mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity
611 Commits 11 Branches 5 Tags
226875567b70b550906f6ead120fa84625b5fed8
Commit Graph

34 Commits

Author SHA1 Message Date
Francesco Gatti 5e71b99265 YoloRT save bias, mask and clasesName into RT file 2022-03-30 20:46:51 +02:00
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 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
hchandirasekar fb52444cdc Replaced dynamic arrays with std::vector ,works on linux ..needs to be tested on windows after clearing up the lnk2019 error 2021-01-25 04:12:05 +05:30
Micaela Verucchi 702791e41a Add support for yolov4x-mish. 
Changes:
- add parameters nms_kind, nms_thresh, new_coords to yolo layer and darknet parser
- added diou nms, new method to compute the BBs
- created test for yolov4x-mish called yolo4x

Tested, all tests work.
Problem to solve: little loss in mAP of yolo4x

Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-11-23 11:29:32 +01:00
Micaela Verucchi f778e1aa99 Fixed boxes to float, add conf thresh as param 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-08-05 19:55:10 +02:00
Francesco Gatti a5d2d4792a fix coords convert 2020-07-27 13:52:39 +02:00
Francesco Gatti 3a0802d70c Resolve detection objects pick by prob threshold. 
Before this it will only pick the last object with prob > thresh wich is absolutely wrong
Now it picks all the objects with prob > thesh.

fixes #94
 2020-07-27 13:45:42 +02:00
Micaela Verucchi 854e1d909a Fix original size 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-05-19 16:33:45 +02:00
Micaela Verucchi 40456592fc Adapt detection classes to use batches, adapt demos, update README 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-05-14 16:41:51 +02:00
Micaela Verucchi 533bb48789 Add json detection creation for codalab check 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-05-11 11:57:58 +02:00
Micaela Verucchi ae1d8cd9e6 Refactoring & documentation 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-04-08 11:20:48 +02:00
Micaela Verucchi 674c61d280 Add opencv script, modified macro, add opencv section into readme 
Signed-off-by: Micaela Verucchi <micaela.verucchi@unimore.it>
 2020-04-06 17:25:53 +02:00
Micaela Verucchi af13e7c954 Add getMemoryUsage function, detection update moved in abstract lass, splitted execution time in pre-inf-post, other minors. 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-04-01 19:18:43 +02:00
Micaela Verucchi 3eda9b9219 Add GPU version for yolo3detection 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-23 21:29:29 +01:00
Micaela Verucchi df37e11709 Modify map demo, using abstract class. Move draw function in abstract class 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-23 19:32:37 +01:00
Micaela Verucchi bbcc33c0cf Refactoring for detection NN 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-20 21:14:12 +01:00
Davide Sapienza 296a6cbc87 Add draw method to Yolo3Detection class. 
Update yolo demo

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-03-03 17:08:25 +01:00
xavier 38a1b9dcb2 Add Mobilenet2SSDLite test 
The new test works both with TensorRT and cuDNN. Preprocessing and
Postprocessing are missing. Add ClippedReLU (for ReLU6), groups for
Conv2d, additional bias for convolution.

Other minors:
-move the timer in the detector to measure all the
processing time for a given frame (both centernet and yolo);
-add int8 flag.

Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-21 10:45:46 +01:00
Davide Sapienza c68d6f318e Merge branch 'master' of https://github.com/ceccocats/tkDNN into cnet 2020-01-20 16:41:19 +01:00
xavier da4f246157 add DLA, plugin for shortcut and leaky. new verison 0.4 2020-01-15 21:48:18 +01:00
nvidia 854a4c316a Add ResizeLayerRT plugin 
Signed-off-by: nvidia <micaelaverucchi@gmail.com>
 2019-12-20 15:27:41 +01:00
Francesco Gatti ec02c7292f save layer names in rt file 2019-09-16 19:41:59 +02:00
mbosi a038e966d9 yolo3 flir ok 2019-09-15 16:19:30 +02:00
mbosi 8c629ebe7b string input and flir test 2019-09-14 19:03:13 +02:00
Francesco Gatti 1aa4f0275d color fix 2019-02-19 08:57:51 +00:00
Francesco Gatti c7941666ec demo for more yolo3 2019-02-19 08:43:35 +00:00
Francesco Gatti 87fe342ca2 yoloRT load anchors 2019-02-18 21:39:14 +01:00
Francesco Gatti bdd8e0bc26 yolo3plug fix 2019-02-18 18:55:48 +00:00
Francesco Gatti 13063b904d yolo3 ok 2019-02-18 15:51:57 +00:00
Francesco Gatti 0d682136de yolo3 berkeley ok 2019-02-18 15:37:39 +00:00