File size: 1,871 Bytes
e86c191 0c9c39d 696ddc7 0c9c39d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 |
---
license: mit
base_model:
- timm/swin_base_patch4_window7_224.ms_in22k_ft_in1k
pipeline_tag: image-classification
library_name: timm
---
# PowerPoint slide classifier
This is a classifier to classify 5 types of PowerPoint slide layouts. Finetuned from `timm/swin_base_patch4_window7_224.ms_in22k_ft_in1k` and trained on 10k powerpoint slide images.
* `0`: Common content slide
* `1`: End slide
* `2`: Start slide
* `3`: Subtitle slide
* `4`: Subtitle list slide
## Usage
### Install timm and dependencies
```bash
pip install timm==1.0.15 torch==2.7.0 torchvision==0.22.0
```
### Inference
Use the following code to classify images from a folder.
```python
import os
import timm
import torch
from PIL import Image
from torchvision import transforms
device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
image_folder = 'path_to_images'
transform = transforms.Compose([
transforms.Resize((224, 224)),
transforms.ToTensor(),
transforms.Normalize(
mean=[0.485, 0.456, 0.406],
std=[0.229, 0.224, 0.225]
)
])
model = timm.create_model('swin_base_patch4_window7_224', pretrained=False, num_classes=5)
model.load_state_dict(torch.load('pytorch_model.bin'))
model.to(device)
model.eval()
image_files = [f for f in os.listdir(image_folder) if f.lower().endswith('.png')]
idx_to_class = {
0: 'content',
1: 'end',
2: 'start',
3: 'subt',
4: 'subtl'
}
with torch.no_grad():
for image_name in image_files:
image_path = os.path.join(image_folder, image_name)
image = Image.open(image_path).convert('RGB')
input_tensor = transform(image).unsqueeze(0).to(device)
output = model(input_tensor)
predicted_class = torch.argmax(output, dim=1).item()
predicted_label = idx_to_class[predicted_class]
print(f"{image_name} --> {predicted_label}")
```
|