Leong
You can download the pre-trained model by runing `cd weights bash download_weights.sh` and run `python3 detect.py --image_folder data/samples/`
Could you put a screenshot with error
The input image size should be 32*n, for example 64, 128, 448 etc
You can try this image size: 960*544. Because of 544/32=17.
check you yolov3-custom.cfg file The error is 4*3*6*11*11 not equal 7260 ---Original--- From: "AadeIT"
@xiaoyuzhu666 if you have 3 class ,you can try this cfg! ```[net] # Testing #batch=1 #subdivisions=1 # Training batch=16 subdivisions=1 width=416 height=416 channels=3 momentum=0.9 decay=0.0005 angle=0 saturation = 1.5 exposure...
这个拆分数据应该跟具体的数据有关，需要保证分布均衡吧，大佬在知乎上https://zhuanlan.zhihu.com/p/129842491 也介绍了挺多的，但是好像没有看到具体的样本划分。 
作者您好，求数据集，非常感谢～ [email protected]
> > 作者您好，求数据集，非常感谢～ > > [[email protected]](mailto:[email protected]) > > 已发 非常感谢，已 star、fork