drop_block2d¶
- torchvision.ops.drop_block2d(input: Tensor, p: float, block_size: int, inplace: bool = False, eps: float = 1e-06, training: bool = True) Tensor [源代码]¶
实施来自 “DropBlock: A regularization method for convolutional networks” <https://arxiv.org/abs/1810.12890> 的 DropBlock2d。
- 参数:
- 返回值:
经过 dropblock 后随机置零的张量。
- 返回类型:
Tensor[N, C, H, W]