| | --- |
| | license: mit |
| | datasets: |
| | - cifar10 |
| | language: |
| | - en |
| | pipeline_tag: image-classification |
| | --- |
| | # 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) |
| | ``` |
| |
|
| | ## Authors |
| |
|
| | - [@fpaissan](https://www.github.com/fpaissan) |
| | - [@matteobeltrami](https://www.github.com/matteobeltrami) |
| |
|
| | --- |
| | license: mit |
| | --- |
