cwq159 / PyTorch-Spiking-YOLOv3

A PyTorch implementation of Spiking-YOLOv3. Two branches are provided, based on two common PyTorch implementation of YOLOv3(ultralytics/yolov3 & eriklindernoren/PyTorch-YOLOv3), with support for Spiking-YOLOv3-Tiny at present.
GNU General Public License v3.0
207 stars 58 forks source link

源码中没有coco.data啊,怎么解决?自己下载吗 #50

Open dnkscu opened 1 year ago

rashmi-ar commented 1 year ago

I have used the following code from https://github.com/pjreddie/darknet/blob/master/cfg/coco.data

classes = 80 train = /PyTorch-Spiking-YOLOv3/data/coco/trainvalno5k.txt valid = /PyTorch-Spiking-YOLOv3/data/coco/5k.txt names = /PyTorch-Spiking-YOLOv3/data/coco.names backup = /PyTorch-Spiking-YOLOv3/backup eval = coco

Hope it helps.

Berumotto1 commented 1 year ago

换到eriklindernoren分支

123456ZF commented 1 year ago

我用自己的数据集跑ultralytics分支时,出现了RuntimeError: shape '[4, 3, 9, 16, 16]' is invalid for input of size 261120。换到eriklindernoren分支后,可以训练其他数据集吗?有什么办法可以解决吗? 谢谢

123456ZF commented 1 year ago

@Berumotto1