tensorflow报错

1.FutureWarning: Passing (type, 1) or '1type' as a synonym of type is deprecate

https://blog.csdn.net/bigdream123/article/details/99467316

2.图像语义分割 Deeplab v3+报错[`predictions` out of bound]解决办法

https://blog.csdn.net/weixin_41713230/article/details/81076292

3.AttributeError: type object 'h5py.h5r.Reference' has no attribute '__reduce_cython__'

https://blog.csdn.net/qq_41185868/article/details/80870336

h5py==2.8.0

4.AttributeError: module 'tensorflow.python.keras.backend' has no attribute 'get_graph'

网址查看tensorflow和keras对应的版本：https://docs.floydhub.com/guides/environments/

5.OP_REQUIRES failed at conv_ops.cc:386 : Resource exhausted: OOM when allocating tensor with shape..

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