Tensorflow调参报错：Resource exhausted OOM when allocating tensor with shape

错误信息

Resource ex hausted: OOM when allocating tensor with shape[200,256,28,28] and****

这是一种调参时常遇到的问题，由于电脑显存不够而导致，我的电脑显存是8g，在调整参数 IMAGES_PER_GPU = 2时，会导致这样的错误，将其改回1错误消失(降低了batch size的大小)。
解决办法

1. 减少Batch 的大小
2. 分析错误的位置，在哪一层出现显卡不够，比如在全连接层出现的，则降低全连接层的维度，把2048改成1024啥的
3. 增加pool 层，降低整个网络的维度。
4. 修改输入图片的大小
5. 有钱任性，换台电脑

# python train.py --logdir myLog --batch_size 256 --dropout_rate 0.5


OP_REQUIRES failed at conv_ops.cc:636 : Resource exhausted: OOM when allocating tensor with shape[32,32,417,417] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
Traceback (most recent call last):
 
    callbacks=[logging, checkpoint])
  File "D:\Anaconda3\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
    return func(*args, **kwargs)
  File "D:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1415, in fit_generator
    initial_epoch=initial_epoch)
  File "D:\Anaconda3\lib\site-packages\keras\engine\training_generator.py", line 213, in fit_generator
    class_weight=class_weight)
  File "D:\Anaconda3\lib\site-packages\keras\engine\training.py", line 1215, in train_on_batch
    outputs = self.train_function(ins)
  File "D:\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2666, in __call__
    return self._call(inputs)
  File "D:\Anaconda3\lib\site-packages\keras\backend\tensorflow_backend.py", line 2636, in _call
    fetched = self._callable_fn(*array_vals)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\client\session.py", line 1382, in __call__
    run_metadata_ptr)
  File "D:\Anaconda3\lib\site-packages\tensorflow\python\framework\errors_impl.py", line 519, in __exit__
    c_api.TF_GetCode(self.status.status))
tensorflow.python.framework.errors_impl.ResourceExhaustedError: OOM when allocating tensor with shape[32,32,417,417]