1113 Commits (5e850c24897a5eb65941703059a85ead2ea5ff8c)
 

Author SHA1 Message Date
AlexeyAB 1c05ebf522 Minor fix 7 years ago
AlexeyAB 3010e1f755 Minor fix 7 years ago
AlexeyAB 6c54f5ffb2 Show inconsistent information if it is present in .cfg and .names files 7 years ago
AlexeyAB 1e512b2308 Letter box is disabled in the darknet.py by defualt 7 years ago
Alexey 3eb58c51b9
Merge pull request #981 from IlyaOvodov/Fix_get_color_depth 7 years ago
IlyaOvodov f0abcfa02b Merge branch 'master' of https://github.com/AlexeyAB/darknet into Fix_get_color_depth 7 years ago
IlyaOvodov 5291935b70 Net color depth is exposed from Detector class 7 years ago
Alexey c8ad33ceba
Update Readme.md 7 years ago
AlexeyAB efaf684cb2 By default letter_box is disabled 7 years ago
Alexey a7ddb20506
Update Readme.md 7 years ago
Alexey d502dea9a4
Update Readme.md 7 years ago
AlexeyAB 132251d723 You can do: fuse_conv_batchnorm(network net) from DLL/SO-library 7 years ago
AlexeyAB 7359843a4b Store wrong annotations to the file: bad_labels.list 7 years ago
AlexeyAB 5d8e3526ed Fix for unreliable IP-cameras 7 years ago
AlexeyAB 483fdfa951 Fix for multi-GPU and DGX 7 years ago
AlexeyAB 4cf4a89f05 Minor fix 7 years ago
AlexeyAB ba70801e98 Minor fixes 7 years ago
Alexey 73a2c52df0
Merge pull request #946 from jinyu121/master 7 years ago
Alexey 0713fd9784
Merge pull request #936 from IlyaOvodov/Fix_GrayScale_PR 7 years ago
Alexey 1a35f49ab3
Merge pull request #950 from IlyaOvodov/Fix_size_PR 7 years ago
IlyaOvodov 51293290fa Fix error in allocation size 7 years ago
Yu Hao 6c675a0927
Fix openCV 3.4.1 highgui 7 years ago
IlyaOvodov 01bec65708 "channel" parameter of [net] is used in detector when preparing images for net. 7 years ago
AlexeyAB ec766fc3f1 Ignore empty extra lines in train.txt 7 years ago
AlexeyAB 6fd90762c5 Fix: Ignore incorrect dataset labels instead of causing seg-fault error. 7 years ago
AlexeyAB 1b7a1a0f33 Fixed top-coordinate output when -ext_output is used for video 7 years ago
Alexey 1d532aa97f
Merge pull request #913 from jing-vision/master 7 years ago
AlexeyAB 160eddddc4 Minor fix 7 years ago
vinjn b36512ea2e classifier.c - add the awesome training chart and make sure "top" is not bigger than "classes" in datacfg file. 7 years ago
Alexey 65e430588d
Merge pull request #909 from jing-vision/master 7 years ago
vinjn 6b6f0f0ca3 classifier.c - set batch=1 in "predict", "demo" and "try" mode. 7 years ago
Alexey 6390a5a2ab
Update Readme.md 7 years ago
AlexeyAB f52040f0bf Classifier uses C++ OpenCV cv::VideoCapture that hasn't bugs. 7 years ago
AlexeyAB eef9f8e5bb Minor fixes 7 years ago
AlexeyAB ec68838342 Fixed memory leaks for Yolo: train, test 7 years ago
AlexeyAB 768b190b10 Minor fix: warning-message if in labels class_id >= classes in cfg-file 7 years ago
AlexeyAB 60cd28bdfb Fixed seg-fault that occurred if <class_id> in labels more than classes= in the cfg-file. 7 years ago
AlexeyAB a2666d5b3c Fixed replace_image_to_label(): replaces directories only for Pascal VOC and COCO, replaces only extensions for other. 7 years ago
AlexeyAB 032acd408a Experimental reinforcement learning. 7 years ago
AlexeyAB f9ecf6fd3f For Release build - equality check: output of [convolutional] == input of [yolo]. 7 years ago
AlexeyAB d01a686246 Fixed compile 7 years ago
AlexeyAB a720bf74e2 Added flag -ext_output for detector demo. Fixed proportional resize of network for random=1 7 years ago
AlexeyAB 46028c6621 Fixed demo for video files: is used do_nms_sort() instead of do_nms_obj(). 7 years ago
AlexeyAB b88b7b645b Save jpg-images for detector demo if used flag: -prefix <filename> 7 years ago
AlexeyAB 4403e71b33 Supported files for training: jpg, jpeg, bmp, png, ppm - and UPPER CASE extensions 7 years ago
Alexey 175c68b9b3
Merge pull request #856 from vinjn/patch-1 7 years ago
Vinjn Zhang c6ca54b411
darknet.py - apply the same changes to build/darknet/x64/ 7 years ago
Vinjn Zhang dbcdac88a5
darknet.py - loading dll files by absolute name 7 years ago
Vinjn Zhang efdeb01a3a
darknet.py - remove unnecessary check of CUDA_HOME 7 years ago
AlexeyAB 7b7c669f49 Added flag -save_labels to save detections as training labels txt-files (pseudo labeling concept) 7 years ago