Create model_card.md
Browse files- model_card.md +27 -0
model_card.md
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
# ALSATIX ResNet50 Model
|
2 |
+
|
3 |
+
This model is trained to classify images into 5 categories:
|
4 |
+
|
5 |
+
1. **Alkol**: Alcohol-related images
|
6 |
+
2. **Normal**: Regular images
|
7 |
+
3. **NSFW**: Not Safe for Work images
|
8 |
+
4. **Silah**: Weapon-related images
|
9 |
+
5. **Tutun**: Tobacco-related images
|
10 |
+
|
11 |
+
## Model Architecture
|
12 |
+
- Base: ResNet50 pre-trained on ImageNet
|
13 |
+
- Custom top layers: Dense (256 units), Dropout (0.5), Output (5 classes)
|
14 |
+
|
15 |
+
## Usage
|
16 |
+
|
17 |
+
To use this model for image classification:
|
18 |
+
|
19 |
+
```python
|
20 |
+
from transformers import TFAutoModelForImageClassification, AutoImageProcessor
|
21 |
+
|
22 |
+
model = TFAutoModelForImageClassification.from_pretrained("iammbrn/alsatix_image_control_model")
|
23 |
+
processor = AutoImageProcessor.from_pretrained("iammbrn/alsatix_image_control_model")
|
24 |
+
|
25 |
+
# Preprocess your image
|
26 |
+
image = processor(image, return_tensors="pt")
|
27 |
+
predictions = model(**image)
|