timm
/

Image Classification
timm
PyTorch
Safetensors
rwightman HF staff commited on
Commit
0b36ae9
1 Parent(s): 90b07ca

Update model config and README

Browse files
Files changed (3) hide show
  1. README.md +146 -2
  2. config.json +1 -0
  3. model.safetensors +3 -0
README.md CHANGED
@@ -2,6 +2,150 @@
2
  tags:
3
  - image-classification
4
  - timm
5
- library_tag: timm
 
 
 
6
  ---
7
- # Model card for tf_efficientnet_b2.ns_jft_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 tf_efficientnet_b2.ns_jft_in1k
11
+
12
+ A EfficientNet image classification model. Trained on ImageNet-1k and unlabeled JFT-300m using Noisy Student semi-supervised learning in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.
13
+
14
+
15
+ ## Model Details
16
+ - **Model Type:** Image classification / feature backbone
17
+ - **Model Stats:**
18
+ - Params (M): 9.1
19
+ - GMACs: 1.0
20
+ - Activations (M): 13.8
21
+ - Image size: 260 x 260
22
+ - **Papers:**
23
+ - EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
24
+ - Self-training with Noisy Student improves ImageNet classification: https://arxiv.org/abs/1911.04252
25
+ - **Dataset:** ImageNet-1k
26
+ - **Original:** https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet
27
+
28
+ ## Model Usage
29
+ ### Image Classification
30
+ ```python
31
+ from urllib.request import urlopen
32
+ from PIL import Image
33
+ import timm
34
+
35
+ img = Image.open(urlopen(
36
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
37
+ ))
38
+
39
+ model = timm.create_model('tf_efficientnet_b2.ns_jft_in1k', pretrained=True)
40
+ model = model.eval()
41
+
42
+ # get model specific transforms (normalization, resize)
43
+ data_config = timm.data.resolve_model_data_config(model)
44
+ transforms = timm.data.create_transform(**data_config, is_training=False)
45
+
46
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
47
+
48
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
49
+ ```
50
+
51
+ ### Feature Map Extraction
52
+ ```python
53
+ from urllib.request import urlopen
54
+ from PIL import Image
55
+ import timm
56
+
57
+ img = Image.open(urlopen(
58
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
59
+ ))
60
+
61
+ model = timm.create_model(
62
+ 'tf_efficientnet_b2.ns_jft_in1k',
63
+ pretrained=True,
64
+ features_only=True,
65
+ )
66
+ model = model.eval()
67
+
68
+ # get model specific transforms (normalization, resize)
69
+ data_config = timm.data.resolve_model_data_config(model)
70
+ transforms = timm.data.create_transform(**data_config, is_training=False)
71
+
72
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
73
+
74
+ for o in output:
75
+ # print shape of each feature map in output
76
+ # e.g.:
77
+ # torch.Size([1, 16, 130, 130])
78
+ # torch.Size([1, 24, 65, 65])
79
+ # torch.Size([1, 48, 33, 33])
80
+ # torch.Size([1, 120, 17, 17])
81
+ # torch.Size([1, 352, 9, 9])
82
+
83
+ print(o.shape)
84
+ ```
85
+
86
+ ### Image Embeddings
87
+ ```python
88
+ from urllib.request import urlopen
89
+ from PIL import Image
90
+ import timm
91
+
92
+ img = Image.open(urlopen(
93
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
94
+ ))
95
+
96
+ model = timm.create_model(
97
+ 'tf_efficientnet_b2.ns_jft_in1k',
98
+ pretrained=True,
99
+ num_classes=0, # remove classifier nn.Linear
100
+ )
101
+ model = model.eval()
102
+
103
+ # get model specific transforms (normalization, resize)
104
+ data_config = timm.data.resolve_model_data_config(model)
105
+ transforms = timm.data.create_transform(**data_config, is_training=False)
106
+
107
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
108
+
109
+ # or equivalently (without needing to set num_classes=0)
110
+
111
+ output = model.forward_features(transforms(img).unsqueeze(0))
112
+ # output is unpooled, a (1, 1408, 9, 9) shaped tensor
113
+
114
+ output = model.forward_head(output, pre_logits=True)
115
+ # output is a (1, num_features) shaped tensor
116
+ ```
117
+
118
+ ## Model Comparison
119
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
120
+
121
+ ## Citation
122
+ ```bibtex
123
+ @inproceedings{tan2019efficientnet,
124
+ title={Efficientnet: Rethinking model scaling for convolutional neural networks},
125
+ author={Tan, Mingxing and Le, Quoc},
126
+ booktitle={International conference on machine learning},
127
+ pages={6105--6114},
128
+ year={2019},
129
+ organization={PMLR}
130
+ }
131
+ ```
132
+ ```bibtex
133
+ @article{Xie2019SelfTrainingWN,
134
+ title={Self-Training With Noisy Student Improves ImageNet Classification},
135
+ author={Qizhe Xie and Eduard H. Hovy and Minh-Thang Luong and Quoc V. Le},
136
+ journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
137
+ year={2019},
138
+ pages={10684-10695}
139
+ }
140
+ ```
141
+ ```bibtex
142
+ @misc{rw2019timm,
143
+ author = {Ross Wightman},
144
+ title = {PyTorch Image Models},
145
+ year = {2019},
146
+ publisher = {GitHub},
147
+ journal = {GitHub repository},
148
+ doi = {10.5281/zenodo.4414861},
149
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
150
+ }
151
+ ```
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": "ns_jft_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:d441728dab04096ffe5ba9fd85d9d7b7d988b0457273e683f9aba17d8e9c58c3
3
+ size 36757206