mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity
564 Commits 11 Branches 5 Tags
6837644eb2ea369d4646ba597810755410b724af
Commit Graph

564 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
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 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
perseusdg de83ae5d25 update tensorrt8 branch 2021-08-30 19:04:26 +05:30
perseusdg 2ffe07057e Mnist works at the moment with trt8,others like yolo4tiny and mobilenet generate the engine files but crash after throwing nvifer1::CudaRuntimeError and when demo is being run ,it doesnt deserialize properly and crashes 2021-08-29 03:18:58 +05:30
perseusdg 3d8b1ac494 Yolo3Detection.cpp doesn't build yet,issues with dependecies of preprocessing and postprocessing on IPluginFactory 2021-08-21 22:29:36 +05:30
perseusdg eba78e7e78 Updates to build libkernel.so under TensorRT 8 2021-08-16 13:59:19 +05:30
perseusdg d2ce966c46 fix return type for bool functions 2021-08-04 12:37:58 +05:30
Harshvardhan Chandirasekar bb902f5b65 fix for downloading weights(utils.cpp) when using docker 2021-07-25 23:53:30 +05:30
perseusdg 1412aa66c4 minor fixes for windows ,for release v0.6 2021-07-24 08:51:44 -07:00
Harshvardhan Chandirasekar e58ddadb7d Merge branch 'ceccocats:master' into master 2021-07-24 08:18:17 -07:00
Micaela Verucchi a992c9feb5 Update README.md 2021-07-23 16:50:15 +02:00
Micaela Verucchi 09080709a9 Remove Issues.md 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-23 15:23:47 +02:00
Micaela Verucchi 7521d10ba7 Update README with gifs 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-23 15:07:52 +02:00
Micaela Verucchi ab349083bf Merge with cnet works, all tests passed. 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
v0.6 		2021-07-23 14:37:04 +02:00
Micaela Verucchi 4f9f27152a Update READMEs 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-23 10:31:34 +02:00
Davide Sapienza 0292e21c33 Merge remote-tracking branch 'origin/master' into cnet 2021-07-22 17:03:23 +02:00
Davide Sapienza 2bb70859da Add FPS results for CenterTrack 2D/3D 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2021-07-22 16:54:25 +02:00
Davide Sapienza b9f82510d3 Add demo_utils. 
This commit splits the utils file into two different files:
utils and demo_utils, to overcome some opencv problems caused
by demo_utils includes.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2021-07-22 10:45:18 +02:00
Davide Sapienza 1216e8bb74 Add camera calibration file reading for demo3d and demoTracker. 
Some minor fixes.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2021-07-21 16:14:53 +02:00
Davide Sapienza be2d361ac6 Update 3d detection 
This commit updates the CenternetDetection3d class and fixes
some bugs.

It also removes the resnet101 network for CenterNet 3D.
This network doesn't exist.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2021-07-21 15:51:13 +02:00
Davide Sapienza f78f7bfddc Fix link in readme files 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2021-07-21 15:35:17 +02:00
Micaela Verucchi f4e71a5a28 Add yolo4_berkeley_f1 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-21 12:56:00 +02:00
Harshvardhan Chandirasekar 548e87fc0e Merge branch 'ceccocats:master' into master 2021-07-21 12:44:24 +05:30
Micaela Verucchi 89b1bb7bee Add missing files 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-20 18:39:25 +02:00
Micaela Verucchi 318dfe4b55 merge with master 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2021-07-20 18:38:46 +02:00