This is quick evaluation of everything, which not fit in any other category on ImageNet-2012.
The architecture is similar to CaffeNet, but has differences:
- Images are resized to small side = 128 for speed reasons.
- fc6 and fc7 layers have 2048 neurons instead of 4096.
- Networks are initialized with LSUV-init
ReLU non-linearity, fc6 and fc7 layer only
| Name | Accuracy | LogLoss | Comments |
|---|---|---|---|
| Default | 0.471 | 2.36 | 290K iters stopped |
| NoBias | 0.445 | 2.50 | Biases initialized with zeros, lr_rate = 0 |
P.S. Logs are merged from lots of "save-resume", because were trained at nights, so plot "Accuracy vs. seconds" will give weird results.