 9cecc5051a -Modified Dockerfile.base to cudagl 
-Changed demo to take in input from demoConfig.yaml file
-Readme changes for demo.md
 2021-11-24 03:39:57 +05:30
perseusdg a8c98e3c31 Signed-off-by: perseusdg <43143075+perseusdg@users.noreply.github.com> 
removed all TRT8_DEPRACTED functions
 2021-11-19 22:40:52 +05:30
perseusdg 19f12d9c15 rds_slam -> tensorrt8 port for rds 2021-11-15 00:08:37 +05:30
perseusdg 6f936096ae Added num of layers in net and netRT,suggestions from pull request 270 on main repo 2021-11-14 07:13:42 +05:30
perseusdg 367061fea2 fps fix 2021-11-13 18:11:46 +05:30
perseusdg d488c3bd17 remove duplicated lines 2021-11-13 02:12:50 +05:30
perseusdg ee5000ccca bug fixes for dla networks and ported optimization from different pull request 2021-11-13 02:00:49 +05:30
perseusdg 9e328c0daa Migrate tkDNN max pooling plugin creation to pluginRegistry from the default method 2021-11-10 20:09:57 +05:30
perseusdg 7dd33cd118 added assert for supportsFormat in plugins 2021-11-10 14:37:16 +05:30
perseusdg 936b680f2f Remove debug prints 2021-11-10 13:45:44 +05:30
perseusdg c0e2097397 - CMakeLists.txt opencv cuda contrib autodetect 
- Updated Docker to cuda-11.3+cudnn-8.2.1+TensorRT-8.0.34,Ubuntu to 20.04 and OpenCV to 4.5.4
- Updated OpenCV4 to 4.5.4 in install_OpenCV4.sh
- Updated README.md
 2021-11-10 12:30:57 +05:30
perseusdg 744396fb0e Update README.md,windows.md and demo.cpp 
Small fixes in DeformableConvRT.cpp
 2021-11-09 13:37:26 +05:30
Micaela Verucchi d2d44e9e92 Fix max elem (remove thrust) for segmentation 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-11-05 19:54:02 +05:30
perseusdg 802c01bd8f windows debug fix 2021-10-30 19:29:21 +05:30
perseusdg 7a89a4a573 ReshapeRT.cpp fix 2021-10-28 23:43:12 +05:30
perseusdg c5e66c6bf6 TRT8 works with almost every nerual network now!!!!(including demo3d) 2021-10-28 23:35:37 +05:30
perseusdg 8c36dd0431 mobilenet works with trt7(IPluginV2IOExt) ,need to test it with trt8 2021-10-27 18:00:33 +05:30
perseusdg 54e7af11ed tensorrt7 support for ipluginv2 2021-10-18 18:07:57 +05:30
perseusdg 18cc6abbb6 DeformableConvRT.h fixes ,cmake cuda arch auto detection 2021-09-07 23:57:52 +05:30
perseusdg 03473743c4 tkDNN works with trt8!!,need to test int8 and mobilenet,dla_cnet (fps seems to be a bit low 350 on trt8 compared to 396 on trt7) 2021-09-07 22:00:28 +05:30
perseusdg 9fa116ce4a tkdnn(trt8) runs now minus the detections ,[executionContext.cpp::enqueueInternal::312] Error Code 3: Internal Error (Parameter check failed at: runtime/api/executionContext.cpp::enqueueInternal::312, condition: mDeviceMemorySize == 0 || mExecutionResources->getDeviceMemory() != nullptr - is the error that causes it 2021-09-07 07:20:46 +05:30
perseusdg 504dee5016 test_yolo4 netRT->destroy() 2021-09-06 15:35:57 +05:30
Harshvardhan Chandirasekar 65ba5c9844 tkDNN can now deserialize tensorrt-8 engine (both through test_* and trtexec) 
but demo has issues in yolo::computeDetections
 2021-09-05 01:06:56 +05:30