显存不够----ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[4096]

 

类似问题 https://github.com/CharlesShang/TFFRCNN/issues/68

参考：

 http://blog.csdn.net/qing101hua/article/details/77153222

方案：

 

take a look at the memory usage of your gpu with

nvidia-smi -l 3

　　

if still free memory that can be used
-> edit lib/fast_rcnn/train.py
~line396 : config.gpu_options.per_process_gpu_memory_fraction = 0.40
edit 0.40 to larger propotion (e.g. 0.9)