运行TensorFlow（GPU）报错如下：

OOM when allocating tensor with shape[225,256,256,36] and type float on /job:localhost/replica:0/tas

原因是GPU OOM内存不够，因此可尝试改成批处理。即将训练的数据块调小。

参考链接：
​​​https://stackoverflow.com/questions/39076388/tensorflow-deep-mnist-resource-exhausted-oom-when-allocating-tensor-with-shape​​

​​https://github.com/tensorflow/tensorflow/issues/609​​