xiangan commited on
Commit
02ada95
·
verified ·
1 Parent(s): 75b40c3

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -3
README.md CHANGED
@@ -30,16 +30,18 @@ cd unicom/mlcd
30
 
31
  ```python
32
  from vit_rope2d_hf import MLCDVisionModel
33
- from transformers import AutoImageProcessor
34
  from PIL import Image
 
35
  import torch
36
 
37
  # Load model and processor
38
  model = MLCDVisionModel.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-336")
39
- processor = AutoImageProcessor.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-336")
40
 
41
  # Process single image
42
- image = Image.open("document.jpg").convert("RGB")
 
43
  inputs = processor(images=image, return_tensors="pt")
44
 
45
  # Get visual features
@@ -48,4 +50,5 @@ with torch.no_grad():
48
  features = outputs.last_hidden_state
49
 
50
  print(f"Extracted features shape: {features.shape}")
 
51
  ```
 
30
 
31
  ```python
32
  from vit_rope2d_hf import MLCDVisionModel
33
+ from transformers import CLIPImageProcessor
34
  from PIL import Image
35
+ import requests
36
  import torch
37
 
38
  # Load model and processor
39
  model = MLCDVisionModel.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-336")
40
+ processor = CLIPImageProcessor.from_pretrained("DeepGlint-AI/mlcd-vit-bigG-patch14-336")
41
 
42
  # Process single image
43
+ url = "http://images.cocodataset.org/val2017/000000039769.jpg"
44
+ image = Image.open(requests.get(url, stream=True).raw)
45
  inputs = processor(images=image, return_tensors="pt")
46
 
47
  # Get visual features
 
50
  features = outputs.last_hidden_state
51
 
52
  print(f"Extracted features shape: {features.shape}")
53
+ # Extracted features shape: torch.Size([1, 577, 1664])
54
  ```