e3442e4764
Move the calibration table saving to the tests/network folder.
...
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2020-04-06 18:06:21 +02:00
bb157be82c
Add TKDNN_CALIB_IMG_PATH and TKDNN_CALIB_LABRL_PATH variable
...
This commit adds two variables for the calibration dataset.
The first is reffered to .txt file that contains the list
of the absolute paths of the images for the INT8 calitration.
The second is referred to .txt file that contains the list
of the absolute paths of the labels of the same images above.
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2020-03-30 18:55:32 +02:00
08e1801c60
Add the Int8 calibrator and the tensorRT Int8 inference
...
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2020-03-27 00:48:14 +01:00
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
555b32b5dc
Refactoring
...
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it >
2020-03-14 17:22:58 +01:00
13b4dffd71
csresnext50-panet-spp works with TensorRT
...
Signed-off-by: Francesco Gatti <gattifrancesco@hotmail.it >
2020-03-12 18:24:41 +01:00
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
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
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
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
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
c68d6f318e
Merge branch 'master' of https://github.com/ceccocats/tkDNN into cnet
2020-01-20 16:41:19 +01:00
8a4d1cac17
compile with tensorrt 5
2020-01-20 14:51:38 +01:00
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
da4f246157
add DLA, plugin for shortcut and leaky. new verison 0.4
2020-01-15 21:48:18 +01:00
23a1365dc4
Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet
2019-12-23 16:14:24 +01:00
7e7f480e2b
Yolov3_tiny works on tensorRT
...
Signed-off-by: fbagni <gattinomicino>
2019-12-23 16:11:41 +01:00
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
f0ea2c027f
Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet
2019-12-20 15:27:55 +01:00
854a4c316a
Add ResizeLayerRT plugin
...
Signed-off-by: nvidia <micaelaverucchi@gmail.com >
2019-12-20 15:27:41 +01:00
d889ed385d
CenterNet TensorRT works. TensorRT serialization not yet implemented
...
Signed-oof-by: Davide Sapienza <sapienza.dav@gmail.com >
2019-12-20 11:05:03 +01:00
44b2bce3ff
Yolo3_tiny CUDNN works, TensorRT doesn't. Add n_masks to Yolo layer.
...
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com >
2019-12-05 20:43:48 +00:00
a2db98670a
Add Yolov3 (COCO80) and Yolov3-tiny (COCO80), TensorRT for tiny not working
...
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com >
2019-12-04 17:01:40 +00:00
f247300469
test simple
2019-10-30 15:40:48 +01:00
6a1707f65e
Merge branch 'cnet' of https://github.com/ceccocats/tkDNN into cnet
2019-10-30 10:20:44 +01:00
8b64d1876f
deformable conv cu
2019-10-30 10:20:04 +01:00
d6d93a74f8
fix
2019-10-30 09:42:54 +01:00
33f36ab204
Deconv tensorrt
2019-10-30 09:40:29 +01:00
02936fa928
ResNet working
2019-10-29 17:21:31 +01:00
ec02c7292f
save layer names in rt file
2019-09-16 19:41:59 +02:00
a85367fa22
dla commented
2019-03-07 17:40:24 +01:00
3714155809
dla
2019-03-06 16:40:12 +01:00
c22219ad16
DLA number print
2019-03-06 13:02:39 +01:00
c7941666ec
demo for more yolo3
2019-02-19 08:43:35 +00:00
87fe342ca2
yoloRT load anchors
2019-02-18 21:39:14 +01:00
bdd8e0bc26
yolo3plug fix
2019-02-18 18:55:48 +00:00
88097a3774
yolo3 ok
2019-01-04 22:28:10 +01:00
2e8d0b1002
yolo3 86 route error
2018-12-23 16:20:17 +01:00
3bd725801d
upsample ok, route have problems
2018-12-22 23:56:01 +01:00
34be4cd00f
yoloRT layer
2018-12-22 21:26:50 +01:00
53b429551d
2 input shortcut
2018-12-21 16:16:38 +01:00
64626bf547
shortcut rt test
2018-12-21 15:53:39 +01:00
6249956469
namespace change
2018-12-14 21:55:16 +01:00
2cf8d8f6fc
fp16 implementation, TODO deallocate in LayerWgs
2017-08-30 14:37:25 +00:00
5595b8037b
interpret
2017-08-22 01:32:59 -07:00
0aa9de4ce8
better rt inference
2017-08-21 12:10:17 +00:00
2b4b9b8e49
F16 inference
2017-08-14 10:16:29 +00:00
66ad6bb1d6
input dim fix
2017-08-14 11:57:28 +02:00
fc9fb4f153
support check
2017-08-14 11:48:29 +02:00
b3a369dc29
RTinference test
2017-08-14 11:24:23 +02:00
Davide Sapienza
Micaela Verucchi
Francesco Gatti
luca
fbagni
Roberto Cavicchioli