Skip to content

DDRNet在预测推理的时候遇到了维度不匹配的问题 #33

@Roylo-bot

Description

@Roylo-bot

在用DDRNet训练自己的数据后(两类,背景和前景),对图片进行预测时,偶尔会出现
File "/0work/LMK/Segment_task/Segmentation-Pytorch/model/DDRNet.py", line 330, in forward
x_ = x_ + F.interpolate(
RuntimeError: The size of tensor a (63) must match the size of tensor b (62) at non-singleton dimension 3
这个维度的bug。
请问该如何解决?

Metadata

Metadata

Assignees

No one assigned

    Labels

    No labels
    No labels

    Projects

    No projects

    Milestone

    No milestone

    Relationships

    None yet

    Development

    No branches or pull requests

    Issue actions