Larry

是的 把*args. batchsize删除 loss = loss_sum / len(test_loader)

用了300W,300VW,WFLW这三个数据集共 Total number of examples: 326427 Test number of examples: 3054 模型使用efficientnet-b0 训练时，loss可以到20左右。 Epoch:[16 ][1200/2551] Loss: 18.896 lr 0.0001 average_time:0.228s remain_time:29.635h

报错的原因：是opencv不能加载yolop模型中的Focus模块， 修改方法：按照blog中的方法修改就行：https://blog.csdn.net/nihate/article/details/112731327

VPS-Net is follow this project to train : https://github.com/eriklindernoren/PyTorch-YOLOv3 you should make custom parking slot dataset to train, annotations format : [classid x_center y_center bbox_w bbox_h vacant] class: right-angled_head :...