ValueError: Expected more than 1 value per channel when training, got input size torch.Size([1, 128]

sunflower821

 关注

阅读 73

2023-07-28


因为用到了BatchNorm，所以batch_size要大于1，drop_last 参数设置为True。

如果是两个GPU训练，batch_size改为4。

参考
ValueError: Expected more than 1 value per channel when training, got input size [1, 16, 1, 1]（解决方案）

Pytorch遇到报错Expected more than 1 value per channel when training, got input size torch.Size

相关推荐

ValueError: Error when checking : expected input_1 to have 4 dimensions, but got array with shape

佃成成成成 27 0 0

RuntimeError: Expected hidden[0] size (1, 64, 256), got (64, 256)

IT程序员 94 0 0

(36)RuntimeError: Given groups=4, weight of size [4, 1, 11, 11], expected input xxxxxxxxx

哈哈镜6567 32 0 0

Expected 4-dimensional input for 4-dimensional weight 64 3 7 7, but got 3-dimensional input of size

Xin_So 80 0 0

expected input to have 3 channels, but got 1 channels instead错误问题

浮游图灵 54 0 0

已解决ValueError: Expected 2D array, got 1D array instead

zidea 41 0 0

成功解决Python中出现的ValueError: not enough values to unpack (expected 2, got 1)的问题

alonwang 81 0 0

torch.zeros(log_probs.size()).scatter_(1, targets.unsqueeze(1).data.cpu(), 1)报错

王远洋 71 0 0

Keras Debug:ValueError: Error when checking target: expected dense_1to have shape (None, 84，) but go

大师的学徒 74 0 0

精彩评论（0）

0 0 举报