InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape = [12288] rhs shape = [49152]
解决办法：清空下checkpoint缓存就可以
免责声明！
本站转载的文章为个人学习借鉴使用，本站对版权不负任何法律责任。如果侵犯了您的隐私权益，请联系本站邮箱yoyou2525@163.com删除。
猜您在找
InvalidArgumentError (see above for traceback): Assign requires shapes of both tensors to match. lhs shape= [2048,38] rhs shape= [2048,2]
卷积层后连接LSTM层的报错（InvalidArgumentError (see above for traceback): Incompatible shapes: [128] vs. [384]）
显存不够----ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[4096]
tensorflow ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[256,256,15,15] and type float on 报错（显存不够报错）
错误：基于tensorflow识别mnist数据集出现ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[10000,32,28,28] and type float on
InvalidArgumentError (see above for traceback): You must feed a value for placeholder tensor 'Y' with dtype float
InvalidArgumentError: ConcatOp : Dimensions of inputs should match: shape[0] = [1,136,240,64] vs. shape[1] = [1,135,240,64]
【error】OutOfRangeError (see above for traceback): RandomShuffleQueue
LHS和RHS理解
Lhs和Rhs的含义