Commit Graph

9 Commits

Author SHA1 Message Date
Francesco Gatti ef91439c87 batch size > 1 2020-04-21 19:20:44 +02:00
Francesco Gatti c248a94101 warning fix 2020-04-09 01:00:14 +02:00
Davide Sapienza 2fbd24625c 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
Davide Sapienza 03d2b88fa6 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
Davide Sapienza 0474f019cf Add TKDNN_MODE variable to the name of the network.
This commit permits to obtain different .rt files for different
precision optimizations of the same network.

Signed-off-by: Davide Sapienza <sapienza.dav@gmail.com>
2020-03-30 15:08:25 +02:00
xavier 808a84131c 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 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
Francesco Gatti f9afee2f3b deconv layer cudnn 2019-10-30 00:05:22 +01:00
Francesco Gatti ca62784f57 include dir fix, cmake dir 2019-09-17 15:22:39 +02:00