1700X + GTX950 跑 CNN卷積神經網路面部表情識別例項程式碼
網站評論功能維護中,對文章的評論記錄於此:
文章:
http://blog.csdn.net/sqh4587/article/details/74507010
tensorflow機器學習之利用CNN卷積神經網路進行面部表情識別的例項程式碼
評論如下:
跑了一把:硬體 1700X+16GRAM+GTX950(2G),都在GPU上跑。CPU利用率很低,約10%。RAM利用率56%左右。共耗時約37分鐘,成功率26.5%
GPU 典型佔用率:
Wed Nov 8 22:36:02 2017
+-----------------------------------------------------------------------------+
| NVIDIA-SMI 384.90 Driver Version: 384.90 |
|-------------------------------+----------------------+----------------------+
| GPU Name Persistence-M| Bus-Id Disp.A | Volatile Uncorr. ECC |
| Fan Temp Perf Pwr:Usage/Cap| Memory-Usage | GPU-Util Compute M. |
|===============================+======================+======================|
| 0 GeForce GTX 950 Off | 00000000:26:00.0 On | N/A |
| 38% 65C P0 71W / 120W | 1935MiB / 1995MiB | 97% Default |
+-----------------------------------------------------------------------------+