|
|
--- |
|
|
license: mit |
|
|
--- |
|
|
# Xception Model for Emotion Recognition |
|
|
|
|
|
This model is based on the **Xception** architecture and trained on the **FER2013** dataset and **CK+** for **emotion recognition**. |
|
|
|
|
|
## Model Details |
|
|
- **Architecture**: Xception |
|
|
- **Input Shape**: (48, 48, 1) |
|
|
- **Output Shape**: 7 classes (emotion categories) |
|
|
- **Pretrained on**: FER2013 dataset (Augmented) |
|
|
- **File Type**: `.h5` |
|
|
|
|
|
## How to Use the Model |
|
|
|
|
|
### Using the Hugging Face Inference API: |
|
|
You can use this model directly through the **Hugging Face Inference API**. Here's an example of how to use it: |
|
|
|
|
|
```python |
|
|
from transformers import pipeline |
|
|
|
|
|
# Replace with the model's name on Hugging Face |
|
|
model_name = "lama9876/Xception-Model" |
|
|
|
|
|
# Load the model using the pipeline |
|
|
model = pipeline('image-classification', model=model_name) |
|
|
|
|
|
# Make a prediction (replace with the path to your image) |
|
|
result = model("path_to_image.jpg") |
|
|
print(result) |
