mirror/darknet
1
0
Fork 0
mirror of https://github.com/pjreddie/darknet.git synced 2023-08-10 21:13:14 +03:00
Code Issues Projects Releases Wiki Activity
Files
7e9416aa8011de1623c91db47bb75c3a7df100eb
darknet/src
History
John Aughey 7e9416aa80 Making a pointer version of network_predict for python. 
The python binding requires the network struct to be passed
as a pointer to it rather than a struct copy.
2019-02-05 11:35:45 -06:00
..
.editorconfig
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
activation_kernels.cu
Minor performance improvement
2019-02-03 00:18:30 +03:00
activation_layer.c
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
activation_layer.h
…
activations.c
Minor speedup on CPU
2019-01-26 19:12:46 +03:00
activations.h
Minor fixes
2019-02-04 23:29:06 +03:00
art.c
Supported OpenCV 3.0 and 2.4.13. Supported Windows and Linux.
2017-08-03 00:48:29 +03:00
avgpool_layer_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
avgpool_layer.c
🔥 🔥 :dragonite:
2016-11-16 00:15:46 -08:00
avgpool_layer.h
…
batchnorm_layer.c
Minor performance improvement
2019-02-03 00:18:30 +03:00
batchnorm_layer.h
stable
2016-05-11 10:45:50 -07:00
blas_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
blas.c
Minor speedup on CPU
2019-01-26 19:12:46 +03:00
blas.h
CUDA minor performance improvement
2019-01-16 18:08:11 +03:00
box.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
box.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
captcha.c
better multigpu
2016-09-20 11:34:49 -07:00
cifar.c
Changed class to class_id
2018-03-01 15:14:58 +03:00
classifier.c
Fixed LSTM-layer
2019-01-28 20:22:14 +03:00
classifier.h
so much need to commit
2016-05-06 16:25:16 -07:00
coco.c
Added -mjpeg_port 8090 for Training. Loss-chart saved to chart.png even when used -dont_show.
2019-01-12 13:45:37 +03:00
col2im_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
col2im.c
updates and things
2016-09-01 16:48:41 -07:00
col2im.h
…
compare.c
Changed class to class_id
2018-03-01 15:14:58 +03:00
connected_layer.c
Minor fixes
2019-02-04 23:29:06 +03:00
connected_layer.h
Fixed RNN (RNN, GRU, LSTM) with cuDNN (batch-norm)
2019-01-27 03:42:44 +03:00
convolutional_kernels.cu
Fixed bug in Tensor Cores training
2019-02-05 19:33:10 +03:00
convolutional_layer.c
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
convolutional_layer.h
LSTM, RNN, GRU - use connected_layer that uses cuDNN. Fixed CRNN for conv-layer with cuDNN.
2019-01-28 23:50:51 +03:00
cost_layer.c
🔥 🔥 :dragonite:
2016-11-16 00:15:46 -08:00
cost_layer.h
…
cpu_gemm.c
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
crnn_layer.c
Fixed CRNN (RNN based on Convolution) layer
2019-02-01 01:30:02 +03:00
crnn_layer.h
Fixed CRNN (RNN based on Convolution) layer
2019-02-01 01:30:02 +03:00
crop_layer_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
crop_layer.c
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
crop_layer.h
lots of stuff
2016-01-28 12:30:38 -08:00
cuda.c
DEBUG=1 fixed
2019-02-05 00:36:17 +03:00
cuda.h
Checks Compute Capability and forcibly disables Tensor Cores for CC < 7.0
2019-02-04 23:28:40 +03:00
darknet.c
CUDA_CHECK definition for debug
2019-02-03 00:19:04 +03:00
data.c
Fix OpenCV compilation. maxpool_layer on GPU uses cuDNN.
2018-10-10 13:51:36 +03:00
data.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
deconvolutional_kernels.cu
good chance I didn't break anything
2016-09-12 13:55:20 -07:00
deconvolutional_layer.c
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
deconvolutional_layer.h
lots of stuff
2016-01-28 12:30:38 -08:00
demo.c
Fixed LSTM-layer
2019-01-28 20:22:14 +03:00
demo.h
Added -mjpeg_port 8090 for Training. Loss-chart saved to chart.png even when used -dont_show.
2019-01-12 13:45:37 +03:00
detection_layer.c
Added Yolo v3
2018-03-28 02:59:03 +03:00
detection_layer.h
Added Yolo v3
2018-03-28 02:59:03 +03:00
detector.c
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
dice.c
better multigpu
2016-09-20 11:34:49 -07:00
dropout_layer_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
dropout_layer.c
🔥 🔥 :dragonite:
2016-11-16 00:15:46 -08:00
dropout_layer.h
lots of stuff
2016-01-28 12:30:38 -08:00
gemm.c
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
gemm.h
Minor fix
2019-01-06 15:45:10 +03:00
getopt.c
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
getopt.h
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
gettimeofday.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
gettimeofday.h
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
go.c
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
gru_layer.c
LSTM, RNN, GRU - use connected_layer that uses cuDNN. Fixed CRNN for conv-layer with cuDNN.
2019-01-28 23:50:51 +03:00
gru_layer.h
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
http_stream.cpp
Add try-catch to the http_stream.cpp
2019-01-31 14:33:05 +03:00
http_stream.h
Another minor fix
2019-01-22 17:31:07 +03:00
im2col_kernels.cu
Minor fixes
2019-02-04 23:29:06 +03:00
im2col.c
updates and things
2016-09-01 16:48:41 -07:00
im2col.h
XNOR uses Tensor Cores on Turing GPU CC>=7.3 (not Volta)
2019-02-02 00:24:34 +03:00
image.c
Training minor fix
2019-01-14 14:42:48 +03:00
image.h
Minor fix
2019-01-14 13:56:42 +03:00
layer.c
Another CUDA performance improvements
2019-01-18 16:29:54 +03:00
layer.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
list.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
list.h
Fixed memory leaks for Yolo: train, test
2018-05-23 18:27:18 +03:00
local_layer.c
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
local_layer.h
…
lstm_layer.c
Fixed CRNN (RNN based on Convolution) layer
2019-02-01 01:30:02 +03:00
lstm_layer.h
add LSTM layer
2019-01-23 22:02:09 -06:00
matrix.c
Fixed calc_anchors
2019-01-21 14:54:51 +03:00
matrix.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
maxpool_layer_kernels.cu
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
maxpool_layer.c
Fixed mAP chart during training for CUDNN=1
2018-12-25 02:34:32 +03:00
maxpool_layer.h
get_coco_dataset.sh downloads MS COCO dataset from images.cocodataset.org
2018-12-21 23:07:37 +03:00
network_kernels.cu
Minor performance improvement
2019-02-03 00:18:30 +03:00
network.c
Making a pointer version of network_predict for python.
2019-02-05 11:35:45 -06:00
network.h
Making a pointer version of network_predict for python.
2019-02-05 11:35:45 -06:00
nightmare.c
stuff
2016-02-29 13:54:12 -08:00
normalization_layer.c
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
normalization_layer.h
…
option_list.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
option_list.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
parser.c
CHECK_CUDA is used everywhere
2019-02-05 16:18:36 +03:00
parser.h
Fixed LSTM-layer
2019-01-28 20:22:14 +03:00
region_layer.c
Fixed memory allocation
2019-01-26 23:25:09 +03:00
region_layer.h
Fixed memory allocation
2019-01-26 23:25:09 +03:00
reorg_layer.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
reorg_layer.h
stuff and things
2016-11-07 23:42:19 -08:00
reorg_old_layer.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
reorg_old_layer.h
Fixed reorg_layer. Old reorg can be used as [reorg_old] in the cfg-file.
2018-03-03 18:09:46 +03:00
rnn_layer.c
Fixed CRNN (RNN based on Convolution) layer
2019-02-01 01:30:02 +03:00
rnn_layer.h
So I have this new programming paradigm.......
2016-09-24 23:12:54 -07:00
rnn_vid.c
Supported OpenCV 3.0 and 2.4.13. Supported Windows and Linux.
2017-08-03 00:48:29 +03:00
rnn.c
Minor fix
2019-02-01 01:32:26 +03:00
route_layer.c
Another CUDA performance improvements
2019-01-18 16:29:54 +03:00
route_layer.h
hey
2016-11-15 22:53:58 -08:00
shortcut_layer.c
Minor speedup on CPU
2019-01-26 19:12:46 +03:00
shortcut_layer.h
shortcut_layer resize for random=1
2018-03-16 01:49:01 +03:00
softmax_layer.c
Classifier now is working. The file softmax_layer.c was outdated
2018-10-06 14:12:02 -05:00
softmax_layer.h
lots of stuff
2016-01-28 12:30:38 -08:00
stb_image_write.h
Fixed STB
2017-08-09 13:34:58 +03:00
stb_image.h
Fixed STB
2017-08-09 13:34:58 +03:00
super.c
better multigpu
2016-09-20 11:34:49 -07:00
swag.c
better multigpu
2016-09-20 11:34:49 -07:00
tag.c
better multigpu
2016-09-20 11:34:49 -07:00
tree.c
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
tree.h
Added include/darknet.h
2019-01-06 23:51:38 +03:00
unistd.h
Sources fixed - Yolo v2 can be used on Windows (MSVS 2015 + CUDA 8.0)
2016-12-02 17:13:40 +03:00
upsample_layer.c
Added Yolo v3
2018-03-28 02:59:03 +03:00
upsample_layer.h
One more try
2018-03-28 03:27:35 +03:00
utils.c
Minor fix
2019-02-01 01:32:26 +03:00
utils.h
Minor fix
2019-02-01 01:32:26 +03:00
voxel.c
Supported OpenCV 3.0 and 2.4.13. Supported Windows and Linux.
2017-08-03 00:48:29 +03:00
writing.c
better multigpu
2016-09-20 11:34:49 -07:00
yolo_console_dll.cpp
Just used spaces for indents instead of Tabs
2018-07-10 23:29:15 +03:00
yolo_layer.c
Minor fixes
2019-02-04 23:29:06 +03:00
yolo_layer.h
Minor fixes
2018-04-11 23:04:23 +03:00
yolo_v2_class.cpp
Fixed DLL/SO
2019-01-28 20:32:30 +03:00
yolo.c
Added -mjpeg_port 8090 for Training. Loss-chart saved to chart.png even when used -dont_show.
2019-01-12 13:45:37 +03:00