darknet

Commit Graph

Author	SHA1	Message	Date
AlexeyAB	89c11f83ed	Fixed darknet.py - uses batch=1 by default	7 years ago
AlexeyAB	573d7e8081	Added def array_to_image(arr): to the darknet.py Usage: import scipy.misc sci_image = scipy.misc.imread(image) im, arr = array_to_image(sci_image)	7 years ago
AlexeyAB	8b5344ee2d	Added BFLOPs output for network configurations	7 years ago
AlexeyAB	3ebcc647b6	Fixed network resizing (random=1) for non-square networks	7 years ago
Alexey	cda8171feb	Merge pull request #765 from HotChick91/AlexeyAB-code Exit with nonzero status on error	7 years ago
AlexeyAB	812d143ebd	Merge branch 'master' of github.com:AlexeyAB/darknet	7 years ago
AlexeyAB	e96401774b	Fixed compile error	7 years ago
Alexey	2c2ba0f8fa	Update Readme.md	7 years ago
AlexeyAB	fb56f6d569	Fixed README.md	7 years ago
Alexey	0948df52b8	Merge pull request #741 from IlyaOvodov/Fix_detector_output Output improvements for detector results:	7 years ago
IlyaOvodov	1b5afb4583	Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount Upd: * struct detection changes reverted to keep it unchanged * cmd line key "-ext_output" is added to manage extended output (rect coords in detector test mode) # Conflicts: # src/detector.c	7 years ago
AlexeyAB	0045074f56	Get pre-trained weights for Yolo v3 tiny	7 years ago
Bartek Gąsiorzewski	ae4ec1a06d	Exit with nonzero status on error	7 years ago
Alexey	6b8fd6f33f	Update Readme.md	7 years ago
Alexey	bde2a30603	Merge pull request #760 from PuneetKohli/fix-log-parser-no-display Change matplotlib backend to 'agg' when 'show_plot' is false.	7 years ago
Puneet Kohli	cdd1cb0e8c	Change matplotlib backend to 'agg' when 'show_plot' is false. This allows the script to be run from command line without any errors (for ex, on a remote machine)	7 years ago
AlexeyAB	c9b8bdee18	Minor fix - what pip-packages are required for Python scripts	7 years ago
Alexey	30e08573d1	Merge pull request #759 from Adesun/log_parser darknet training log parser	7 years ago
AlexeyAB	efcbdb5425	Added yolov3-tiny.cfg	7 years ago
Ade	a1c5bae6fb	Update readme.md	7 years ago
Adesun	d3d4c0e699	parsing training log and plot save loss data to csv	7 years ago
Alexey	85388d6708	Merge pull request #754 from tigerhawkvok/python3-detection-runner Python3 detection runner	7 years ago
Philip Kahn	51fbf01277	Address GPU message in root dir	7 years ago
Philip Kahn	75295718e1	Address GPU message in build dir	7 years ago
Philip Kahn	1aadf29a51	fix detection paths	7 years ago
Philip Kahn	3a2a8653a6	Fix detection paths	7 years ago
Philip Kahn	29f3c37314	Remove debugging line	7 years ago
Philip Kahn	9c400dc5b8	Remove debugging line	7 years ago
Philip Kahn	3459c47bfa	Also replace root version to Python3	7 years ago
Philip Kahn	eaecb49a5f	Change darknet.py to Python 3 compatibility	7 years ago
AlexeyAB	89354d0a0c	Fixed memory leaks. And fixes for Web-camera and IP-camera.	7 years ago
AlexeyAB	4232ace376	Fix webcam memory leak	7 years ago
iovodov	028696bf15	Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount	7 years ago
Alexey	535353cdaa	Merge pull request #737 from IlyaOvodov/Fix_thin FIX #736: Detector does not draw rects for images with small resolutions	7 years ago
iovodov	92b25a7200	FIX #736 : Detector does not draw rects for images with small resolutions	7 years ago
AlexeyAB	a0e288f0dc	Increased speed of darknet.py. Fixed functions related to resize_image().	7 years ago
Alexey	5e3dcb6f34	Update Readme.md	7 years ago
AlexeyAB	15139eb6ab	Fixed TP/FP/FN, IoU calculation for specified threshold	7 years ago
AlexeyAB	3df335bb50	Fixed SSE4.1 dependencies when AVX=1 on Linux	7 years ago
Alexey	a2f3644e87	Merge pull request #675 from IlyaOvodov/Flip_Fix Fix of issue #674: parameter "flip" is added to [net] parameters for cla…	7 years ago
iovodov	9207607a59	Fix issue #674 : parameter "flip" is added to [net] parameters for classifier and detector flip=0 switches flip augmentation off. Default is flip=1 which is consistent with a previous behaviour.	7 years ago
AlexeyAB	e18a303d1c	Fixed utils.c for short lines.	7 years ago
AlexeyAB	5d616450a4	Usage of calc_anchors	7 years ago
AlexeyAB	5767893292	Fixed typo for calc_anchors	7 years ago
AlexeyAB	c2c8595b08	Fixed detection and validate(recall, map) for .png and .bmp images.	7 years ago
AlexeyAB	eccfccdaf7	Focal loss fixed	7 years ago
AlexeyAB	6056b835eb	Fixed Focal-loss	7 years ago
AlexeyAB	57fce97fd5	yolo_console_dll.cpp uses Yolo v3 by default	7 years ago
AlexeyAB	8fcf3f04ee	sure ODR	7 years ago
AlexeyAB	9f2dbfa7df	Added flag AVX to the Makefile	7 years ago

1 2 3 4 5 ...

748 Commits (89c11f83ed49c58c3031200d8ed053b4f671db09) All Branches Search

748 Commits (89c11f83ed49c58c3031200d8ed053b4f671db09)

All Branches