Hugging Face's logo

lrzjason
/
anime_portrait_vit

Image Classification
Transformers
Safetensors
vit
anime
Inference Endpoints
Model card Files Community
lrzjason commited on
Commit
14295f4
·
verified ·
1 Parent(s): e54f8e2

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +3 -5
README.md CHANGED
@@ -1,17 +1,15 @@
1
  ---
2
  license: apache-2.0
 
 
3
  ---
4
  Trained a vit model to do classification on anime dataset.
5
 
6
  Divided into four categories: head_only, upperbody, knee_level, fullbody
7
  + head_only
8
- ![head_only](https://huggingface.co/lrzjason/anime_portrait_vit/blob/main/head_only_example.jpg)
9
  + upperbody
10
- ![upperbody](https://huggingface.co/lrzjason/anime_portrait_vit/blob/main/upperbody_example.jpg)
11
  + knee_level
12
- ![knee_level](https://huggingface.co/lrzjason/anime_portrait_vit/blob/main/knee_level_example.jpg)
13
  + fullbody
14
- ![fullbody](https://huggingface.co/lrzjason/anime_portrait_vit/blob/main/fullbody_example.jpg)
15
  ```
16
  from datasets import load_dataset
17
  from PIL import Image
@@ -37,4 +35,4 @@ with torch.no_grad():
37
  # model predicts one of the 1000 ImageNet classes
38
  predicted_label = logits.argmax(-1).item()
39
  print(f'predicted_label: {model.config.id2label[predicted_label]}')
40
- ```
 
1
  ---
2
  license: apache-2.0
3
+ tags:
4
+ - anime
5
  ---
6
  Trained a vit model to do classification on anime dataset.
7
 
8
  Divided into four categories: head_only, upperbody, knee_level, fullbody
9
  + head_only
 
10
  + upperbody
 
11
  + knee_level
 
12
  + fullbody
 
13
  ```
14
  from datasets import load_dataset
15
  from PIL import Image
 
35
  # model predicts one of the 1000 ImageNet classes
36
  predicted_label = logits.argmax(-1).item()
37
  print(f'predicted_label: {model.config.id2label[predicted_label]}')
38
+ ```