micromind checkpoints for CIFAR-10
This repository contains checkpoints for the CIFAR-10 dataset for the following networks:
| Model | Top 1 Accuracy | Top 5 Accuracy |
|---|---|---|
PhiNet(alpha=3, beta=0.75, t_zero=6, num_layers=7, resolution=160) |
93.61% | 99.77% |
PhiNet(alpha=0.75, beta=1, t_zero=6, num_layers=5, resolution=160) |
86.8% | 99.5% |
PhiNet(alpha=0.35, beta=1, t_zero=6, num_layers=7, resolution=160) |
88.08% | 99.48% |
PhiNet(alpha=0.25, beta=1, t_zero=6, num_layers=7, resolution=160) |
84.97% | 99.3% |
PhiNet(alpha=0.25, beta=1, t_zero=5, num_layers=7, resolution=160) |
83.01% | 99.2% |
To download and use this repo:
from micromind import PhiNet
model = PhiNet.from_pretrained("CIFAR-10", alpha=3.0, beta=0.75, t_zero=6, num_layers=7, num_classes=10, resolution=160)