Update README.md

README.md

@@ -1,9 +1,23 @@
 ---
 license: apache-2.0
+language:
+- en
+base_model:
+- google/siglip2-base-patch16-224
+pipeline_tag: image-classification
+library_name: transformers
+tags:
+- gym
+- workout
+- classifier
 ---
-
 ![sdfvdfv.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/kJ1YXUFjmOahI6LmpI--x.png)
 
+# **Gym-Workout-Classifier-SigLIP2**
+
+> **Gym-Workout-Classifier-SigLIP2** is an image classification vision-language encoder model fine-tuned from **google/siglip2-base-patch16-224** for a single-label classification task. It is designed to classify gym workout exercises using the **SiglipForImageClassification** architecture.  
+
+
     Classification Report:
                          precision    recall  f1-score   support
     
@@ -37,5 +51,90 @@ license: apache-2.0
 
 ![download.png](https://cdn-uploads.huggingface.co/production/uploads/65bb837dbfb878f46c77de4c/czlXLMN1O6q2yL4364ySm.png)
 
+The model categorizes images into 22 workout classes:
+- **Class 0:** "barbell biceps curl"
+- **Class 1:** "bench press"
+- **Class 2:** "chest fly machine"
+- **Class 3:** "deadlift"
+- **Class 4:** "decline bench press"
+- **Class 5:** "hammer curl"
+- **Class 6:** "hip thrust"
+- **Class 7:** "incline bench press"
+- **Class 8:** "lat pulldown"
+- **Class 9:** "lateral raises"
+- **Class 10:** "leg extension"
+- **Class 11:** "leg raises"
+- **Class 12:** "plank"
+- **Class 13:** "pull up"
+- **Class 14:** "push up"
+- **Class 15:** "romanian deadlift"
+- **Class 16:** "russian twist"
+- **Class 17:** "shoulder press"
+- **Class 18:** "squat"
+- **Class 19:** "t bar row"
+- **Class 20:** "tricep dips"
+- **Class 21:** "tricep pushdown"
+
+# **Run with Transformers🤗**
+
+```python
+!pip install -q transformers torch pillow gradio
+```
+
+```python
+import gradio as gr
+from transformers import AutoImageProcessor
+from transformers import SiglipForImageClassification
+from transformers.image_utils import load_image
+from PIL import Image
+import torch
+
+# Load model and processor
+model_name = "prithivMLmods/Gym-Workout-Classifier-SigLIP2"
+model = SiglipForImageClassification.from_pretrained(model_name)
+processor = AutoImageProcessor.from_pretrained(model_name)
+
+def workout_classification(image):
+    """Predicts workout exercise classification for an image."""
+    image = Image.fromarray(image).convert("RGB")
+    inputs = processor(images=image, return_tensors="pt")
+    
+    with torch.no_grad():
+        outputs = model(**inputs)
+        logits = outputs.logits
+        probs = torch.nn.functional.softmax(logits, dim=1).squeeze().tolist()
+    
+    labels = {
+        "0": "barbell biceps curl", "1": "bench press", "2": "chest fly machine", "3": "deadlift",
+        "4": "decline bench press", "5": "hammer curl", "6": "hip thrust", "7": "incline bench press",
+        "8": "lat pulldown", "9": "lateral raises", "10": "leg extension", "11": "leg raises",
+        "12": "plank", "13": "pull up", "14": "push up", "15": "romanian deadlift",
+        "16": "russian twist", "17": "shoulder press", "18": "squat", "19": "t bar row",
+        "20": "tricep dips", "21": "tricep pushdown"
+    }
+    predictions = {labels[str(i)]: round(probs[i], 3) for i in range(len(probs))}
+    
+    return predictions
+
+# Create Gradio interface
+iface = gr.Interface(
+    fn=workout_classification,
+    inputs=gr.Image(type="numpy"),
+    outputs=gr.Label(label="Prediction Scores"),
+    title="Gym Workout Classification",
+    description="Upload an image to classify the workout exercise."
+)
+
+# Launch the app
+if __name__ == "__main__":
+    iface.launch()
+```
+
+# **Intended Use:**  
 
+The **Gym-Workout-Classifier-SigLIP2** model is designed to classify different gym exercises based on images. Potential use cases include:  
 
+- **Workout Tracking:** Identifying exercises performed during a workout session.
+- **Personal Training Assistance:** Helping trainers analyze and correct exercise form.
+- **Gym Activity Monitoring:** Automating exercise logging and analysis in fitness apps.
+- **AI-Powered Fitness Coaching:** Supporting AI-based fitness programs with real-time workout recognition.