mmr/tkDNN
Archived
1
0
Fork 0
Code Issues 46 Pull Requests 12 Releases 4 Activity
389 Commits 11 Branches 5 Tags
cbfc8ea4f2d8d52763b36e2c8ad2db4d4aa9d621
Commit Graph

207 Commits

Author SHA1 Message Date
Micaela Verucchi bbcc33c0cf Refactoring for detection NN 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-20 21:14:12 +01:00
Micaela Verucchi c7d9c38ea0 Add OPENCV_CUDA define, to allow having preprocess both in CPU and GPU (Mobilenet and Centernet) 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-20 10:21:11 +01:00
Micaela Verucchi 58fe723b6a Style fix, useless params removed 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-19 18:13:35 +01:00
Micaela Verucchi f44f377771 Add preprocess function, allow preprocess on GPU for mobilenetdetection 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-19 17:53:29 +01:00
Micaela Verucchi 43fd92f701 Fix conv2d with additional bias for tensorRT. Fix reshape deserialize. Mb2512 works with tensorRT 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-17 13:18:05 +01:00
Micaela Verucchi 1d388ca51a Add mobilenetv2ssdlite512 test. 
Works for CuDNN, not for tensorRT.
Modified channels in second convolution for classification headers from 126 to 486, when changing size from 300 to 512.
Added size 512 SSD specs and support to COCO dataset (81 classes, first BACKGROUND due to repo for training).
Refactoring class names.

Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-17 10:35:02 +01:00
Francesco Gatti 555b32b5dc Refactoring 
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it>
 2020-03-14 17:22:58 +01:00
Francesco Gatti cf7fbadcd2 Add function to download weigths if do no exist, for each test. Add some controls in map demo. 
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it>
 2020-03-14 17:02:07 +01:00
xavier 9d17cb42f4 Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet 2020-03-12 20:18:11 +01:00
Francesco Gatti 13b4dffd71 csresnext50-panet-spp works with TensorRT 
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it>
 2020-03-12 18:24:41 +01:00
Francesco Gatti f6527f51e3 Add csresnext50-panet-spp test. Works on CUDNN. Does not work with TensorRT 
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it>
 2020-03-11 18:37:26 +01:00
xavier d0d462c015 Merge 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-03-10 15:43:26 +01:00
xavier 2d46f16b70 Add tiny yolo 512 test 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-03-10 15:40:11 +01:00
Micaela Verucchi 4b85a2238a Add writing results on file for map demo 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-03-10 14:35:25 +01:00
Francesco Gatti 406f8cc9b3 - ImuOdom model into class 
- Route layer input array hard copy
- fix utils
 2020-03-09 19:44:21 +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
Micaela Verucchi fe206ea24c Fix dependencies problems 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
 2020-02-27 16:48:10 +01:00
xavier 3eb079dd13 Add Mobilenetv2 SSD Lite post and preprocessing, add mobilenet demo 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-02-26 17:42:20 +01:00
xavier 209a3e8492 Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet 2020-02-21 10:49:35 +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
Francesco Gatti 443691414a LSTM ok 2020-02-16 17:21:58 +01:00
Francesco Gatti 1a1c54f364 structure ok, result wrong 2020-02-16 17:08:19 +01:00
Francesco Gatti 10b7160677 works but it need cleaning 2020-02-16 16:28:39 +01:00
Francesco Gatti 4746121d43 LSTM params 2020-02-15 20:37:08 +01:00
Davide Sapienza 2c1df5619f Move pre-processing on GPU 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-14 18:44:13 +01:00
Francesco Gatti 4fa5d2c231 lstm return seq 2020-02-13 23:21:28 +01:00
Francesco Gatti c1c2173e4d removed unused var 2020-02-13 23:10:48 +01:00
Francesco Gatti 03d39d991c LSTM to be tested 2020-02-13 23:04:29 +01:00
Francesco Gatti a9c0db0bf6 LSTM cudnn test 2020-02-13 19:27:18 +01:00
Davide Sapienza 97b88ef52d Fix a bug in the deformable kernel. 
There was a wrong variable initialization.

Fixes: 51ffcb1f50 ("Optimize deformable kernel")

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-11 16:28:17 +01:00
xavier 1936e54870 Change README.md, add config.yaml, refactoring 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-02-11 11:25:42 +01:00
xavier b5c0baa99d Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet 2020-02-11 10:32:52 +01:00
Davide Sapienza 51ffcb1f50 Optimize deformable kernel 
Signed-off.by: Ignacio Sañudo Olmedo<ignacio.sanudoolmedo@unimore.it>
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-11 10:06:08 +01:00
xavier d601e980f6 Add avg precision, recall, f1score computation, other minors 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-02-10 18:19:08 +01:00
Davide Sapienza 9007e25a00 Remove mallocs and frees from the kernels 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-07 14:50:05 +01:00
xavier 289a97d06c Refactoring map_demo, add evaluation.h and evaluation.cpp 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-02-07 12:47:02 +01:00
Davide Sapienza 2503eba173 Fix memory leak 
This commit moves cublasCreate out from dcn_v2_cuda_forward
to save some milliseconds and it adds cublasDestroy (cause
of memory leak).

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-06 23:09:12 +01:00
Davide Sapienza 70eb5214cc Change CenterNet input dimension. 
This commit changes the image input dimension, it updates the
CenterNet detection class.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-06 18:08:06 +01:00
Davide Sapienza 4616be0738 Add grouped convolutions in CUDNN and tensorRT. 
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-02-05 14:32:58 +01:00
Davide Sapienza 7f239efdc0 Centernet: fix pooling problem, add centrnet demo 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-01-21 12:50:18 +01:00
Davide Sapienza c68d6f318e Merge branch 'master' of https://github.com/ceccocats/tkDNN into cnet 2020-01-20 16:41:19 +01:00
luca 8a4d1cac17 compile with tensorrt 5 2020-01-20 14:51:38 +01:00
Davide Sapienza b23cf9fe70 Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet 
Signed-off-by: Michaela Verucchi <micaelaverucchi@gmail.com>
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-01-20 12:35:27 +01:00
Davide Sapienza 7838cb4922 Pre-process, Process and Post-process work 
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com>
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
 2020-01-20 12:27:49 +01:00
xavier da4f246157 add DLA, plugin for shortcut and leaky. new verison 0.4 2020-01-15 21:48:18 +01:00
xavier 0f0c8c28e1 Merge with master, works with Jetpack 4.3 
Signed-off-by: xavier <micaelaverucchi@gmail.com>
 2020-01-15 19:24:19 +01:00
xavier c32a0be257 Batchnorm eps fix, works on jetpack 4.3 2020-01-15 18:06:02 +01:00
fbagni 23a1365dc4 Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet 2019-12-23 16:14:24 +01:00
fbagni 7e7f480e2b Yolov3_tiny works on tensorRT 
Signed-off-by: fbagni <gattinomicino>
 2019-12-23 16:11:41 +01:00
Davide Sapienza 5272f1cde6 CenterNet TensorRT serialization works 
This commit adds the Deformable layer serialization.

Signed-oof-by: Davide Sapienza <sapienza.dav@gmail.com>
 2019-12-23 15:31:13 +01:00