AlexeyAB
b3254ed523
Fixed many warnings
6 years ago
Alexey
6d6202f666
Merge pull request #2621 from jveitchmichaelis/tiff_ext
...
Correctly locate annotation files for tiff images
6 years ago
Alexey
6f146a9d07
Merge pull request #2632 from kehonsyo/suppress_c4819
...
suppress C4819 warnings to the cuda file in CP932 environment.
6 years ago
AlexeyAB
84be2e8316
Minor fix
6 years ago
Alexey
e231729478
Merge branch 'master' into tiff_ext
6 years ago
AlexeyAB
4cd10ee547
Another one fix
6 years ago
AlexeyAB
2f0592d540
Compile fixes
6 years ago
none
9c3237acc8
suppress C4819 warnings to the cuda file in CP932 environment.
6 years ago
AlexeyAB
24dc5b7853
Another compile fix
6 years ago
AlexeyAB
d762df531f
Compile fix
6 years ago
AlexeyAB
b6e15f1656
ZED 3D Camera support added to ./uselib (yolo_console_cpp.exe) example
6 years ago
Josh Veitch-Michaelis
328cce0bf5
cleaner check for extension
6 years ago
Josh Veitch-Michaelis
f73ace38fa
fix output message
6 years ago
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.
6 years ago
Josh Veitch-Michaelis
fc2996968e
find annotation files for tiff images
6 years ago
Alexey
7a854302ef
Merge pull request #2542 from kossolax/patch-2
...
Segfault if height > width
6 years ago
Alexey
dd27d67f58
Merge pull request #2536 from cenit/dev/cenit/cmakeConfig
...
improve darknet library handling for downstream projects, other small updates
6 years ago
Stefano Sinigardi
4fc5c6e7b0
improve compatibility with latest pthreadVC renaming on vcpkg
6 years ago
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.
6 years ago
Stefano Sinigardi
8804479dbd
[appveyor] explode matrix to workaround time bomb
6 years ago
Stefano Sinigardi
2c8ff8db0d
create cmake targets for proper lib export
6 years ago
AlexeyAB
b751bac175
Fixed mAP calculation for CRNN layer during training
6 years ago
Alexey
ef803e05df
Merge pull request #2514 from cenit/dev/cenit/appveyor
...
fix cuda build on appveyor, remove old unsupported config on macOS
6 years ago
Stefano Sinigardi
fe9eaa9872
improve build script based on user feedback
6 years ago
AlexeyAB
540beb52ec
get & label OTB dataset
6 years ago
Stefano Sinigardi
8fd3e7ad25
switch debug/release build order, better futureproof for next cmakeTargets work
6 years ago
Stefano Sinigardi
40cdaaaa43
add artifacts on appveyor
6 years ago
Stefano Sinigardi
80c9fa76a4
refresh build scripts
6 years ago
AlexeyAB
d5cb0b490c
scripts/README.md
6 years ago
Stefano Sinigardi
80d0582ee4
fix cuda build on appveyor, remove old unsupported config on macOS
6 years ago
Alexey
42b8c0751e
Update Readme.md
6 years ago
AlexeyAB
dd0fdfb684
Compile fix
6 years ago
AlexeyAB
75f2a3e7cf
Added object Detection & Tracking using conv-rnn layer on frames from video
6 years ago
AlexeyAB
50956447f8
Fixed issue with killed mjpeg_stream
6 years ago
AlexeyAB
ec1b66ace2
Merge branch 'master' of github.com:AlexeyAB/darknet
6 years ago
AlexeyAB
e0596a1046
Added cmd/sh scripts for downloading ILSVRC2012 train & valid for Windows
6 years ago
Alexey
aa24da9fba
Merge pull request #2476 from cenit/dev/cenit/CI
...
[CI] add scripts for travis and appveyor
6 years ago
AlexeyAB
cfb80e39cd
Fixed http_stream.cpp
6 years ago
Stefano Sinigardi
2c0d857110
[appveyor-cuda] add another env variable
6 years ago
Stefano Sinigardi
6c7540420b
[opencv-cuda] handle properly cuda enabled but opencv built without cuda support
6 years ago
Stefano Sinigardi
278df5e89e
[appveyor] disable building opencv[cuda], it's too slow
6 years ago
Stefano Sinigardi
6dbfeee159
[appveyor] fix CUDA paths again
6 years ago
Stefano Sinigardi
52312f5f8f
[appveyor/cuda] extract all files from CUDA archive
6 years ago
AlexeyAB
9b09abe122
Fixed convolutional-layer when it is used as base for crnn-layer
6 years ago
AlexeyAB
e8c3905e54
Functions for fixing nan
6 years ago
Stefano Sinigardi
2acbfe9592
[ci] try cuda builds on windows, skip building uselib_track if opencv does not have cuda support
6 years ago
Stefano Sinigardi
139ddab7fa
remove unused cpu function in .cu file
6 years ago
Stefano Sinigardi
3b43d32dff
[ci] add tests for included libs, add link path for linux
6 years ago
Stefano Sinigardi
caeb0aee05
[CI] add CUDA build tests in matrix
6 years ago
Stefano Sinigardi
2a874b49a0
[CI] trying to improve resiliency
6 years ago