Zero-Shot Image Classification
Transformers
Safetensors
siglip2
vision
marksverdhei commited on
Commit
630b7cb
·
verified ·
1 Parent(s): b53b807

Fix error in example code snippet

Browse files

Looks like you forgot to load the image from the url in the first example. This PR fixes that.

Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -26,6 +26,7 @@ Here is how to use this model to perform zero-shot image classification:
26
 
27
  ```python
28
  from transformers import pipeline
 
29
 
30
  # load pipeline
31
  ckpt = "google/siglip2-base-patch16-naflex"
@@ -33,6 +34,7 @@ image_classifier = pipeline(model=ckpt, task="zero-shot-image-classification")
33
 
34
  # load image and candidate labels
35
  url = "http://images.cocodataset.org/val2017/000000039769.jpg"
 
36
  candidate_labels = ["2 cats", "a plane", "a remote"]
37
 
38
  # run inference
 
26
 
27
  ```python
28
  from transformers import pipeline
29
+ from transformers.image_utils import load_image
30
 
31
  # load pipeline
32
  ckpt = "google/siglip2-base-patch16-naflex"
 
34
 
35
  # load image and candidate labels
36
  url = "http://images.cocodataset.org/val2017/000000039769.jpg"
37
+ image = load_image(url)
38
  candidate_labels = ["2 cats", "a plane", "a remote"]
39
 
40
  # run inference