tensorflow.python.framework.errors.InvalidArgumentError: Input to reshape is a tensor with xxx value

今天被这个错误折磨得死去活来的,怎么修改都没有找到问题的症结所在:
这里写图片描述
在stack overflow上查看一下原因,发现是:

The mistake was very simple. I found that I should set 'VALID', not 'SAME' in conv2 so that I can make 12, 12, 32 shape before flatting operation. Thank you turtle to help me out.

这个是到哪里修改呢?还是不知。
另外一个参考:

he error tensorflow.python.framework.errors.InvalidArgumentError: Input to reshape is a tensor with 6400 values, but the requested shape requires a multiple of 3840 suggests that the input tensor of tf.reshape() in line 20 has a number of values that is not a multiple of 3840.

That's because tensor l1 isn't defined within function model (you might have used it earlier and it might have 6400 values). You probably want to set l1=layer1. Note that tensor l4 isn't defined in function model either.
  • 0
    点赞
  • 3
    收藏
    觉得还不错? 一键收藏
  • 10
    评论
评论 10
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值