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
1,447 Commits 3 Branches 0 Tags
d91d59a22fea9c266f06c2ae5edb23d38fd83c20
Commit Graph

1447 Commits

This Branch
This Branch
All Branches
Author SHA1 Message Date
AlexeyAB
2f0592d540 Compile fixes 2019-03-18 15:22:38 +03:00
none
9c3237acc8 suppress C4819 warnings to the cuda file in CP932 environment. 2019-03-18 09:44:43 +09:00
none
44c881233a add Visual studio 2017 "Enterprise" edition to edition check. 2019-03-18 09:17:17 +09:00
AlexeyAB
24dc5b7853 Another compile fix 2019-03-18 02:56:32 +03:00
AlexeyAB
d762df531f Compile fix 2019-03-18 02:53:48 +03:00
AlexeyAB
b6e15f1656 ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example 2019-03-18 02:48:52 +03:00
Stefano Sinigardi
93ff87f74b [win-pthreads] correctly handle static libs 2019-03-16 22:24:36 +01:00
Josh Veitch-Michaelis
328cce0bf5 cleaner check for extension 2019-03-15 22:51:15 +00:00
Josh Veitch-Michaelis
f73ace38fa fix output message 2019-03-15 22:10:38 +00:00
Josh Veitch-Michaelis
1a3971f5f7 alert user if annotation file doesn't exist 
Currently darknet will continue silently if an annotation file isn't found. This can happen when the user provides an unsupported image format and the extension is not replaced. Probably this function should be modified to change any extension to .txt, since OpenCV (for example) supports many image extensions.
 2019-03-15 22:01:04 +00:00
Josh Veitch-Michaelis
fc2996968e find annotation files for tiff images 2019-03-15 21:58:53 +00:00
Stefano Sinigardi
f9085d8c2a remove unused cmake module 2019-03-13 23:45:01 +01:00
Stefano Sinigardi
a3a836f56a add a switch to force build with local libs 2019-03-13 23:40:44 +01:00
Stefano Sinigardi
d6294761be x64 only 2019-03-13 23:36:13 +01:00
Stefano Sinigardi
5be12ce058 move Stb lib to 3rdparty folder 2019-03-13 23:21:37 +01:00
Alexey
7a854302ef Merge pull request #2542 from kossolax/patch-2 
Segfault if height > width
 2019-03-13 02:41:42 +03:00
Alexey
dd27d67f58 Merge pull request #2536 from cenit/dev/cenit/cmakeConfig 
improve darknet library handling for downstream projects, other small updates
 2019-03-12 01:19:02 +03:00
Stefano Sinigardi
4fc5c6e7b0 improve compatibility with latest pthreadVC renaming on vcpkg 2019-03-08 21:48:23 +01:00
Steve Zaretti
17fed7c4e2 Segfault if height > width 
./darknet classifier train data/sort.data cfg/alexnet.cfg -dont_show
alexnet
1
 compute_capability = 750, cudnn_half = 1 
layer     filters    size              input                output
   0 conv     96 11 x11 / 4   128 x 256 x   3   ->    30 x  62 x  96 0.130 BF
   1 max          3 x 3 / 2    30 x  62 x  96   ->    14 x  30 x  96 0.000 BF
   2 conv    256  5 x 5 / 1    14 x  30 x  96   ->    14 x  30 x 256 0.516 BF
   3 max          3 x 3 / 2    14 x  30 x 256   ->     6 x  14 x 256 0.000 BF
   4 conv    384  3 x 3 / 1     6 x  14 x 256   ->     6 x  14 x 384 0.149 BF
   5 conv    384  3 x 3 / 1     6 x  14 x 384   ->     6 x  14 x 384 0.223 BF
   6 conv    256  3 x 3 / 1     6 x  14 x 384   ->     6 x  14 x 256 0.149 BF
   7 max          3 x 3 / 2     6 x  14 x 256   ->     2 x   6 x 256 0.000 BF
   8 connected                            3072  ->  4096
   9 dropout       p = 0.50               4096  ->  4096
  10 connected                            4096  ->  4096
  11 dropout       p = 0.50               4096  ->  4096
  12 connected                            4096  ->  1261
  13 softmax                                        1261
  14 cost                                           1261
Total BFLOPS 1.167 
 Allocate additional workspace_size = 1940.23 MB 
Learning Rate: 0.01, Momentum: 0.9, Decay: 0.0005
893253
Loaded: 0.205056 seconds
Segmentation fault (core dumped)




 This PR fix this issue:
./darknet classifier train data/sort.data cfg/alexnet.cfg -dont_show
alexnet
1
 compute_capability = 750, cudnn_half = 1 
layer     filters    size              input                output
   0 conv     96 11 x11 / 4   128 x 256 x   3   ->    30 x  62 x  96 0.130 BF
   1 max          3 x 3 / 2    30 x  62 x  96   ->    14 x  30 x  96 0.000 BF
   2 conv    256  5 x 5 / 1    14 x  30 x  96   ->    14 x  30 x 256 0.516 BF
   3 max          3 x 3 / 2    14 x  30 x 256   ->     6 x  14 x 256 0.000 BF
   4 conv    384  3 x 3 / 1     6 x  14 x 256   ->     6 x  14 x 384 0.149 BF
   5 conv    384  3 x 3 / 1     6 x  14 x 384   ->     6 x  14 x 384 0.223 BF
   6 conv    256  3 x 3 / 1     6 x  14 x 384   ->     6 x  14 x 256 0.149 BF
   7 max          3 x 3 / 2     6 x  14 x 256   ->     2 x   6 x 256 0.000 BF
   8 connected                            3072  ->  4096
   9 dropout       p = 0.50               4096  ->  4096
  10 connected                            4096  ->  4096
  11 dropout       p = 0.50               4096  ->  4096
  12 connected                            4096  ->  1261
  13 softmax                                        1261
  14 cost                                           1261
Total BFLOPS 1.167 
 Allocate additional workspace_size = 1940.23 MB 
Learning Rate: 0.01, Momentum: 0.9, Decay: 0.0005
893253
Loaded: 0.509795 seconds
1, 0.000: 4.070450, 4.070450 avg, 0.010000 rate, 0.310202 seconds, 128 images
Loaded: 0.416345 seconds
2, 0.000: 4.069521, 4.070357 avg, 0.010000 rate, 0.055622 seconds, 256 images
Loaded: 0.451087 seconds



I'll tell you later if training is converging.
 2019-03-06 10:19:13 +01:00
Stefano Sinigardi
8804479dbd [appveyor] explode matrix to workaround time bomb 2019-03-05 18:35:07 +01:00
Stefano Sinigardi
2c8ff8db0d create cmake targets for proper lib export 2019-03-05 18:34:53 +01:00
AlexeyAB
b751bac175 Fixed mAP calculation for CRNN layer during training 2019-03-05 02:15:44 +03:00
Alexey
ef803e05df Merge pull request #2514 from cenit/dev/cenit/appveyor 
fix cuda build on appveyor, remove old unsupported config on macOS
 2019-03-04 17:04:41 +03:00
Stefano Sinigardi
fe9eaa9872 improve build script based on user feedback 2019-03-04 10:22:13 +01:00
AlexeyAB
540beb52ec get & label OTB dataset 2019-03-04 04:05:17 +03:00
Stefano Sinigardi
8fd3e7ad25 switch debug/release build order, better futureproof for next cmakeTargets work 2019-03-03 23:35:38 +01:00
Stefano Sinigardi
40cdaaaa43 add artifacts on appveyor 2019-03-03 19:57:40 +01:00
Stefano Sinigardi
80c9fa76a4 refresh build scripts 2019-03-03 16:55:15 +01:00
AlexeyAB
d5cb0b490c scripts/README.md 2019-03-03 15:09:41 +03:00
Stefano Sinigardi
80d0582ee4 fix cuda build on appveyor, remove old unsupported config on macOS 2019-03-03 13:07:49 +01:00
Alexey
42b8c0751e Update Readme.md 2019-03-03 13:18:32 +03:00
AlexeyAB
dd0fdfb684 Compile fix 2019-03-02 03:37:55 +03:00
AlexeyAB
75f2a3e7cf Added object Detection & Tracking using conv-rnn layer on frames from video 2019-03-02 03:32:24 +03:00
AlexeyAB
50956447f8 Fixed issue with killed mjpeg_stream 2019-03-01 19:01:14 +03:00
AlexeyAB
ec1b66ace2 Merge branch 'master' of github.com:AlexeyAB/darknet 2019-03-01 16:56:21 +03:00
AlexeyAB
e0596a1046 Added cmd/sh scripts for downloading ILSVRC2012 train & valid for Windows 2019-03-01 16:56:00 +03:00
Alexey
aa24da9fba Merge pull request #2476 from cenit/dev/cenit/CI 
[CI] add scripts for travis and appveyor
 2019-03-01 16:19:18 +03:00
AlexeyAB
cfb80e39cd Fixed http_stream.cpp 2019-03-01 15:49:23 +03:00
Stefano Sinigardi
2c0d857110 [appveyor-cuda] add another env variable 2019-03-01 12:03:41 +01:00
Stefano Sinigardi
6c7540420b [opencv-cuda] handle properly cuda enabled but opencv built without cuda support 2019-03-01 11:23:31 +01:00
Stefano Sinigardi
278df5e89e [appveyor] disable building opencv[cuda], it's too slow 2019-03-01 11:11:25 +01:00
Stefano Sinigardi
6dbfeee159 [appveyor] fix CUDA paths again 2019-03-01 09:27:29 +01:00
Stefano Sinigardi
52312f5f8f [appveyor/cuda] extract all files from CUDA archive 2019-02-28 21:04:58 +01:00
AlexeyAB
9b09abe122 Fixed convolutional-layer when it is used as base for crnn-layer 2019-02-28 20:47:22 +03:00
AlexeyAB
e8c3905e54 Functions for fixing nan 2019-02-28 20:38:13 +03:00
Stefano Sinigardi
2acbfe9592 [ci] try cuda builds on windows, skip building uselib_track if opencv does not have cuda support 2019-02-28 18:13:17 +01:00
Stefano Sinigardi
139ddab7fa remove unused cpu function in .cu file 2019-02-28 18:13:17 +01:00
Stefano Sinigardi
3b43d32dff [ci] add tests for included libs, add link path for linux 2019-02-28 18:13:17 +01:00
Stefano Sinigardi
caeb0aee05 [CI] add CUDA build tests in matrix 2019-02-28 18:13:09 +01:00
Stefano Sinigardi
2a874b49a0 [CI] trying to improve resiliency 2019-02-28 18:13:09 +01:00