【无标题】

最新推荐文章于 2025-06-02 17:43:54 发布

weixin_37971351

最新推荐文章于 2025-06-02 17:43:54 发布

阅读量486

点赞数

文章标签： pytorch 深度学习 python

本文链接：https://blog.youkuaiyun.com/weixin_37971351/article/details/121404836

版权

Traceback (most recent call last): File “train_meta.py”, line 326,
in
train(epoch) File “train_meta.py”, line 221, in train
loss = region_loss(output, target) File “/opt/conda/lib/python3.6/site-packages/torch/nn/modules/module.py”,
line 477, in call
result = self.forward(input, **kwargs) File “/home/wujunxian/data/Fewshot_Detection-master/region_loss.py”, line
303, in forward
nH, nW, self.noobject_scale, self.object_scale, self.thresh, self.seen) File
“/home/wujunxian/data/Fewshot_Detection-master/region_loss.py”, line
60, in build_targets
if target[b][t5+1] == 0:
RuntimeError: dimension specified as 0 but tensor has no dimensions

这是因为张量target只有一维，而索引target[b][t*5+1]超出了自身维度。