rwightman HF staff commited on
Commit
5c5dfee
1 Parent(s): d3b01eb
Files changed (4) hide show
  1. README.md +93 -0
  2. config.json +32 -0
  3. model.safetensors +3 -0
  4. pytorch_model.bin +3 -0
README.md ADDED
@@ -0,0 +1,93 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ tags:
3
+ - image-classification
4
+ - timm
5
+ library_name: timm
6
+ license: mit
7
+ datasets:
8
+ - imagenet-1k
9
+ ---
10
+ # Model card for convmixer_768_32.in1k
11
+
12
+ A ConvMixer 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): 21.1
18
+ - GMACs: 19.5
19
+ - Activations (M): 26.0
20
+ - Image size: 224 x 224
21
+ - **Papers:**
22
+ - Patches Are All You Need?: https://arxiv.org/abs/2201.09792
23
+ - **Dataset:** ImageNet-1k
24
+ - **Original:** https://github.com/locuslab/convmixer
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('convmixer_768_32.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
+ ### Image Embeddings
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
+ 'convmixer_768_32.in1k',
61
+ pretrained=True,
62
+ num_classes=0, # remove classifier nn.Linear
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)) # output is (batch_size, num_features) shaped tensor
71
+
72
+ # or equivalently (without needing to set num_classes=0)
73
+
74
+ output = model.forward_features(transforms(img).unsqueeze(0))
75
+ # output is unpooled, a (1, 768, 32, 32) shaped tensor
76
+
77
+ output = model.forward_head(output, pre_logits=True)
78
+ # output is a (1, num_features) shaped tensor
79
+ ```
80
+
81
+ ## Model Comparison
82
+ Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).
83
+
84
+ ## Citation
85
+ ```bibtex
86
+ @article{Chen2021CrossViTCM,
87
+ title={CrossViT: Cross-Attention Multi-Scale Vision Transformer for Image Classification},
88
+ author={Chun-Fu Chen and Quanfu Fan and Rameswar Panda},
89
+ journal={2021 IEEE/CVF International Conference on Computer Vision (ICCV)},
90
+ year={2021},
91
+ pages={347-356}
92
+ }
93
+ ```
config.json ADDED
@@ -0,0 +1,32 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architecture": "convmixer_768_32",
3
+ "num_classes": 1000,
4
+ "num_features": 768,
5
+ "pretrained_cfg": {
6
+ "tag": "in1k",
7
+ "custom_load": false,
8
+ "input_size": [
9
+ 3,
10
+ 224,
11
+ 224
12
+ ],
13
+ "fixed_input_size": false,
14
+ "interpolation": "bicubic",
15
+ "crop_pct": 0.96,
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": null,
29
+ "first_conv": "stem.0",
30
+ "classifier": "head"
31
+ }
32
+ }
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:62ed5ec91004012a90d1a1ad043c4a74724ad444c82a277a6fff10803391743b
3
+ size 84881892
pytorch_model.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba09b2db7517291bf983ff27a8d4921d752fbef6b6ae2fe3248aa0f8d54e9a8f
3
+ size 84989233