Add model
Browse files- README.md +93 -0
- config.json +35 -0
- model.safetensors +3 -0
- 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: apache-2.0
|
7 |
+
datasets:
|
8 |
+
- imagenet-1k
|
9 |
+
---
|
10 |
+
# Model card for visformer_small.in1k
|
11 |
+
|
12 |
+
A Visformer image classification model. Trained on ImageNet-1k by https://github.com/hzhang57 and https://github.com/developer0hye.
|
13 |
+
|
14 |
+
## Model Details
|
15 |
+
- **Model Type:** Image classification / feature backbone
|
16 |
+
- **Model Stats:**
|
17 |
+
- Params (M): 40.2
|
18 |
+
- GMACs: 4.9
|
19 |
+
- Activations (M): 11.4
|
20 |
+
- Image size: 224 x 224
|
21 |
+
- **Papers:**
|
22 |
+
- Visformer: The Vision-friendly Transformer: https://arxiv.org/abs/2104.12533
|
23 |
+
- **Dataset:** ImageNet-1k
|
24 |
+
- **Original:** https://github.com/danczs/Visformer
|
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('visformer_small.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 |
+
'visformer_small.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, 7, 7) 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 |
+
@inproceedings{chen2021visformer,
|
87 |
+
title={Visformer: The vision-friendly transformer},
|
88 |
+
author={Chen, Zhengsu and Xie, Lingxi and Niu, Jianwei and Liu, Xuefeng and Wei, Longhui and Tian, Qi},
|
89 |
+
booktitle={Proceedings of the IEEE/CVF international conference on computer vision},
|
90 |
+
pages={589--598},
|
91 |
+
year={2021}
|
92 |
+
}
|
93 |
+
```
|
config.json
ADDED
@@ -0,0 +1,35 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"architecture": "visformer_small",
|
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": true,
|
14 |
+
"interpolation": "bicubic",
|
15 |
+
"crop_pct": 0.9,
|
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 |
+
7,
|
30 |
+
7
|
31 |
+
],
|
32 |
+
"first_conv": "stem.0",
|
33 |
+
"classifier": "head"
|
34 |
+
}
|
35 |
+
}
|
model.safetensors
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:322de7c0427d7e5d797cebdd23230c82829981e544b0597022464faf963950b8
|
3 |
+
size 160999326
|
pytorch_model.bin
ADDED
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
1 |
+
version https://git-lfs.github.com/spec/v1
|
2 |
+
oid sha256:06966b9df3f2e8b940ec71f8c420e38f52147d4ff043c7edd01b8b2876d42cfd
|
3 |
+
size 161051329
|