darknet

darknet copied to clipboard

``` $ python -V 3.11.4 $ conda -V 23.5.2 $ darknet -V Darknet code version: 2023.09.27 CUDA-version: 10020 (11080), cuDNN: 7.6.5, CUDNN_HALF=1, GPU count: 1 CUDNN_HALF=1 OpenCV version: 4.2.0 $...

12343954

deprecate msbuild solutions

16

what's your opinion, @AlexeyAB ?

cenit

darknet stuck at beginning of execution

2

Hi, I'm using darknet for custom object detection and YOLOv4 in a Google Colab project. Until last week the code was working fine, but now I'm getting stuck at the...

joarezpj

Hi everyone so i had this issue with setting the right hyperparameter such as batch size, subdivision, max batch, etc for achieveng higher mAP and accuracy after training with YOLO...

joan2212

gsarathkumar92

Layer before convolutional layer must output image.: No such file or directory (When adding 2 SAM layers)

1

When trying to train the yolov2 with 2 changes in the cfg (addition of 2 SAM layers), the model doesnt start training. When the 2nd SAM layer is removed, the...

riririririi

Not found CUDA

1

 Hello, I want to build yolo in Windows 11 and this is what I get an issue. I already build opencv with CUDA successfully and already added a path...

SokPhanith

Detector can now receive a buffer as parameter for both cfg and weights

7

This was a feature requested in #6019 . As the constructors were the same, I had to make another one with another signature.

grandec

This branch has a code update to automatically stop train when the required map is achieved.

bilal-yousaf-confiz

https://github.com/AlexeyAB/darknet/issues/49 https://github.com/AlexeyAB/darknet/issues/85 I refer to the above steps to modify the code and recompile it, and after rostopic echo /darknet_ros/bounding_ boxes, the ID of each detected object will be displayed,...

ysys98