备注

您正在阅读 MMClassification 0.x 版本的文档。MMClassification 0.x 会在 2022 年末被切换为次要分支。建议您升级到 MMClassification 1.0 版本，体验更多新特性和新功能。请查阅 MMClassification 1.0 的安装教程、迁移教程以及更新日志。

mmcls.models.ClsHead

class mmcls.models.ClsHead(loss={'loss_weight': 1.0, 'type': 'CrossEntropyLoss'}, topk=(1,), cal_acc=False, init_cfg=None)

classification head.

参数

• loss (dict) – Config of classification loss.

• topk (int | tuple) – Top-k accuracy.

• cal_acc (bool) – Whether to calculate accuracy during training. If you use Mixup/CutMix or something like that during training, it is not reasonable to calculate accuracy. Defaults to False.