We provide linear evaluation logs in case you need them. Note that since the last stage (epoch>80) of training will not necessarily affect the final performance, so some of our runnings may not reach to the complete 100 epochs.
| Models | #Epoch | FLOPs (x108) | OPs (x108) | Top-1 (%) | Logs |
|---|---|---|---|---|---|
| MoCo V2 baseline | 200 | 0.12 | 0.87 | 46.9 | Download |
| Our enhanced MoCo V2 | 200 | 0.12 | 0.87 | 52.5 | Download |
| Our MoCo V2 + Distillation Loss | 200 | 0.12 | 0.87 | 56.0 | Download |
| Our Distillation Loss Only | 200 | 0.12 | 0.87 | 61.5 | Download |
Zhiqiang Shen, CMU (zhiqiangshen0214 at gmail.com)