Hugging Face's logo

timm
/
mobilenetv4_hybrid_medium.e200_r256_in12k

Image Classification
timm
PyTorch
Safetensors
Transformers
Model card Files
xet
Community
rwightman HF Staff commited on
Commit
1e63715
·
verified ·
1 Parent(s): 281db79

Add model

Browse files
Files changed (4) hide show
  1. README.md +182 -0
  2. config.json +41 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,182 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-classification
4
+ - timm
5
+ library_name: timm
6
+ license: apache-2.0
7
+ datasets:
8
+ - imagenet-12k
9
+ ---
10
+ # Model card for mobilenetv4_hybrid_medium.e200_r256_in12k
11
+
12
+ A MobileNet-V4 image classification model. Trained on ImageNet-12k by Ross Wightman.
13
+
14
+
15
+
16
+ ## Model Details
17
+ - **Model Type:** Image classification / feature backbone
18
+ - **Model Stats:**
19
+ - Params (M): 24.9
20
+ - GMACs: 1.3
21
+ - Activations (M): 8.4
22
+ - Image size: train = 256 x 256, test = 320 x 320
23
+ - **Dataset:** ImageNet-12k
24
+ - **Papers:**
25
+ - MobileNetV4 -- Universal Models for the Mobile Ecosystem: https://arxiv.org/abs/2404.10518
26
+ - PyTorch Image Models: https://github.com/huggingface/pytorch-image-models
27
+ - **Original:** https://github.com/tensorflow/models/tree/master/official/vision
28
+
29
+ ## Model Usage
30
+ ### Image Classification
31
+ ```python
32
+ from urllib.request import urlopen
33
+ from PIL import Image
34
+ import timm
35
+
36
+ img = Image.open(urlopen(
37
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
38
+ ))
39
+
40
+ model = timm.create_model('mobilenetv4_hybrid_medium.e200_r256_in12k', pretrained=True)
41
+ model = model.eval()
42
+
43
+ # get model specific transforms (normalization, resize)
44
+ data_config = timm.data.resolve_model_data_config(model)
45
+ transforms = timm.data.create_transform(**data_config, is_training=False)
46
+
47
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
48
+
49
+ top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
50
+ ```
51
+
52
+ ### Feature Map Extraction
53
+ ```python
54
+ from urllib.request import urlopen
55
+ from PIL import Image
56
+ import timm
57
+
58
+ img = Image.open(urlopen(
59
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
60
+ ))
61
+
62
+ model = timm.create_model(
63
+ 'mobilenetv4_hybrid_medium.e200_r256_in12k',
64
+ pretrained=True,
65
+ features_only=True,
66
+ )
67
+ model = model.eval()
68
+
69
+ # get model specific transforms (normalization, resize)
70
+ data_config = timm.data.resolve_model_data_config(model)
71
+ transforms = timm.data.create_transform(**data_config, is_training=False)
72
+
73
+ output = model(transforms(img).unsqueeze(0)) # unsqueeze single image into batch of 1
74
+
75
+ for o in output:
76
+ # print shape of each feature map in output
77
+ # e.g.:
78
+ # torch.Size([1, 32, 128, 128])
79
+ # torch.Size([1, 48, 64, 64])
80
+ # torch.Size([1, 80, 32, 32])
81
+ # torch.Size([1, 160, 16, 16])
82
+ # torch.Size([1, 960, 8, 8])
83
+
84
+ print(o.shape)
85
+ ```
86
+
87
+ ### Image Embeddings
88
+ ```python
89
+ from urllib.request import urlopen
90
+ from PIL import Image
91
+ import timm
92
+
93
+ img = Image.open(urlopen(
94
+ 'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
95
+ ))
96
+
97
+ model = timm.create_model(
98
+ 'mobilenetv4_hybrid_medium.e200_r256_in12k',
99
+ pretrained=True,
100
+ num_classes=0, # remove classifier nn.Linear
101
+ )
102
+ model = model.eval()
103
+
104
+ # get model specific transforms (normalization, resize)
105
+ data_config = timm.data.resolve_model_data_config(model)
106
+ transforms = timm.data.create_transform(**data_config, is_training=False)
107
+
108
+ output = model(transforms(img).unsqueeze(0)) # output is (batch_size, num_features) shaped tensor
109
+
110
+ # or equivalently (without needing to set num_classes=0)
111
+
112
+ output = model.forward_features(transforms(img).unsqueeze(0))
113
+ # output is unpooled, a (1, 960, 8, 8) shaped tensor
114
+
115
+ output = model.forward_head(output, pre_logits=True)
116
+ # output is a (1, num_features) shaped tensor
117
+ ```
118
+
119
+ ## Model Comparison
120
+ ### By Top-1
121
+
122
+ | model |top1 |top1_err|top5 |top5_err|param_count|img_size|
123
+ |--------------------------------------------------------------------------------------------------|------|--------|------|--------|-----------|--------|
124
+ | [mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k)|84.99 |15.01 |97.294|2.706 |32.59 |544 |
125
+ | [mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k)|84.772|15.228 |97.344|2.656 |32.59 |480 |
126
+ | [mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r448_in12k_ft_in1k)|84.64 |15.36 |97.114|2.886 |32.59 |448 |
127
+ | [mobilenetv4_hybrid_large.ix_e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k) |84.356|15.644 |96.892 |3.108 |37.76 |448 |
128
+ | [mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e230_r384_in12k_ft_in1k)|84.314|15.686 |97.102|2.898 |32.59 |384 |
129
+ | [mobilenetv4_hybrid_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.e600_r384_in1k) |84.266|15.734 |96.936 |3.064 |37.76 |448 |
130
+ | [mobilenetv4_hybrid_large.ix_e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.ix_e600_r384_in1k) |83.990|16.010 |96.702 |3.298 |37.76 |384 |
131
+ | [mobilenetv4_conv_aa_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e600_r384_in1k) |83.824|16.176 |96.734|3.266 |32.59 |480 |
132
+ | [mobilenetv4_hybrid_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_large.e600_r384_in1k) |83.800|16.200 |96.770 |3.230 |37.76 |384 |
133
+ | [mobilenetv4_hybrid_medium.ix_e550_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k) |83.394|16.606 |96.760|3.240 |11.07 |448 |
134
+ | [mobilenetv4_conv_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_large.e600_r384_in1k) |83.392|16.608 |96.622 |3.378 |32.59 |448 |
135
+ | [mobilenetv4_conv_aa_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_aa_large.e600_r384_in1k) |83.244|16.756 |96.392|3.608 |32.59 |384 |
136
+ | [mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k)|82.99 |17.01 |96.67 |3.33 |11.07 |320 |
137
+ | [mobilenetv4_hybrid_medium.ix_e550_r384_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r384_in1k) |82.968|17.032 |96.474|3.526 |11.07 |384 |
138
+ | [mobilenetv4_conv_large.e600_r384_in1k](http://hf.co/timm/mobilenetv4_conv_large.e600_r384_in1k) |82.952|17.048 |96.266 |3.734 |32.59 |384 |
139
+ | [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) |82.674|17.326 |96.31 |3.69 |32.59 |320 |
140
+ | [mobilenetv4_hybrid_medium.ix_e550_r256_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k) |82.492|17.508 |96.278|3.722 |11.07 |320 |
141
+ | [mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e200_r256_in12k_ft_in1k)|82.364|17.636 |96.256|3.744 |11.07 |256 |
142
+ | [mobilenetv4_conv_large.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_large.e500_r256_in1k) |81.862|18.138 |95.69 |4.31 |32.59 |256 |
143
+ | [mobilenetv4_hybrid_medium.ix_e550_r256_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.ix_e550_r256_in1k) |81.446|18.554 |95.704|4.296 |11.07 |256 |
144
+ | [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) |81.276|18.724 |95.742|4.258 |11.07 |256 |
145
+ | [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) |80.858|19.142 |95.768|4.232 |9.72 |320 |
146
+ | [mobilenetv4_hybrid_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_hybrid_medium.e500_r224_in1k) |80.442|19.558 |95.38 |4.62 |11.07 |224 |
147
+ | [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) |80.142|19.858 |95.298|4.702 |9.72 |256 |
148
+ | [mobilenetv4_conv_medium.e500_r256_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r256_in1k) |79.928|20.072 |95.184|4.816 |9.72 |256 |
149
+ | [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) |79.808|20.192 |95.186|4.814 |9.72 |256 |
150
+ | [mobilenetv4_conv_blur_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_blur_medium.e500_r224_in1k) |79.438|20.562 |94.932|5.068 |9.72 |224 |
151
+ | [efficientnet_b0.ra4_e3600_r224_in1k](http://hf.co/timm/efficientnet_b0.ra4_e3600_r224_in1k) |79.364|20.636 |94.754|5.246 |5.29 |256 |
152
+ | [mobilenetv4_conv_medium.e500_r224_in1k](http://hf.co/timm/mobilenetv4_conv_medium.e500_r224_in1k) |79.094|20.906 |94.77 |5.23 |9.72 |224 |
153
+ | [efficientnet_b0.ra4_e3600_r224_in1k](http://hf.co/timm/efficientnet_b0.ra4_e3600_r224_in1k) |78.584|21.416 |94.338|5.662 |5.29 |224 |
154
+ | [mobilenetv1_100h.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100h.ra4_e3600_r224_in1k) |76.596|23.404 |93.272|6.728 |5.28 |256 |
155
+ | [mobilenetv1_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100.ra4_e3600_r224_in1k) |76.094|23.906 |93.004|6.996 |4.23 |256 |
156
+ | [mobilenetv1_100h.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100h.ra4_e3600_r224_in1k) |75.662|24.338 |92.504|7.496 |5.28 |224 |
157
+ | [mobilenetv1_100.ra4_e3600_r224_in1k](http://hf.co/timm/mobilenetv1_100.ra4_e3600_r224_in1k) |75.382|24.618 |92.312|7.688 |4.23 |224 |
158
+ | [mobilenetv4_conv_small.e2400_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e2400_r224_in1k) |74.616|25.384 |92.072|7.928 |3.77 |256 |
159
+ | [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) |74.292|25.708 |92.116|7.884 |3.77 |256 |
160
+ | [mobilenetv4_conv_small.e2400_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e2400_r224_in1k) |73.756|26.244 |91.422|8.578 |3.77 |224 |
161
+ | [mobilenetv4_conv_small.e1200_r224_in1k](http://hf.co/timm/mobilenetv4_conv_small.e1200_r224_in1k) |73.454|26.546 |91.34 |8.66 |3.77 |224 |
162
+
163
+ ## Citation
164
+ ```bibtex
165
+ @article{qin2024mobilenetv4,
166
+ title={MobileNetV4-Universal Models for the Mobile Ecosystem},
167
+ author={Qin, Danfeng and Leichner, Chas and Delakis, Manolis and Fornoni, Marco and Luo, Shixin and Yang, Fan and Wang, Weijun and Banbury, Colby and Ye, Chengxi and Akin, Berkin and others},
168
+ journal={arXiv preprint arXiv:2404.10518},
169
+ year={2024}
170
+ }
171
+ ```
172
+ ```bibtex
173
+ @misc{rw2019timm,
174
+ author = {Ross Wightman},
175
+ title = {PyTorch Image Models},
176
+ year = {2019},
177
+ publisher = {GitHub},
178
+ journal = {GitHub repository},
179
+ doi = {10.5281/zenodo.4414861},
180
+ howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
181
+ }
182
+ ```
config.json ADDED
@@ -0,0 +1,41 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "mobilenetv4_hybrid_medium",
3
+ "num_classes": 11821,
4
+ "num_features": 960,
5
+ "pretrained_cfg": {
6
+ "tag": "e200_r256_in12k",
7
+ "custom_load": false,
8
+ "input_size": [
9
+ 3,
10
+ 256,
11
+ 256
12
+ ],
13
+ "test_input_size": [
14
+ 3,
15
+ 320,
16
+ 320
17
+ ],
18
+ "fixed_input_size": false,
19
+ "interpolation": "bicubic",
20
+ "crop_pct": 0.95,
21
+ "test_crop_pct": 1.0,
22
+ "crop_mode": "center",
23
+ "mean": [
24
+ 0.485,
25
+ 0.456,
26
+ 0.406
27
+ ],
28
+ "std": [
29
+ 0.229,
30
+ 0.224,
31
+ 0.225
32
+ ],
33
+ "num_classes": 11821,
34
+ "pool_size": [
35
+ 12,
36
+ 12
37
+ ],
38
+ "first_conv": "conv_stem",
39
+ "classifier": "classifier"
40
+ }
41
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:789b9fd582e6d2a7555f19d66ea2afa0cfcddaede8a7a92557ee3284f7177e22
3
+ size 100111188
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d92a003c81b414bb0af39d69e8a3b940c001d1079a320d3033e9e96a7d98f3df
3
+ size 100276458