tensorflow:OOM when allocating tensor with shape[.....] and type

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。

感谢:
https://blog.csdn.net/nima1994/article/details/79651564


原文出处:/show_1EF5JIXKBPs9.html