AlexeyAB / darknet

YOLOv4 / Scaled-YOLOv4 / YOLO - Neural Networks for Object Detection (Windows and Linux version of Darknet )
http://pjreddie.com/darknet/
Other
21.73k stars 7.96k forks source link

CSPDarknet-53 #5309

Closed furkanaydinoz closed 4 years ago

furkanaydinoz commented 4 years ago

Hello, I want to train my own object detection weights with Yolov4. However, I could not find the CSPDarknet-53 convolutional weights mentioned in the article(https://arxiv.org/pdf/2004.10934.pdf page:12). Should I use the darknet53.conv.74 weights in Yolov3? Or is it still not released for yolov4?

Eve66666 commented 4 years ago

In readme.md, use CTRL +F to search for "yolov4.conv.137"

DataXujing commented 4 years ago

U should use "yolov4.conv.137

AlexeyAB commented 4 years ago

https://github.com/AlexeyAB/darknet#how-to-train-to-detect-your-custom-objects

https://drive.google.com/open?id=1JKF-bdIklxOOVy-2Cr5qdvjgGpmGfcbp

Download pre-trained weights for the convolutional layers and put to the directory build\darknet\x64

for yolov4.cfg, yolov4-custom.cfg (162 MB): yolov4.conv.137 for csresnext50-panet-spp.cfg (133 MB): csresnext50-panet-spp.conv.112 for yolov3.cfg, yolov3-spp.cfg (154 MB): darknet53.conv.74 for yolov3-tiny-prn.cfg , yolov3-tiny.cfg (6 MB): yolov3-tiny.conv.11 for enet-coco.cfg (EfficientNetB0-Yolov3) (14 MB): enetb0-coco.conv.132

furkanaydinoz commented 4 years ago

Thank you for your feedback