Update model config and README
Browse files
README.md
CHANGED
|
@@ -26,6 +26,7 @@ NOTE: So far, these are the only known MNV4 weights. Official weights for Tensor
|
|
| 26 |
- **Dataset:** ImageNet-1k
|
| 27 |
- **Papers:**
|
| 28 |
- MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
|
|
|
|
| 29 |
- **Original:** https://github.com/tensorflow/models/tree/master/official/vision
|
| 30 |
|
| 31 |
## Model Usage
|
|
@@ -121,17 +122,38 @@ output = model.forward_head(output, pre_logits=True)
|
|
| 121 |
## Model Comparison
|
| 122 |
### By Top-1
|
| 123 |
|
| 124 |
-
|model
|
| 125 |
-
|
| 126 |
-
|mobilenetv4_conv_large.e500_r256_in1k
|
| 127 |
-
|mobilenetv4_conv_large.e500_r256_in1k
|
| 128 |
-
|mobilenetv4_hybrid_medium.e500_r224_in1k
|
| 129 |
-
|mobilenetv4_conv_medium.e500_r256_in1k
|
| 130 |
-
|mobilenetv4_hybrid_medium.e500_r224_in1k
|
| 131 |
-
|mobilenetv4_conv_blur_medium.e500_r224_in1k|80.142|19.858 |95.298|4.702 |9.72 |256 |
|
| 132 |
-
|mobilenetv4_conv_medium.e500_r256_in1k
|
| 133 |
-
|mobilenetv4_conv_medium.e500_r224_in1k
|
| 134 |
-
|mobilenetv4_conv_blur_medium.e500_r224_in1k|79.438|20.562 |94.932|5.068 |9.72 |224 |
|
| 135 |
-
|mobilenetv4_conv_medium.e500_r224_in1k
|
| 136 |
-
|mobilenetv4_conv_small.e1200_r224_in1k
|
| 137 |
-
|mobilenetv4_conv_small.e1200_r224_in1k
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 26 |
- **Dataset:** ImageNet-1k
|
| 27 |
- **Papers:**
|
| 28 |
- MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
|
| 29 |
+
- PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
|
| 30 |
- **Original:** https://github.com/tensorflow/models/tree/master/official/vision
|
| 31 |
|
| 32 |
## Model Usage
|
|
|
|
| 122 |
## Model Comparison
|
| 123 |
### By Top-1
|
| 124 |
|
| 125 |
+
| model |top1 |top1_err|top5 |top5_err|param_count|img_size|
|
| 126 |
+
|--------------------------------------------------------------------------------------------------|------|--------|------|--------|-----------|--------|
|
| 127 |
+
| [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) |82.674|17.326 |96.31 |3.69 |32.59 |320 |
|
| 128 |
+
| [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) |81.862|18.138 |95.69 |4.31 |32.59 |256 |
|
| 129 |
+
| [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) |81.276|18.724 |95.742|4.258 |11.07 |256 |
|
| 130 |
+
| [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) |80.858|19.142 |95.768|4.232 |9.72 |320 |
|
| 131 |
+
| [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) |80.442|19.558 |95.38 |4.62 |11.07 |224 |
|
| 132 |
+
| [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) |80.142|19.858 |95.298|4.702 |9.72 |256 |
|
| 133 |
+
| [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) |79.928|20.072 |95.184|4.816 |9.72 |256 |
|
| 134 |
+
| [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) |79.808|20.192 |95.186|4.814 |9.72 |256 |
|
| 135 |
+
| [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) |79.438|20.562 |94.932|5.068 |9.72 |224 |
|
| 136 |
+
| [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) |79.094|20.906 |94.77 |5.23 |9.72 |224 |
|
| 137 |
+
| [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) |74.292|25.708 |92.116|7.884 |3.77 |256 |
|
| 138 |
+
| [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) |73.454|26.546 |91.34 |8.66 |3.77 |224 |
|
| 139 |
+
|
| 140 |
+
## Citation
|
| 141 |
+
```bibtex
|
| 142 |
+
@article{qin2024mobilenetv4,
|
| 143 |
+
title={MobileNetV4-Universal Models for the Mobile Ecosystem},
|
| 144 |
+
author={Qin, Danfeng and Leichner, Chas and Delakis, Manolis and Fornoni, Marco and Luo, Shixin and Yang, Fan and Wang, Weijun and Banbury, Colby and Ye, Chengxi and Akin, Berkin and others},
|
| 145 |
+
journal={arXiv preprint arXiv:2404.10518},
|
| 146 |
+
year={2024}
|
| 147 |
+
}
|
| 148 |
+
```
|
| 149 |
+
```bibtex
|
| 150 |
+
@misc{rw2019timm,
|
| 151 |
+
author = {Ross Wightman},
|
| 152 |
+
title = {PyTorch Image Models},
|
| 153 |
+
year = {2019},
|
| 154 |
+
publisher = {GitHub},
|
| 155 |
+
journal = {GitHub repository},
|
| 156 |
+
doi = {10.5281/zenodo.4414861},
|
| 157 |
+
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
|
| 158 |
+
}
|
| 159 |
+
```
|