从AlexNet模型（正常跑通） 切换到ResNet50 模型时报错
Created by: liyutg
因为使用了自定义数据集，所以修改了读取数据的代码
系统信息
paddle 版本 1.3.2 GPU 型号 Tesla K40m 11441MiB Please NOTE: device: 1, CUDA Capability: 35, Driver API Version: 10.1, Runtime API Version: 9.0 device: 0, cuDNN Version: 7.0.
项目配置信息
------------- Configuration Arguments -------------
--model=ResNet50 \
--batch_size=256 \
--total_images=31718 \
--class_dim=61 \
--image_shape=3,224,224 \
--model_save_dir=output/ \
--with_mem_opt=True \
--lr_strategy=piecewise_decay \
--num_epochs=120 \
--lr=0.1 \
--l2_decay=1e-4 \
----------------------------------------------------报错信息
W0413 13:19:44.940369 13978 device_context.cc:263] Please NOTE: device: 0, CUDA Capability: 35, Driver API Version: 10.1, Runtime API Version: 9.0 W0413 13:19:44.940452 13978 device_context.cc:271] device: 0, cuDNN Version: 7.0. W0413 13:19:50.571400 16109 system_allocator.cc:122] Cannot malloc 9999.6 MB GPU memory. Please shrink FLAGS_fraction_of_gpu_memory_to_use environment variable to a lower value. Current value is 0.92 W0413 13:19:50.571779 16109 legacy_allocator.cc:191] Cannot allocate 196.000000MB in GPU 0, available 1.214539GB W0413 13:19:50.571794 16109 legacy_allocator.cc:194] total 11996954624 W0413 13:19:50.571805 16109 legacy_allocator.cc:195] GpuMinChunkSize 256.000000B W0413 13:19:50.571813 16109 legacy_allocator.cc:198] GpuMaxChunkSize 9.765232GB W0413 13:19:50.571827 16109 legacy_allocator.cc:201] GPU memory used: 9.633711GB