rwightman HF staff commited on
Commit
b3aef16
1 Parent(s): a30ccd6
Files changed (4) hide show
  1. README.md +157 -0
  2. config.json +35 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,157 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
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 test_efficientnet_ln.r160_in1k
11
+
12
+ A very small test EfficientNet image classification model for testing and sanity checks. Trained on ImageNet-1k by Ross Wightman.
13
+
14
+ ## Model Details
15
+ - **Model Type:** Image classification / feature backbone
16
+ - **Model Stats:**
17
+ - Params (M): 0.4
18
+ - GMACs: 0.1
19
+ - Activations (M): 0.6
20
+ - Image size: 160 x 160
21
+ - **Dataset:** ImageNet-1k
22
+ - **Papers:**
23
+ - PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
24
+ - **Original:** https://github.com/huggingface/pytorch-image-models
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('test_efficientnet_ln.r160_in1k', 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
+ 'test_efficientnet_ln.r160_in1k',
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, 16, 80, 80])
76
+ # torch.Size([1, 24, 40, 40])
77
+ # torch.Size([1, 32, 20, 20])
78
+ # torch.Size([1, 48, 10, 10])
79
+ # torch.Size([1, 64, 5, 5])
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
+ 'test_efficientnet_ln.r160_in1k',
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, 256, 5, 5) 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
+ ### By Top-1
118
+
119
+ |model |img_size|top1 |top5 |param_count|
120
+ |--------------------------------|--------|------|------|-----------|
121
+ |test_convnext3.r160_in1k |192 |54.558|79.356|0.47 |
122
+ |test_convnext2.r160_in1k |192 |53.62 |78.636|0.48 |
123
+ |test_convnext2.r160_in1k |160 |53.51 |78.526|0.48 |
124
+ |test_convnext3.r160_in1k |160 |53.328|78.318|0.47 |
125
+ |test_convnext.r160_in1k |192 |48.532|74.944|0.27 |
126
+ |test_nfnet.r160_in1k |192 |48.298|73.446|0.38 |
127
+ |test_convnext.r160_in1k |160 |47.764|74.152|0.27 |
128
+ |test_nfnet.r160_in1k |160 |47.616|72.898|0.38 |
129
+ |test_efficientnet.r160_in1k |192 |47.164|71.706|0.36 |
130
+ |test_efficientnet_evos.r160_in1k|192 |46.924|71.53 |0.36 |
131
+ |test_byobnet.r160_in1k |192 |46.688|71.668|0.46 |
132
+ |test_efficientnet_evos.r160_in1k|160 |46.498|71.006|0.36 |
133
+ |test_efficientnet.r160_in1k |160 |46.454|71.014|0.36 |
134
+ |test_byobnet.r160_in1k |160 |45.852|70.996|0.46 |
135
+ |test_efficientnet_ln.r160_in1k |192 |44.538|69.974|0.36 |
136
+ |test_efficientnet_gn.r160_in1k |192 |44.448|69.75 |0.36 |
137
+ |test_efficientnet_ln.r160_in1k |160 |43.916|69.404|0.36 |
138
+ |test_efficientnet_gn.r160_in1k |160 |43.88 |69.162|0.36 |
139
+ |test_vit2.r160_in1k |192 |43.454|69.798|0.46 |
140
+ |test_resnet.r160_in1k |192 |42.376|68.744|0.47 |
141
+ |test_vit2.r160_in1k |160 |42.232|68.982|0.46 |
142
+ |test_vit.r160_in1k |192 |41.984|68.64 |0.37 |
143
+ |test_resnet.r160_in1k |160 |41.578|67.956|0.47 |
144
+ |test_vit.r160_in1k |160 |40.946|67.362|0.37 |
145
+
146
+ ## Citation
147
+ ```bibtex
148
+ @misc{rw2019timm,
149
+ author = {Ross Wightman},
150
+ title = {PyTorch Image Models},
151
+ year = {2019},
152
+ publisher = {GitHub},
153
+ journal = {GitHub repository},
154
+ doi = {10.5281/zenodo.4414861},
155
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
156
+ }
157
+ ```
config.json ADDED
@@ -0,0 +1,35 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "test_efficientnet_ln",
3
+ "num_classes": 1000,
4
+ "num_features": 256,
5
+ "pretrained_cfg": {
6
+ "tag": "r160_in1k",
7
+ "custom_load": false,
8
+ "input_size": [
9
+ 3,
10
+ 160,
11
+ 160
12
+ ],
13
+ "fixed_input_size": false,
14
+ "interpolation": "bicubic",
15
+ "crop_pct": 0.95,
16
+ "crop_mode": "center",
17
+ "mean": [
18
+ 0.485,
19
+ 0.456,
20
+ 0.406
21
+ ],
22
+ "std": [
23
+ 0.229,
24
+ 0.224,
25
+ 0.225
26
+ ],
27
+ "num_classes": 1000,
28
+ "pool_size": [
29
+ 5,
30
+ 5
31
+ ],
32
+ "first_conv": "conv_stem",
33
+ "classifier": "classifier"
34
+ }
35
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c14bdb1a89d3b838ea802ac7aed127b3bc3a30b3e3f459049d91f15d0dbdc31b
3
+ size 1429056
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:910f925825b672d3f9d3607a6a8adb4ad7b9c656d0400679d489cba0646411fa
3
+ size 1443137