网络环境:ubuntu系统下,python3.4以上,tensorflow1.12.0以上.需要自己训练
* Random split 50k training set into 45k/5k train/eval split.
* Pad to 36x36 and random crop. Horizontal flip. Per-image whitening.
* Momentum optimizer 0.9.
* Learning rate schedule: 0.1 (40k), 0.01 (60k), 0.001 (>60k).
* L2 weight decay: 0.002.
* Batch size: 128. (28-10 wide and 1001 layer bottleneck use 64)
1