默认情况下，Tensorflow占用所有可用的GPU内存.但是，有一种方法可以改变这一点.在我的模型中，我这样做:

By default, Tensorflow occupies all GPU memory available. However, there is a way to change this. In my model, I do this:

config = tf.ConfigProto()
config.gpu_options.allow_growth = True

然后，您可以在开始会话时使用此配置:

Then you can use this config when you start your session:

with tf.Session(config=config) as sess:

现在，模型将仅使用所需的内存，然后您可以尝试使用不同的批处理大小，并查看何时内存用完.

Now, the model will only use as much memory as it needs, and then you can try with different batch sizes and see when it runs out of memory.