94e558003d
Shelfnet works on tensorRT (shortcut need to be fixed)
...
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com >
2020-06-23 12:50:24 +02:00
6fd261f628
Shelfnet works on cuDNN. To test everything else
...
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com >
2020-06-22 18:11:19 +02:00
db0f8a4d99
Support yolov4
...
Signed-off-by: Micaela Verucchi <micaelaverucchi@gmail.com >
2020-04-28 20:35:30 +02:00
6e5ab031c4
Deformable batch works
...
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2020-04-25 02:47:31 +02:00
0e5c90634f
Fix the Deformable convolution code sintax.
...
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2020-04-08 11:14:34 +02:00
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
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
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
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
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
e99b353d8b
Fix the inference operation of the deformable convolutional layer.
...
This commit removes the malloc operation in the inference
method and adds the sigmoid kernel.
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2019-12-19 14:47:57 +01:00
df888a3457
Add CenterNet based on Resnet101, TensorRT not implemented.
...
Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com >
2019-12-18 18:59:54 +01:00
8b64d1876f
deformable conv cu
2019-10-30 10:20:04 +01:00
ca62784f57
include dir fix, cmake dir
2019-09-17 15:22:39 +02:00
Micaela Verucchi
dsapienza
Davide Sapienza
Francesco Gatti