darknet

darknet copied to clipboard

Keeping this in mind [https://github.com/AlexeyAB/darknet/pull/7282](https://github.com/AlexeyAB/darknet/pull/7282) proposing a simple solution. show_img is Mat pointer. Just cropping desired portion out of Mat. Useful for cropping detections in video, when src/image_opencv.cpp is used...

rg321

Basuki74

Multiprocessing in darknet_video.py (NOT final!)

3

# Disclaimer - I'm **not aiming to merge this *PR*** anywhere (that's the reason why I left there debug and other stuff), it's just a point that I've reached (and...

CristiFati

In this branch, I solved the #8615 issue and did some refactors. Firstly, I created a new variable which is a flag for `save_label_actual` and It helps people to get...

bariscankurtkaya

Currently `get_network_output_gpu_layer` symbol is undefined in `libdarknet.so`. Therefore intermediate layer GPU outputs cannot be extracted through Python bindings. This is caused by inconsistent function declaration and definition in `network_kernels.cu`. Specifically:...

hangst

Fix for #8655

vtyw

add file existence check in yolo_console_dll.cpp

1

I'm trying to use C++ API to integrate darknet with my C++ project on windows. I followed the tutorial on [this topic](https://github.com/AlexeyAB/darknet#how-to-use-yolo-as-dll-and-so-libraries) in README.md. During the test toward my input...

RRRChangeche

added simple IO error processing in detector.c

1

ivan2201

if one anchor is asigned to multi label, then should choose the max iou truth label

5

during training stage, if one anchor is asigned to multi label, then should choose the max iou truth label. the default action is choose the last truth label, but in...

ZouJiu1

I want to use yolo v4 to train and output the area and coordinates on the picture.

db777888999