AlexeyAB
|
63a2f005aa
|
Compile fix
|
2019-01-09 13:46:53 +03:00 |
AlexeyAB
|
e6eba22adb
|
Graceful shutdown closes sockets
|
2019-01-09 03:20:29 +03:00 |
AlexeyAB
|
c31a245665
|
Experimental. Use -json_port 8070 to allow connection to the port:8070 to get json-stream
|
2019-01-09 00:11:59 +03:00 |
AlexeyAB
|
ead84c8ba2
|
Now you can un-comment several lines for saving images of cropped objects to /result_img/ directory
|
2019-01-08 18:34:59 +03:00 |
AlexeyAB
|
fd0df9297c
|
Fixed compiling yolo_cpp_dll.sln in Debug & x64
|
2019-01-08 01:21:19 +03:00 |
AlexeyAB
|
3ff5084590
|
Added include/darknet.h
|
2019-01-06 23:51:38 +03:00 |
AlexeyAB
|
c56931dd75
|
Compile fix
|
2019-01-06 16:00:00 +03:00 |
AlexeyAB
|
c75fbb5f2e
|
Minor fix
|
2019-01-06 15:45:10 +03:00 |
Alexey
|
333f1de2c3
|
Update Readme.md
|
2019-01-06 01:27:41 +03:00 |
AlexeyAB
|
48d461f9bd
|
Temporary experimental XNOR improvements on CPU
|
2019-01-04 23:19:45 +03:00 |
Alexey
|
1a2f16e9d9
|
Update Readme.md
|
2019-01-04 19:01:33 +03:00 |
AlexeyAB
|
29f509e2b7
|
Added yolov3-tiny_3l.cfg for small objects
|
2019-01-04 18:46:10 +03:00 |
AlexeyAB
|
527578744b
|
Minor fix
|
2018-12-29 22:56:38 +03:00 |
AlexeyAB
|
cb94ef9308
|
Use `dont_show` in the obj.data file to disable detection for a specific class
|
2018-12-29 21:52:31 +03:00 |
AlexeyAB
|
08f0f80b66
|
Adam optimizer fixed
|
2018-12-29 01:32:11 +03:00 |
AlexeyAB
|
64e478db07
|
Fix training approach (convolutional layer)
|
2018-12-27 00:31:28 +03:00 |
AlexeyAB
|
dc827f4c1c
|
Minor fix for mAP calculation during training
|
2018-12-27 00:30:05 +03:00 |
Alexey
|
95773cfb42
|
Merge pull request #2111 from heethesh/master
Fixed typo in weights file
|
2018-12-26 16:34:34 +03:00 |
Heethesh Vhavle
|
5bc7c06891
|
Fixed typo in weights file
|
2018-12-26 17:21:54 +04:00 |
AlexeyAB
|
1b20072096
|
Optimized memory consumption during Training with -map flag
|
2018-12-25 21:06:13 +03:00 |
AlexeyAB
|
b87080882a
|
Minor fix for multi-GPU training with -map flag
|
2018-12-25 18:21:32 +03:00 |
AlexeyAB
|
06232b31f4
|
Compile fix
|
2018-12-25 02:38:33 +03:00 |
AlexeyAB
|
f38d060137
|
Fixed mAP chart during training for CUDNN=1
|
2018-12-25 02:34:32 +03:00 |
Alexey
|
78d1ade380
|
Update Readme.md
|
2018-12-23 01:00:16 +03:00 |
AlexeyAB
|
7d0efaa936
|
get_coco_dataset.sh downloads MS COCO dataset from images.cocodataset.org
|
2018-12-21 23:07:37 +03:00 |
AlexeyAB
|
49189c22e8
|
Fix mAP chart
|
2018-12-19 01:54:18 +03:00 |
Alexey
|
9f5478983d
|
Update Readme.md
|
2018-12-15 19:29:19 +03:00 |
Alexey
|
2c04b6ab9a
|
Update Readme.md
|
2018-12-13 16:29:16 +03:00 |
AlexeyAB
|
f0bed8ef73
|
Fixed drawing mAP
|
2018-12-12 23:20:44 +03:00 |
Alexey
|
6b4dca27d3
|
Update Readm.emd
|
2018-12-12 18:05:09 +03:00 |
AlexeyAB
|
3969ce30ed
|
Speedup Tensor Cores: 1st layer uses FP32 and pre-allocate GPU memory for Tensor Cores
|
2018-12-11 23:48:58 +03:00 |
AlexeyAB
|
25f133d6ef
|
Another one minor fix
|
2018-12-11 21:26:36 +03:00 |
AlexeyAB
|
cb998db949
|
Some fix for CUDNN_HALF
|
2018-12-11 21:16:18 +03:00 |
AlexeyAB
|
e9226be3ed
|
calc_anchors can be used without OpenCV, and it uses (1-IoU) instead of Euclidean distance
|
2018-12-11 15:59:23 +03:00 |
AlexeyAB
|
fb1ee79576
|
Minor fix
|
2018-12-10 02:22:45 +03:00 |
Alexey
|
3256967119
|
Update Readme.md
|
2018-12-10 01:37:40 +03:00 |
AlexeyAB
|
a621235783
|
Switch to Tensor Cores after 2000 iterations.
|
2018-12-10 01:35:08 +03:00 |
AlexeyAB
|
89c6213af0
|
When is used -map flag for training - calculate mAP for each 4 Epochs.
|
2018-12-10 01:33:32 +03:00 |
Alexey
|
ca3bf2fa92
|
Update Readme.md
|
2018-12-10 01:30:48 +03:00 |
Alexey
|
89cb877689
|
Update Readme.md
|
2018-12-10 01:24:58 +03:00 |
AlexeyAB
|
7bd6b2f720
|
Compilation fix
|
2018-12-09 18:28:51 +03:00 |
AlexeyAB
|
dc7f8a32ae
|
mAP calculation during training, if is used flag -map
|
2018-12-09 18:18:47 +03:00 |
AlexeyAB
|
742bb7c7ce
|
Compile fix
|
2018-12-07 22:52:07 +03:00 |
AlexeyAB
|
7c2f302321
|
Fixed nan issue for training with CUDNN_HALF=1 by using Tensor Cores
|
2018-12-07 22:40:10 +03:00 |
AlexeyAB
|
21a4ec9390
|
Saving loss-chart for each 100 iterations automatically
|
2018-11-26 11:11:56 +03:00 |
AlexeyAB
|
9f7d7c58b5
|
Minor fixes. Use CUDA 10.0
|
2018-11-17 02:48:46 +03:00 |
AlexeyAB
|
14ed6fcb6e
|
Added -iou_thresh 0.05 flag for ./darknet detector map
|
2018-11-08 15:05:47 +03:00 |
AlexeyAB
|
25f65f6878
|
Added fast_binarize_weights_gpu()
|
2018-11-05 22:38:35 +03:00 |
Alexey
|
2c5e383c04
|
Update Readme.md
|
2018-11-01 03:32:31 +03:00 |
AlexeyAB
|
08e8e0c8c2
|
Minor fix
|
2018-10-28 23:58:08 +03:00 |