tensorflow-gpu验证准确率是报错如上：
解决办法：
1. 加入os.environ['CUDA_VISIBLE_DEVICES']='2'
强制使用CPU验证-----慢
2.'batch_size', 降低为32，即可使用GPU跑------快
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
tensorflow报错 tensorflow Resource exhausted: OOM when allocating tensor with shape
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[1,1424,2128,64]
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
ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape
Tensorflow:If you want to see a list of allocated tensors when OOM happens, add report_tensor_alloca
ValueError: Error when checking input: expected conv2d_1_input to have 4 dimensions, but got array with shape (60000, 28, 28)
kubernetes continually evict pod when node's inode exhausted
pytorch--(MisMatch in shape & invalid index of a 0-dim tensor)
关于类型为numpy，TensorFlow.tensor，torch.tensor的shape变化以及相互转化
Android resource compilation failed