timm
/

Image Classification
timm
PyTorch
Safetensors
rwightman HF staff commited on
Commit
274d7ee
1 Parent(s): 38c9c01

Update model config and README

Browse files
Files changed (3) hide show
  1. README.md +144 -2
  2. config.json +1 -0
  3. model.safetensors +3 -0
README.md CHANGED
@@ -2,6 +2,148 @@
2
  tags:
3
  - image-classification
4
  - timm
5
- library_tag: timm
 
 
 
6
  ---
7
- # Model card for efficientnet_b2_pruned.in1k
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
2
  tags:
3
  - image-classification
4
  - timm
5
+ library_name: timm
6
+ license: apache-2.0
7
+ datasets:
8
+ - imagenet-1k
9
  ---
10
+ # Model card for efficientnet_b2_pruned.in1k
11
+
12
+ A EfficientNet image classification model. Knapsack pruned from existing weights.
13
+
14
+
15
+ ## Model Details
16
+ - **Model Type:** Image classification / feature backbone
17
+ - **Model Stats:**
18
+ - Params (M): 8.3
19
+ - GMACs: 0.7
20
+ - Activations (M): 9.1
21
+ - Image size: 260 x 260
22
+ - **Papers:**
23
+ - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
24
+ - Knapsack Pruning with Inner Distillation: https://arxiv.org/abs/2002.08258
25
+ - **Dataset:** ImageNet-1k
26
+
27
+ ## Model Usage
28
+ ### Image Classification
29
+ ```python
30
+ from urllib.request import urlopen
31
+ from PIL import Image
32
+ import timm
33
+
34
+ img = Image.open(urlopen(
35
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
36
+ ))
37
+
38
+ model = timm.create_model('efficientnet_b2_pruned.in1k', pretrained=True)
39
+ model = model.eval()
40
+
41
+ # get model specific transforms (normalization, resize)
42
+ data_config = timm.data.resolve_model_data_config(model)
43
+ transforms = timm.data.create_transform(**data_config, is_training=False)
44
+
45
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
46
+
47
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
48
+ ```
49
+
50
+ ### Feature Map Extraction
51
+ ```python
52
+ from urllib.request import urlopen
53
+ from PIL import Image
54
+ import timm
55
+
56
+ img = Image.open(urlopen(
57
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
58
+ ))
59
+
60
+ model = timm.create_model(
61
+ 'efficientnet_b2_pruned.in1k',
62
+ pretrained=True,
63
+ features_only=True,
64
+ )
65
+ model = model.eval()
66
+
67
+ # get model specific transforms (normalization, resize)
68
+ data_config = timm.data.resolve_model_data_config(model)
69
+ transforms = timm.data.create_transform(**data_config, is_training=False)
70
+
71
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
72
+
73
+ for o in output:
74
+ # print shape of each feature map in output
75
+ # e.g.:
76
+ # torch.Size([1, 16, 130, 130])
77
+ # torch.Size([1, 17, 65, 65])
78
+ # torch.Size([1, 42, 33, 33])
79
+ # torch.Size([1, 116, 17, 17])
80
+ # torch.Size([1, 352, 9, 9])
81
+
82
+ print(o.shape)
83
+ ```
84
+
85
+ ### Image Embeddings
86
+ ```python
87
+ from urllib.request import urlopen
88
+ from PIL import Image
89
+ import timm
90
+
91
+ img = Image.open(urlopen(
92
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
93
+ ))
94
+
95
+ model = timm.create_model(
96
+ 'efficientnet_b2_pruned.in1k',
97
+ pretrained=True,
98
+ num_classes=0, # remove classifier nn.Linear
99
+ )
100
+ model = model.eval()
101
+
102
+ # get model specific transforms (normalization, resize)
103
+ data_config = timm.data.resolve_model_data_config(model)
104
+ transforms = timm.data.create_transform(**data_config, is_training=False)
105
+
106
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
107
+
108
+ # or equivalently (without needing to set num_classes=0)
109
+
110
+ output = model.forward_features(transforms(img).unsqueeze(0))
111
+ # output is unpooled, a (1, 1408, 9, 9) shaped tensor
112
+
113
+ output = model.forward_head(output, pre_logits=True)
114
+ # output is a (1, num_features) shaped tensor
115
+ ```
116
+
117
+ ## Model Comparison
118
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
119
+
120
+ ## Citation
121
+ ```bibtex
122
+ @inproceedings{tan2019efficientnet,
123
+ title={Efficientnet: Rethinking model scaling for convolutional neural networks},
124
+ author={Tan, Mingxing and Le, Quoc},
125
+ booktitle={International conference on machine learning},
126
+ pages={6105--6114},
127
+ year={2019},
128
+ organization={PMLR}
129
+ }
130
+ ```
131
+ ```bibtex
132
+ @article{aflalo2020knapsack,
133
+ title={Knapsack pruning with inner distillation},
134
+ author={Aflalo, Yonathan and Noy, Asaf and Lin, Ming and Friedman, Itamar and Zelnik, Lihi},
135
+ journal={arXiv preprint arXiv:2002.08258},
136
+ year={2020}
137
+ }
138
+ ```
139
+ ```bibtex
140
+ @misc{rw2019timm,
141
+ author = {Ross Wightman},
142
+ title = {PyTorch Image Models},
143
+ year = {2019},
144
+ publisher = {GitHub},
145
+ journal = {GitHub repository},
146
+ doi = {10.5281/zenodo.4414861},
147
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
148
+ }
149
+ ```
config.json CHANGED
@@ -3,6 +3,7 @@
3
  "num_classes": 1000,
4
  "num_features": 1408,
5
  "pretrained_cfg": {
 
6
  "custom_load": false,
7
  "input_size": [
8
  3,
 
3
  "num_classes": 1000,
4
  "num_features": 1408,
5
  "pretrained_cfg": {
6
+ "tag": "in1k",
7
  "custom_load": false,
8
  "input_size": [
9
  3,
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fdd245144827c76220197ef672898e24557bb1db7e5b944cf78cdeab74b0eca8
3
+ size 33510258