END-TO-END OPTIMIZED IMAGE COMPRESSION代码报错记录

这里记录论文END-TO-END OPTIMIZED IMAGE COMPRESSION相关代码报错的记录（我这里运行的tensorflow1.15版本对应的代码）
github：https://github.com/tensorflow/compression

1、cuda设备问题

tensorflow.python.framework.errors_impl.InvalidArgumentError: Invalid device ordinal value (1). Valid range is [0, 0].
	while setting up XLA_GPU_JIT device number 1

解决方法
最后在命令前面加上CUDA_VISIBLE_DEVICE:

CUDA_VISIBLE_DEVICES=0 python bls2017.py --verbose train --train_glob="/home/ll/END-TO-END-OPTIMIZED-IMAGE-COMPRESSION/image/*JPEG"

或者在代码中加入

import os
os.environ['CUDA_VISIBLE_DEVICES']='0'

2、

tensorflow.python.framework.errors_impl.InvalidArgumentError: {{function_node __inference_Dataset_map_<lambda>_122}} assertion failed: [Need value.shape >= size, got ] [230 170 3] [256 256 3]
	 [[{{node random_crop/Assert/Assert}}]]
	 [[IteratorGetNext]]