timm
/

Image Classification
timm
PyTorch
Safetensors
rwightman HF staff commited on
Commit
492a94c
1 Parent(s): bb60105
Files changed (4) hide show
  1. README.md +127 -0
  2. config.json +34 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,127 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-classification
4
+ - timm
5
+ library_name: timm
6
+ license: unknown
7
+ datasets:
8
+ - imagenet-1k
9
+ ---
10
+ # Model card for dla169
11
+
12
+ A DLA (Deep Layer Aggregation) image classification model. Trained on ImageNet-1k by paper authors.
13
+
14
+ ## Model Details
15
+ - **Model Type:** Image classification / feature backbone
16
+ - **Model Stats:**
17
+ - Params (M): 53.4
18
+ - GMACs: 11.6
19
+ - Activations (M): 20.2
20
+ - Image size: 224 x 224
21
+ - **Papers:**
22
+ - Deep Layer Aggregation: https://arxiv.org/abs/1707.06484
23
+ - **Original:** https://github.com/ucbdrive/dla
24
+ - **Dataset:** ImageNet-1k
25
+
26
+ ## Model Usage
27
+ ### Image Classification
28
+ ```python
29
+ from urllib.request import urlopen
30
+ from PIL import Image
31
+ import timm
32
+
33
+ img = Image.open(urlopen(
34
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
35
+ ))
36
+
37
+ model = timm.create_model('dla169', pretrained=True)
38
+ model = model.eval()
39
+
40
+ # get model specific transforms (normalization, resize)
41
+ data_config = timm.data.resolve_model_data_config(model)
42
+ transforms = timm.data.create_transform(**data_config, is_training=False)
43
+
44
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
45
+
46
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
47
+ ```
48
+
49
+ ### Feature Map Extraction
50
+ ```python
51
+ from urllib.request import urlopen
52
+ from PIL import Image
53
+ import timm
54
+
55
+ img = Image.open(urlopen(
56
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
57
+ ))
58
+
59
+ model = timm.create_model(
60
+ 'dla169',
61
+ pretrained=True,
62
+ features_only=True,
63
+ )
64
+ model = model.eval()
65
+
66
+ # get model specific transforms (normalization, resize)
67
+ data_config = timm.data.resolve_model_data_config(model)
68
+ transforms = timm.data.create_transform(**data_config, is_training=False)
69
+
70
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
71
+
72
+ for o in output:
73
+ # print shape of each feature map in output
74
+ # e.g.:
75
+ # torch.Size([1, 32, 112, 112])
76
+ # torch.Size([1, 128, 56, 56])
77
+ # torch.Size([1, 256, 28, 28])
78
+ # torch.Size([1, 512, 14, 14])
79
+ # torch.Size([1, 1024, 7, 7])
80
+
81
+ print(o.shape)
82
+ ```
83
+
84
+ ### Image Embeddings
85
+ ```python
86
+ from urllib.request import urlopen
87
+ from PIL import Image
88
+ import timm
89
+
90
+ img = Image.open(urlopen(
91
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
92
+ ))
93
+
94
+ model = timm.create_model(
95
+ 'dla169',
96
+ pretrained=True,
97
+ num_classes=0, # remove classifier nn.Linear
98
+ )
99
+ model = model.eval()
100
+
101
+ # get model specific transforms (normalization, resize)
102
+ data_config = timm.data.resolve_model_data_config(model)
103
+ transforms = timm.data.create_transform(**data_config, is_training=False)
104
+
105
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
106
+
107
+ # or equivalently (without needing to set num_classes=0)
108
+
109
+ output = model.forward_features(transforms(img).unsqueeze(0))
110
+ # output is unpooled, a (1, 1024, 7, 7) shaped tensor
111
+
112
+ output = model.forward_head(output, pre_logits=True)
113
+ # output is a (1, num_features) shaped tensor
114
+ ```
115
+
116
+ ## Model Comparison
117
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
118
+
119
+ ## Citation
120
+ ```bibtex
121
+ @inproceedings{yu2018deep,
122
+ title={Deep layer aggregation},
123
+ author={Yu, Fisher and Wang, Dequan and Shelhamer, Evan and Darrell, Trevor},
124
+ booktitle={Proceedings of the IEEE conference on computer vision and pattern recognition},
125
+ year={2018}
126
+ }
127
+ ```
config.json ADDED
@@ -0,0 +1,34 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "dla169",
3
+ "num_classes": 1000,
4
+ "num_features": 1024,
5
+ "pretrained_cfg": {
6
+ "custom_load": false,
7
+ "input_size": [
8
+ 3,
9
+ 224,
10
+ 224
11
+ ],
12
+ "fixed_input_size": false,
13
+ "interpolation": "bilinear",
14
+ "crop_pct": 0.875,
15
+ "crop_mode": "center",
16
+ "mean": [
17
+ 0.485,
18
+ 0.456,
19
+ 0.406
20
+ ],
21
+ "std": [
22
+ 0.229,
23
+ 0.224,
24
+ 0.225
25
+ ],
26
+ "num_classes": 1000,
27
+ "pool_size": [
28
+ 7,
29
+ 7
30
+ ],
31
+ "first_conv": "base_layer.0",
32
+ "classifier": "fc"
33
+ }
34
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1594d3db34d97e74c5f0edd5805dbeffc4a175991de058bbe5bbcd5244141339
3
+ size 214109796
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:bf94cecf8fdce7bd8d9a87caf77fa732c9a3e47e574c8ffdf62a7b9215ae82e0
3
+ size 214357471