Update model config and README
Browse files
README.md
CHANGED
@@ -2,7 +2,6 @@
|
|
2 |
tags:
|
3 |
- image-classification
|
4 |
- timm
|
5 |
-
- transformers
|
6 |
library_name: timm
|
7 |
license: apache-2.0
|
8 |
datasets:
|
@@ -27,7 +26,7 @@ There are a number of models in the lower end of model scales that originate in
|
|
27 |
| betwixt | 640 | 2560 (4) | 10 | 12 | y |
|
28 |
| base | 768 | 3072 (4) | 12 | 12 | n |
|
29 |
| so150m2 | 832 | 2176 (2.57) | 13 | 21 | y |
|
30 |
-
|
|
31 |
|
32 |
Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below.
|
33 |
|
@@ -141,8 +140,9 @@ output = model.forward_head(output, pre_logits=True)
|
|
141 |
## Model Comparison
|
142 |
| model | top1 | top5 | param_count | img_size |
|
143 |
| -------------------------------------------------- | ------ | ------ | ----------- | -------- |
|
144 |
-
| [
|
145 |
-
| [
|
|
|
146 |
| [vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 87.438 | 98.256 | 64.11 | 384 |
|
147 |
| [vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k) | 86.608 | 97.934 | 64.11 | 256 |
|
148 |
| [vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 86.594 | 98.02 | 60.4 | 384 |
|
@@ -190,4 +190,4 @@ output = model.forward_head(output, pre_logits=True)
|
|
190 |
journal={ICLR},
|
191 |
year={2021}
|
192 |
}
|
193 |
-
```
|
|
|
2 |
tags:
|
3 |
- image-classification
|
4 |
- timm
|
|
|
5 |
library_name: timm
|
6 |
license: apache-2.0
|
7 |
datasets:
|
|
|
26 |
| betwixt | 640 | 2560 (4) | 10 | 12 | y |
|
27 |
| base | 768 | 3072 (4) | 12 | 12 | n |
|
28 |
| so150m2 | 832 | 2176 (2.57) | 13 | 21 | y |
|
29 |
+
| so150m | 896 | 2304 (2.62) | 14 | 18 | y |
|
30 |
|
31 |
Pretrained on ImageNet-12k and fine-tuned on ImageNet-1k by Ross Wightman in `timm` using recipe template described below.
|
32 |
|
|
|
140 |
## Model Comparison
|
141 |
| model | top1 | top5 | param_count | img_size |
|
142 |
| -------------------------------------------------- | ------ | ------ | ----------- | -------- |
|
143 |
+
| [vit_so150m2_patch16_reg1_gap_448.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_448.sbb2_e200_in12k_ft_in1k) | 88.068 | 98.588 | 136.33 | 448 |
|
144 |
+
| [vit_so150m2_patch16_reg1_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_384.sbb2_e200_in12k_ft_in1k) | 87.930 | 98.502 | 136.33 | 384 |
|
145 |
+
| [vit_so150m2_patch16_reg1_gap_256.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_so150m2_patch16_reg1_gap_256.sbb2_e200_in12k_ft_in1k) | 87.308 | 98.326 | 136.33 | 256 |
|
146 |
| [vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 87.438 | 98.256 | 64.11 | 384 |
|
147 |
| [vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_mediumd_patch16_reg4_gap_256.sbb2_e200_in12k_ft_in1k) | 86.608 | 97.934 | 64.11 | 256 |
|
148 |
| [vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k](https://huggingface.co/timm/vit_betwixt_patch16_reg4_gap_384.sbb2_e200_in12k_ft_in1k) | 86.594 | 98.02 | 60.4 | 384 |
|
|
|
190 |
journal={ICLR},
|
191 |
year={2021}
|
192 |
}
|
193 |
+
```
|