beingamit99 commited on
Commit
c3a9d45
·
1 Parent(s): 03f6a59

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +7 -10
README.md CHANGED
@@ -40,20 +40,20 @@ Feel free to explore and integrate this model into your applications for accurat
40
  ### Approach
41
 
42
  ### First Approach
43
- <code>
44
  import numpy as np
45
  from PIL import Image
46
  from transformers import AutoImageProcessor, AutoModelForImageClassification
47
 
48
- #Load the model and image processor
49
  processor = AutoImageProcessor.from_pretrained("beingamit99/car_damage_detection")
50
  model = AutoModelForImageClassification.from_pretrained("beingamit99/car_damage_detection")
51
 
52
- #Load and process the image
53
  image = Image.open(IMAGE)
54
  inputs = processor(images=image, return_tensors="pt")
55
 
56
- #Make predictions
57
  outputs = model(**inputs)
58
  logits = outputs.logits.detach().cpu().numpy()
59
  predicted_class_id = np.argmax(logits)
@@ -61,15 +61,12 @@ predicted_proba = np.max(logits)
61
  label_map = model.config.id2label
62
  predicted_class_name = label_map[predicted_class_id]
63
 
64
- #Print the results
65
- print(f"Predicted class: {predicted_class_name} (probability: {predicted_proba:.4f})")
66
- </code>
67
 
68
  ### Second Approach
69
- <code>
70
  from transformers import pipeline
71
-
72
  #Create a classification pipeline
73
  pipe = pipeline("image-classification", model="beingamit99/car_damage_detection")
74
  pipe(IMAGE)
75
- </code>
 
40
  ### Approach
41
 
42
  ### First Approach
43
+ ```python
44
  import numpy as np
45
  from PIL import Image
46
  from transformers import AutoImageProcessor, AutoModelForImageClassification
47
 
48
+ # Load the model and image processor
49
  processor = AutoImageProcessor.from_pretrained("beingamit99/car_damage_detection")
50
  model = AutoModelForImageClassification.from_pretrained("beingamit99/car_damage_detection")
51
 
52
+ # Load and process the image
53
  image = Image.open(IMAGE)
54
  inputs = processor(images=image, return_tensors="pt")
55
 
56
+ # Make predictions
57
  outputs = model(**inputs)
58
  logits = outputs.logits.detach().cpu().numpy()
59
  predicted_class_id = np.argmax(logits)
 
61
  label_map = model.config.id2label
62
  predicted_class_name = label_map[predicted_class_id]
63
 
64
+ # Print the results
65
+ print(f"Predicted class: {predicted_class_name} (probability: {predicted_proba:.4f}")
 
66
 
67
  ### Second Approach
68
+ ```python
69
  from transformers import pipeline
 
70
  #Create a classification pipeline
71
  pipe = pipeline("image-classification", model="beingamit99/car_damage_detection")
72
  pipe(IMAGE)