Update model config and README
Browse files
README.md
CHANGED
@@ -9,8 +9,11 @@ datasets:
|
|
9 |
---
|
10 |
# Model card for convnext_zepto_rms.ra4_e3600_r224_in1k
|
11 |
|
12 |
-
A
|
13 |
|
|
|
|
|
|
|
14 |
|
15 |
## Model Details
|
16 |
- **Model Type:** Image classification / feature backbone
|
@@ -19,11 +22,10 @@ A ConvNeXt image classification model. Trained in `timm` on ImageNet-1k by Ross
|
|
19 |
- GMACs: 0.3
|
20 |
- Activations (M): 2.7
|
21 |
- Image size: 224 x 224
|
22 |
-
- **Papers:**
|
23 |
-
- @: m
|
24 |
-
- A ConvNet for the 2020s: https://arxiv.org/abs/2201.03545
|
25 |
-
- **Original:** https://github.com/huggingface/pytorch-image-models
|
26 |
- **Dataset:** ImageNet-1k
|
|
|
|
|
|
|
27 |
|
28 |
## Model Usage
|
29 |
### Image Classification
|
@@ -115,78 +117,92 @@ output = model.forward_head(output, pre_logits=True)
|
|
115 |
```
|
116 |
|
117 |
## Model Comparison
|
118 |
-
|
119 |
-
|
120 |
-
|
121 |
-
|
122 |
-
|
|
123 |
-
|
124 |
-
| [
|
125 |
-
| [
|
126 |
-
| [
|
127 |
-
| [
|
128 |
-
| [
|
129 |
-
| [
|
130 |
-
| [
|
131 |
-
| [
|
132 |
-
| [
|
133 |
-
| [
|
134 |
-
| [
|
135 |
-
| [
|
136 |
-
| [
|
137 |
-
| [
|
138 |
-
| [
|
139 |
-
| [
|
140 |
-
| [
|
141 |
-
| [
|
142 |
-
| [
|
143 |
-
| [
|
144 |
-
| [
|
145 |
-
| [
|
146 |
-
| [
|
147 |
-
| [
|
148 |
-
| [
|
149 |
-
| [
|
150 |
-
| [
|
151 |
-
| [
|
152 |
-
| [
|
153 |
-
| [
|
154 |
-
| [
|
155 |
-
| [
|
156 |
-
| [
|
157 |
-
| [
|
158 |
-
| [
|
159 |
-
| [
|
160 |
-
| [
|
161 |
-
| [
|
162 |
-
| [
|
163 |
-
| [
|
164 |
-
| [
|
165 |
-
| [
|
166 |
-
| [
|
167 |
-
| [
|
168 |
-
| [
|
169 |
-
| [
|
170 |
-
| [
|
171 |
-
| [
|
172 |
-
| [
|
173 |
-
| [
|
174 |
-
| [
|
175 |
-
| [
|
176 |
-
| [
|
177 |
-
| [
|
178 |
-
| [
|
179 |
-
| [
|
|
|
|
|
|
|
|
|
|
|
|
|
180 |
|
181 |
## Citation
|
182 |
```bibtex
|
183 |
-
|
|
|
|
|
|
|
|
|
|
|
184 |
```
|
185 |
```bibtex
|
186 |
-
@
|
187 |
-
author
|
188 |
-
title
|
189 |
-
|
190 |
-
|
|
|
|
|
|
|
191 |
}
|
192 |
```
|
|
|
9 |
---
|
10 |
# Model card for convnext_zepto_rms.ra4_e3600_r224_in1k
|
11 |
|
12 |
+
A MobileNet-V4 image classification model. Trained on ImageNet-1k by Ross Wightman.
|
13 |
|
14 |
+
Trained with `timm` scripts using hyper-parameters inspired by the MobileNet-V4 small, mixed with go-to hparams from `timm` and "ResNet Strikes Back".
|
15 |
+
|
16 |
+
A collection of hparams (timm .yaml config files) for this training series can be found here: https://gist.github.com/rwightman/f6705cb65c03daeebca8aa129b1b94ad
|
17 |
|
18 |
## Model Details
|
19 |
- **Model Type:** Image classification / feature backbone
|
|
|
22 |
- GMACs: 0.3
|
23 |
- Activations (M): 2.7
|
24 |
- Image size: 224 x 224
|
|
|
|
|
|
|
|
|
25 |
- **Dataset:** ImageNet-1k
|
26 |
+
- **Papers:**
|
27 |
+
- MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
|
28 |
+
- PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
|
29 |
|
30 |
## Model Usage
|
31 |
### Image Classification
|
|
|
117 |
```
|
118 |
|
119 |
## Model Comparison
|
120 |
+
### By Top-1
|
121 |
+
|
122 |
+
| model | top1 | top5 | param_count | img_size |
|
123 |
+
|--------------------------------------------------------------------------------------------------------------------------|--------|--------|-------------|----------|
|
124 |
+
| [mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k) | 84.99 | 97.294 | 32.59 | 544 |
|
125 |
+
| [mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k) | 84.772 | 97.344 | 32.59 | 480 |
|
126 |
+
| [mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k) | 84.64 | 97.114 | 32.59 | 448 |
|
127 |
+
| [mobilenetv4_hybrid_large.ix_e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k) | 84.356 | 96.892 | 37.76 | 448 |
|
128 |
+
| [mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k) | 84.314 | 97.102 | 32.59 | 384 |
|
129 |
+
| [mobilenetv4_hybrid_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.e600_r384_in1k) | 84.266 | 96.936 | 37.76 | 448 |
|
130 |
+
| [mobilenetv4_hybrid_large.ix_e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k) | 83.990 | 96.702 | 37.76 | 384 |
|
131 |
+
| [mobilenetv4_conv_aa_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e600_r384_in1k) | 83.824 | 96.734 | 32.59 | 480 |
|
132 |
+
| [mobilenetv4_hybrid_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.e600_r384_in1k) | 83.800 | 96.770 | 37.76 | 384 |
|
133 |
+
| [mobilenetv4_hybrid_medium.ix_e550_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k) | 83.394 | 96.760 | 11.07 | 448 |
|
134 |
+
| [mobilenetv4_conv_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_large.e600_r384_in1k) | 83.392 | 96.622 | 32.59 | 448 |
|
135 |
+
| [mobilenetv4_conv_aa_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e600_r384_in1k) | 83.244 | 96.392 | 32.59 | 384 |
|
136 |
+
| [mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k) | 82.99 | 96.67 | 11.07 | 320 |
|
137 |
+
| [mobilenetv4_hybrid_medium.ix_e550_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k) | 82.968 | 96.474 | 11.07 | 384 |
|
138 |
+
| [mobilenetv4_conv_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_large.e600_r384_in1k) | 82.952 | 96.266 | 32.59 | 384 |
|
139 |
+
| [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) | 82.674 | 96.31 | 32.59 | 320 |
|
140 |
+
| [mobilenetv4_hybrid_medium.ix_e550_r256_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k) | 82.492 | 96.278 | 11.07 | 320 |
|
141 |
+
| [mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k) | 82.364 | 96.256 | 11.07 | 256 |
|
142 |
+
| [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) | 81.862 | 95.69 | 32.59 | 256 |
|
143 |
+
| [resnet50d.ra4_e3600_r224_in1k](http://hf.co/timm/resnet50d.ra4_e3600_r224_in1k) | 81.838 | 95.922 | 25.58 | 288 |
|
144 |
+
| [mobilenetv3_large_150d.ra4_e3600_r256_in1k](http://hf.co/timm/mobilenetv3_large_150d.ra4_e3600_r256_in1k) | 81.806 | 95.9 | 14.62 | 320 |
|
145 |
+
| [mobilenetv4_hybrid_medium.ix_e550_r256_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k) | 81.446 | 95.704 | 11.07 | 256 |
|
146 |
+
| [efficientnet_b1.ra4_e3600_r240_in1k](http://hf.co/timm/efficientnet_b1.ra4_e3600_r240_in1k) | 81.440 | 95.700 | 7.79 | 288 |
|
147 |
+
| [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) | 81.276 | 95.742 | 11.07 | 256 |
|
148 |
+
| [resnet50d.ra4_e3600_r224_in1k](http://hf.co/timm/resnet50d.ra4_e3600_r224_in1k) | 80.952 | 95.384 | 25.58 | 224 |
|
149 |
+
| [mobilenetv3_large_150d.ra4_e3600_r256_in1k](http://hf.co/timm/mobilenetv3_large_150d.ra4_e3600_r256_in1k) | 80.944 | 95.448 | 14.62 | 256 |
|
150 |
+
| [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) | 80.858 | 95.768 | 9.72 | 320 |
|
151 |
+
| [mobilenet_edgetpu_v2_m.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenet_edgetpu_v2_m.ra4_e3600_r224_in1k) | 80.680 | 95.442 | 8.46 | 256 |
|
152 |
+
| [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) | 80.442 | 95.38 | 11.07 | 224 |
|
153 |
+
| [efficientnet_b1.ra4_e3600_r240_in1k](http://hf.co/timm/efficientnet_b1.ra4_e3600_r240_in1k) | 80.406 | 95.152 | 7.79 | 240 |
|
154 |
+
| [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) | 80.142 | 95.298 | 9.72 | 256 |
|
155 |
+
| [mobilenet_edgetpu_v2_m.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenet_edgetpu_v2_m.ra4_e3600_r224_in1k) | 80.130 | 95.002 | 8.46 | 224 |
|
156 |
+
| [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) | 79.928 | 95.184 | 9.72 | 256 |
|
157 |
+
| [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) | 79.808 | 95.186 | 9.72 | 256 |
|
158 |
+
| [resnetv2_34d.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_34d.ra4_e3600_r224_in1k) | 79.590 | 94.770 | 21.82 | 288 |
|
159 |
+
| [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) | 79.438 | 94.932 | 9.72 | 224 |
|
160 |
+
| [efficientnet_b0.ra4_e3600_r224_in1k](http://hf.co/timm/efficientnet_b0.ra4_e3600_r224_in1k) | 79.364 | 94.754 | 5.29 | 256 |
|
161 |
+
| [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) | 79.094 | 94.77 | 9.72 | 224 |
|
162 |
+
| [resnetv2_34.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_34.ra4_e3600_r224_in1k) | 79.072 | 94.566 | 21.80 | 288 |
|
163 |
+
| [resnet34.ra4_e3600_r224_in1k](http://hf.co/timm/resnet34.ra4_e3600_r224_in1k) | 78.952 | 94.450 | 21.80 | 288 |
|
164 |
+
| [efficientnet_b0.ra4_e3600_r224_in1k](http://hf.co/timm/efficientnet_b0.ra4_e3600_r224_in1k) | 78.584 | 94.338 | 5.29 | 224 |
|
165 |
+
| [resnetv2_34d.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_34d.ra4_e3600_r224_in1k) | 78.268 | 93.952 | 21.82 | 224 |
|
166 |
+
| [resnetv2_34.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_34.ra4_e3600_r224_in1k) | 77.636 | 93.528 | 21.80 | 224 |
|
167 |
+
| [mobilenetv1_125.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_125.ra4_e3600_r224_in1k) | 77.600 | 93.804 | 6.27 | 256 |
|
168 |
+
| [resnet34.ra4_e3600_r224_in1k](http://hf.co/timm/resnet34.ra4_e3600_r224_in1k) | 77.448 | 93.502 | 21.80 | 224 |
|
169 |
+
| [mobilenetv3_large_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv3_large_100.ra4_e3600_r224_in1k) | 77.164 | 93.336 | 5.48 | 256 |
|
170 |
+
| [mobilenetv1_125.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_125.ra4_e3600_r224_in1k) | 76.924 | 93.234 | 6.27 | 224 |
|
171 |
+
| [mobilenetv1_100h.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100h.ra4_e3600_r224_in1k) | 76.596 | 93.272 | 5.28 | 256 |
|
172 |
+
| [mobilenetv3_large_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv3_large_100.ra4_e3600_r224_in1k) | 76.310 | 92.846 | 5.48 | 224 |
|
173 |
+
| [mobilenetv1_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100.ra4_e3600_r224_in1k) | 76.094 | 93.004 | 4.23 | 256 |
|
174 |
+
| [resnetv2_18d.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_18d.ra4_e3600_r224_in1k) | 76.044 | 93.020 | 11.71 | 288 |
|
175 |
+
| [resnet18d.ra4_e3600_r224_in1k](http://hf.co/timm/resnet18d.ra4_e3600_r224_in1k) | 76.024 | 92.780 | 11.71 | 288 |
|
176 |
+
| [mobilenetv1_100h.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100h.ra4_e3600_r224_in1k) | 75.662 | 92.504 | 5.28 | 224 |
|
177 |
+
| [mobilenetv1_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100.ra4_e3600_r224_in1k) | 75.382 | 92.312 | 4.23 | 224 |
|
178 |
+
| [resnetv2_18.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_18.ra4_e3600_r224_in1k) | 75.340 | 92.678 | 11.69 | 288 |
|
179 |
+
| [mobilenetv4_conv_small.e2400_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e2400_r224_in1k) | 74.616 | 92.072 | 3.77 | 256 |
|
180 |
+
| [resnetv2_18d.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_18d.ra4_e3600_r224_in1k) | 74.412 | 91.936 | 11.71 | 224 |
|
181 |
+
| [resnet18d.ra4_e3600_r224_in1k](http://hf.co/timm/resnet18d.ra4_e3600_r224_in1k) | 74.322 | 91.832 | 11.71 | 224 |
|
182 |
+
| [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) | 74.292 | 92.116 | 3.77 | 256 |
|
183 |
+
| [mobilenetv4_conv_small.e2400_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e2400_r224_in1k) | 73.756 | 91.422 | 3.77 | 224 |
|
184 |
+
| [resnetv2_18.ra4_e3600_r224_in1k](http://hf.co/timm/resnetv2_18.ra4_e3600_r224_in1k) | 73.578 | 91.352 | 11.69 | 224 |
|
185 |
+
| [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) | 73.454 | 91.34 | 3.77 | 224 |
|
186 |
+
| [mobilenetv4_conv_small_050.e3000_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small_050.e3000_r224_in1k) | 65.810 | 86.424 | 2.24 | 256 |
|
187 |
+
| [mobilenetv4_conv_small_050.e3000_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small_050.e3000_r224_in1k) | 64.762 | 85.514 | 2.24 | 224 |
|
188 |
|
189 |
## Citation
|
190 |
```bibtex
|
191 |
+
@article{qin2024mobilenetv4,
|
192 |
+
title={MobileNetV4-Universal Models for the Mobile Ecosystem},
|
193 |
+
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},
|
194 |
+
journal={arXiv preprint arXiv:2404.10518},
|
195 |
+
year={2024}
|
196 |
+
}
|
197 |
```
|
198 |
```bibtex
|
199 |
+
@misc{rw2019timm,
|
200 |
+
author = {Ross Wightman},
|
201 |
+
title = {PyTorch Image Models},
|
202 |
+
year = {2019},
|
203 |
+
publisher = {GitHub},
|
204 |
+
journal = {GitHub repository},
|
205 |
+
doi = {10.5281/zenodo.4414861},
|
206 |
+
howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
|
207 |
}
|
208 |
```
|