yourusername commited on
Commit
f562949
1 Parent(s): b3bbed0

:pencil: add to readme

Browse files
Files changed (1) hide show
  1. README.md +31 -0
README.md CHANGED
@@ -7,3 +7,34 @@ datasets:
7
  ---
8
 
9
  # ViT For Age Classification
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  ---
8
 
9
  # ViT For Age Classification
10
+
11
+ A vision transformer finetuned to classify the age of a given person's face.
12
+
13
+
14
+ ## Usage in Transformers
15
+
16
+ ```python
17
+ import requests
18
+ from PIL import Image
19
+ from io import BytesIO
20
+
21
+ from transformers import ViTFeatureExtractor, ViTForImageClassification
22
+
23
+ # Get example image from official fairface repo + read it in as an image
24
+ r = requests.get('https://github.com/dchen236/FairFace/blob/master/detected_faces/race_Asian_face0.jpg?raw=true')
25
+ im = Image.open(BytesIO(r.content))
26
+
27
+ # Init model, transforms
28
+ model = ViTForImageClassification.from_pretrained('nateraw/vit-age-classifier')
29
+ transforms = ViTFeatureExtractor.from_pretrained('nateraw/vit-age-classifier')
30
+
31
+ # Transform our image and pass it through the model
32
+ inputs = transforms(im, return_tensors='pt')
33
+ output = model(**inputs)
34
+
35
+ # Predicted Class probabilities
36
+ proba = output.logits.softmax(1)
37
+
38
+ # Predicted Classes
39
+ preds = proba.argmax(1)
40
+ ```