timm
/

Image Classification
timm
PyTorch
Safetensors
rwightman HF staff commited on
Commit
4c8fefe
1 Parent(s): 52683c6

Update model config and README

Browse files
Files changed (3) hide show
  1. README.md +126 -1
  2. config.json +2 -1
  3. model.safetensors +3 -0
README.md CHANGED
@@ -3,5 +3,130 @@ tags:
3
  - image-classification
4
  - timm
5
  library_tag: timm
 
 
 
 
 
6
  ---
7
- # Model card for eva_large_patch14_196.in22k_ft_in22k_in1k
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
3
  - image-classification
4
  - timm
5
  library_tag: timm
6
+ license: mit
7
+ datasets:
8
+ - imagenet-1k
9
+ - imagenet-22k
10
+ - imagenet-22k
11
  ---
12
+ # Model card for eva_large_patch14_196.in22k_ft_in22k_in1k
13
+
14
+ An EVA image classification model. Pretrained on ImageNet-22k with masked image modeling (using EVA-CLIP as a MIM teacher) and fine-tuned on ImageNet-22k then on ImageNet-1k by paper authors.
15
+
16
+ NOTE: `timm` checkpoints are float32 for consistency with other models. Original checkpoints are float16 or bfloat16 in some cases, see originals if that's preferred.
17
+
18
+
19
+ ## Model Details
20
+ - **Model Type:** Image classification / feature backbone
21
+ - **Model Stats:**
22
+ - Params (M): 304.1
23
+ - GMACs: 61.6
24
+ - Activations (M): 63.5
25
+ - Image size: 196 x 196
26
+ - **Papers:**
27
+ - EVA: Exploring the Limits of Masked Visual Representation Learning at Scale: https://arxiv.org/abs/2211.07636
28
+ - **Pretrain Dataset:**
29
+ - ImageNet-22k
30
+ - ImageNet-22k
31
+ - **Dataset:** ImageNet-1k
32
+ - **Original:**
33
+ - https://github.com/baaivision/EVA
34
+ - https://huggingface.co/BAAI/EVA
35
+
36
+ ## Model Usage
37
+ ### Image Classification
38
+ ```python
39
+ from urllib.request import urlopen
40
+ from PIL import Image
41
+ import timm
42
+
43
+ img = Image.open(urlopen(
44
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
45
+ ))
46
+
47
+ model = timm.create_model('eva_large_patch14_196.in22k_ft_in22k_in1k', pretrained=True)
48
+ model = model.eval()
49
+
50
+ # get model specific transforms (normalization, resize)
51
+ data_config = timm.data.resolve_model_data_config(model)
52
+ transforms = timm.data.create_transform(**data_config, is_training=False)
53
+
54
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
55
+
56
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
57
+ ```
58
+
59
+ ### Image Embeddings
60
+ ```python
61
+ from urllib.request import urlopen
62
+ from PIL import Image
63
+ import timm
64
+
65
+ img = Image.open(urlopen(
66
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
67
+ ))
68
+
69
+ model = timm.create_model(
70
+ 'eva_large_patch14_196.in22k_ft_in22k_in1k',
71
+ pretrained=True,
72
+ num_classes=0, # remove classifier nn.Linear
73
+ )
74
+ model = model.eval()
75
+
76
+ # get model specific transforms (normalization, resize)
77
+ data_config = timm.data.resolve_model_data_config(model)
78
+ transforms = timm.data.create_transform(**data_config, is_training=False)
79
+
80
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
81
+
82
+ # or equivalently (without needing to set num_classes=0)
83
+
84
+ output = model.forward_features(transforms(img).unsqueeze(0))
85
+ # output is unpooled, a (1, 197, 1024) shaped tensor
86
+
87
+ output = model.forward_head(output, pre_logits=True)
88
+ # output is a (1, num_features) shaped tensor
89
+ ```
90
+
91
+ ## Model Comparison
92
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
93
+
94
+ |model |top1 |top5 |param_count|img_size|
95
+ |-----------------------------------------------|------|------|-----------|--------|
96
+ |eva02_large_patch14_448.mim_m38m_ft_in22k_in1k |90.054|99.042|305.08 |448 |
97
+ |eva02_large_patch14_448.mim_in22k_ft_in22k_in1k|89.946|99.01 |305.08 |448 |
98
+ |eva_giant_patch14_560.m30m_ft_in22k_in1k |89.792|98.992|1014.45 |560 |
99
+ |eva02_large_patch14_448.mim_in22k_ft_in1k |89.626|98.954|305.08 |448 |
100
+ |eva02_large_patch14_448.mim_m38m_ft_in1k |89.57 |98.918|305.08 |448 |
101
+ |eva_giant_patch14_336.m30m_ft_in22k_in1k |89.56 |98.956|1013.01 |336 |
102
+ |eva_giant_patch14_336.clip_ft_in1k |89.466|98.82 |1013.01 |336 |
103
+ |eva_large_patch14_336.in22k_ft_in22k_in1k |89.214|98.854|304.53 |336 |
104
+ |eva_giant_patch14_224.clip_ft_in1k |88.882|98.678|1012.56 |224 |
105
+ |eva02_base_patch14_448.mim_in22k_ft_in22k_in1k |88.692|98.722|87.12 |448 |
106
+ |eva_large_patch14_336.in22k_ft_in1k |88.652|98.722|304.53 |336 |
107
+ |eva_large_patch14_196.in22k_ft_in22k_in1k |88.592|98.656|304.14 |196 |
108
+ |eva02_base_patch14_448.mim_in22k_ft_in1k |88.23 |98.564|87.12 |448 |
109
+ |eva_large_patch14_196.in22k_ft_in1k |87.934|98.504|304.14 |196 |
110
+ |eva02_small_patch14_336.mim_in22k_ft_in1k |85.74 |97.614|22.13 |336 |
111
+ |eva02_tiny_patch14_336.mim_in22k_ft_in1k |80.658|95.524|5.76 |336 |
112
+
113
+ ## Citation
114
+ ```bibtex
115
+ @article{EVA,
116
+ title={EVA: Exploring the Limits of Masked Visual Representation Learning at Scale},
117
+ author={Fang, Yuxin and Wang, Wen and Xie, Binhui and Sun, Quan and Wu, Ledell and Wang, Xinggang and Huang, Tiejun and Wang, Xinlong and Cao, Yue},
118
+ journal={arXiv preprint arXiv:2211.07636},
119
+ year={2022}
120
+ }
121
+ ```
122
+ ```bibtex
123
+ @misc{rw2019timm,
124
+ author = {Ross Wightman},
125
+ title = {PyTorch Image Models},
126
+ year = {2019},
127
+ publisher = {GitHub},
128
+ journal = {GitHub repository},
129
+ doi = {10.5281/zenodo.4414861},
130
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
131
+ }
132
+ ```
config.json CHANGED
@@ -28,6 +28,7 @@
28
  "num_classes": 1000,
29
  "pool_size": null,
30
  "first_conv": "patch_embed.proj",
31
- "classifier": "head"
 
32
  }
33
  }
 
28
  "num_classes": 1000,
29
  "pool_size": null,
30
  "first_conv": "patch_embed.proj",
31
+ "classifier": "head",
32
+ "license": "mit"
33
  }
34
  }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:344971ca59cf0c12194061924f848b66c2e932a13c5dd6fc07d1c9779b781fc3
3
+ size 1216597406