Improve model card: add usage example, fix preprocessing details, expand limitations

Add an extended description including:
- Working code example using the transformers pipeline
- Updated preprocessing details with specific values (224x224, ImageNet normalization)
- Expanded limitations section with concrete details on dataset bias, class imbalance, skin tone bias, and input requirements

README.md

@@ -1,24 +1,17 @@
----
-license: apache-2.0
----
+---
+license: apache-2.0
+---
 # Vision Transformer (ViT) for Facial Expression Recognition Model Card
 
 ## Model Overview
-
 - **Model Name:** [trpakov/vit-face-expression](https://huggingface.co/trpakov/vit-face-expression)
-
 - **Task:** Facial Expression/Emotion Recognition
-
 - **Dataset:** [FER2013](https://www.kaggle.com/datasets/msambare/fer2013)
-
 - **Model Architecture:** [Vision Transformer (ViT)](https://huggingface.co/docs/transformers/model_doc/vit)
-
 - **Finetuned from model:** [vit-base-patch16-224-in21k](https://huggingface.co/google/vit-base-patch16-224-in21k)
 
 ## Model Description
-
 The vit-face-expression model is a Vision Transformer fine-tuned for the task of facial emotion recognition. 
-
 It is trained on the FER2013 dataset, which consists of facial images categorized into seven different emotions:
 - Angry
 - Disgust
@@ -29,18 +22,44 @@ It is trained on the FER2013 dataset, which consists of facial images categorize
 - Neutral
 
 ## Data Preprocessing
-
 The input images are preprocessed before being fed into the model. The preprocessing steps include:
-- **Resizing:** Images are resized to the specified input size.
-- **Normalization:** Pixel values are normalized to a specific range.
+- **Resizing:** Images are resized to 224x224 pixels before being fed into the model.
+- **Normalization:** Pixel values are normalized using ImageNet mean and standard deviation.
 - **Data Augmentation:** Random transformations such as rotations, flips, and zooms are applied to augment the training dataset.
 
 ## Evaluation Metrics
-
 - **Validation set accuracy:** 0.7113
 - **Test set accuracy:** 0.7116
 
-## Limitations
+## Usage
+```python
+from transformers import pipeline
+from PIL import Image
+
+# Load the model
+pipe = pipeline("image-classification", model="trpakov/vit-face-expression")
+
+# Load an image (must contain a face)
+image = Image.open("your_image.jpg").convert("RGB")
 
-- **Data Bias:** The model's performance may be influenced by biases present in the training data.
-- **Generalization:** The model's ability to generalize to unseen data is subject to the diversity of the training dataset.
+# Run inference
+results = pipe(image)
+
+# Output: list of dicts with 'label' and 'score'
+# Example: [{'label': 'happy', 'score': 0.98}, {'label': 'neutral', 'score': 0.01}, ...]
+print(results)
+```
+
+## Limitations
+- **Dataset bias:** FER2013 is collected from Google Image Search and is known 
+  to contain noisy and mislabelled samples, which affects model reliability.
+- **Class imbalance:** The dataset is heavily skewed toward "happy" and "neutral", 
+  making the model less reliable for underrepresented classes like "disgust" and "fear".
+- **Skin tone bias:** The model may perform worse on darker skin tones due to 
+  underrepresentation in the training data.
+- **Input requirements:** The model expects a cropped, frontal face image. 
+  Performance degrades significantly on profile faces, occluded faces, or 
+  images where the face is not the primary subject.
+- **Image size:** Input images are resized to 224x224 pixels internally.
+- **Real-world generalization:** Lab-posed expressions in training data differ 
+  from natural spontaneous expressions in the wild.