跑yolox遇到的BUG

1.

问题：

        Error(s) in loading state_dict for YOLOX:
        size mismatch for head.cls_preds.0.weight: copying a param with shape torch.Size([6, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([8, 128, 1, 1]).
        size mismatch for head.cls_preds.0.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([8]).
        size mismatch for head.cls_preds.1.weight: copying a param with shape torch.Size([6, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([8, 128, 1, 1]).
        size mismatch for head.cls_preds.1.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([8]).
        size mismatch for head.cls_preds.2.weight: copying a param with shape torch.Size([6, 128, 1, 1]) from checkpoint, the shape in current model is torch.Size([8, 128, 1, 1]).
        size mismatch for head.cls_preds.2.bias: copying a param with shape torch.Size([6]) from checkpoint, the shape in current model is torch.Size([8]).

原因：

        头一天跑的6个类别的数据集得到的权重参数，第二天又跑的8个类别的数据集，测试六个类别数据时发生的错误。看报错说明预训练权重和本地模型不匹配（本地模型是8个类别，权重参数是六个）。

解决办法：

        1.把YOLOX/yolox/exp/yolox_base.py中的self.num_classes为6（测试数据的类别总数）

        2.命令行输入python setup.py install

2.

问题：

        AttributeError: 'NoneType' object has no attribute 'shape'

原因：

        数据集路径有中文

解决办法：

        把数据路径改过来，或者看看传的图片是否存在