Clean initial commit

.gitattributes

@@ -0,0 +1,36 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz filter=lfs diff=lfs merge=lfs -text
+*.zip filter=lfs diff=lfs merge=lfs -text
+*.zst filter=lfs diff=lfs merge=lfs -text
+*tfevents* filter=lfs diff=lfs merge=lfs -text
+*.jpg filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,12 @@
+---
+title: Rice-classification With Export Result Feature
+emoji: 📉
+colorFrom: green
+colorTo: purple
+sdk: gradio
+sdk_version: 6.5.1
+app_file: app.py
+pinned: false
+---
+
+Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference

app.py

@@ -0,0 +1,292 @@
+import cv2
+import numpy as np
+from PIL import Image
+import torch
+from torchvision import models, transforms
+from ultralytics import YOLO
+import gradio as gr
+import torch.nn as nn
+import pandas as pd
+from io import BytesIO
+
+# ============================================
+# RICE ANALYZER PRO
+# Advanced Grain Analytics and Quality Assessment Platform
+# ============================================
+
+# --- SYSTEM CONFIGURATION ---
+device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
+
+# Initialize detection and classification models
+try:
+    detection_model = YOLO('best.pt')
+    classifier_network = models.resnet50(weights=None)
+    classifier_network.fc = nn.Linear(classifier_network.fc.in_features, 3)
+    classifier_network.load_state_dict(
+        torch.load('rice_resnet_model.pth', map_location=device)
+    )
+    classifier_network = classifier_network.to(device)
+    classifier_network.eval()
+    models_loaded = True
+except Exception as e:
+    print(f"Model initialization failed: {e}")
+    detection_model = None
+    classifier_network = None
+    models_loaded = False
+
+# --- VARIETY DEFINITIONS ---
+VARIETY_MAP = {
+    0: "C9 Premium",
+    1: "Kant Special",
+    2: "Superfine Grade"
+}
+
+VARIETY_COLORS = {
+    "C9 Premium": (255, 100, 100),      # Red
+    "Kant Special": (100, 100, 255),    # Blue
+    "Superfine Grade": (100, 255, 100)  # Green
+}
+
+# --- IMAGE PREPROCESSING ---
+image_preprocessor = transforms.Compose([
+    transforms.Resize((224, 224)),
+    transforms.ToTensor(),
+    transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
+])
+
+# ============================================
+# ANALYTICS FUNCTIONS
+# ============================================
+
+def classify_grain(grain_image):
+    """
+    Classify a single grain using the neural network.
+    Returns the grain variety label.
+    """
+    if not models_loaded:
+        return "System Error"
+    
+    tensor_input = image_preprocessor(grain_image).unsqueeze(0).to(device)
+    with torch.no_grad():
+        output = classifier_network(tensor_input)
+        class_idx = torch.argmax(output, dim=1).item()
+    return VARIETY_MAP[class_idx]
+
+def generate_distribution_report(variety_counts):
+    """
+    Generate a text-based summary of grain variety distribution
+    with total counts, percentages, and dominant variety.
+    """
+    total = sum(variety_counts.values())
+    if total == 0:
+        return "No grains detected for analysis."
+    
+    report = ["## Grain Distribution Report\n"]
+    report.append(f"Total Grains Detected: **{total}**\n\n")
+    report.append("### Breakdown by Variety:\n")
+    
+    for variety, count in sorted(variety_counts.items(), key=lambda x: x[1], reverse=True):
+        percentage = (count / total) * 100
+        bar_length = int(percentage / 5)
+        bar = "█" * bar_length + "░" * (20 - bar_length)
+        report.append(f"- {variety}: {count}  ({percentage:.1f}%) {bar}\n")
+    
+    dominant_variety = max(variety_counts.items(), key=lambda x: x[1])[0]
+    report.append(f"\nDominant Variety: **{dominant_variety}**\n")
+    return "".join(report)
+
+def generate_csv_export(grain_details):
+    """
+    Convert grain detection results into CSV format for export.
+    """
+    if not grain_details:
+        return None
+    
+    df = pd.DataFrame(grain_details)
+    csv_buffer = BytesIO()
+    df.to_csv(csv_buffer, index=False)
+    csv_buffer.seek(0)
+    return csv_buffer.getvalue().decode()
+
+def analyze_rice_image(input_image):
+    """
+    Full analysis pipeline:
+    1. Detect grains
+    2. Classify each grain
+    3. Annotate image
+    4. Generate distribution report
+    5. Generate CSV export
+    """
+    if not models_loaded:
+        raise gr.Error("Analysis engine not available. Check model files.")
+    
+    if input_image is None:
+        raise gr.Error("Please upload an image to start analysis.")
+    
+    # Convert PIL image to BGR array for OpenCV
+    img_array = np.array(input_image)
+    img_bgr = cv2.cvtColor(img_array, cv2.COLOR_RGB2BGR)
+    
+    # Step 1: Detect grains
+    results = detection_model(img_bgr, verbose=False)[0]
+    boxes = results.boxes.xyxy.cpu().numpy()
+    
+    if len(boxes) == 0:
+        return (
+            Image.fromarray(cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)),
+            "No grains detected. Try a clearer image.",
+            None
+        )
+    
+    # Step 2: Classify grains
+    variety_counts = {v: 0 for v in VARIETY_MAP.values()}
+    grain_details = []
+    
+    for idx, box in enumerate(boxes):
+        x1, y1, x2, y2 = map(int, box[:4])
+        crop = img_bgr[y1:y2, x1:x2]
+        
+        if crop.shape[0] > 0 and crop.shape[1] > 0:
+            pil_crop = Image.fromarray(cv2.cvtColor(crop, cv2.COLOR_BGR2RGB))
+            variety_label = classify_grain(pil_crop)
+            variety_counts[variety_label] += 1
+            
+            # Save details for CSV export
+            grain_details.append({
+                "Grain_ID": f"G{idx+1:04d}",
+                "Variety": variety_label,
+                "X_center": (x1 + x2)//2,
+                "Y_center": (y1 + y2)//2
+            })
+            
+            # Annotate image
+            color = VARIETY_COLORS[variety_label]
+            cv2.rectangle(img_bgr, (x1, y1), (x2, y2), color, 3)
+            label = variety_label
+            (w, h), _ = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.7, 2)
+            cv2.rectangle(img_bgr, (x1, y1-h-10), (x1+w, y1), color, -1)
+            cv2.putText(img_bgr, label, (x1, y1-5), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (255,255,255), 2)
+    
+    # Step 3: Generate analytics report
+    report_text = generate_distribution_report(variety_counts)
+    csv_export = generate_csv_export(grain_details)
+    
+    return (
+        Image.fromarray(cv2.cvtColor(img_bgr, cv2.COLOR_BGR2RGB)),
+        report_text,
+        csv_export
+    )
+
+# ============================================
+# GRADIO USER INTERFACE
+# ============================================
+
+custom_css = """
+.gradio-container {
+    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+}
+.header-box {
+    background: linear-gradient(135deg, #1e5631 0%, #4c9a2a 100%);
+    padding: 25px;
+    border-radius: 12px;
+    color: white;
+    text-align: center;
+    margin-bottom: 20px;
+}
+"""
+
+with gr.Blocks(css=custom_css, title="Rice Classifier") as app:
+    
+    gr.HTML("""
+        <div class="header-box">
+            <h1>Rice Analyzer Pro</h1>
+            <p>Advanced Grain Classification | Rice Grain Locattor</p>
+        </div>
+    """)
+    
+    with gr.Tabs():
+        # Analysis Tab
+        with gr.Tab("Analysis"):
+            gr.Markdown("""
+            ### How to Use
+            1. Upload a clear image of rice grains.
+            2. Click "Start Analysis".
+            3. Review annotated results, distribution report, and export CSV.
+            
+            **Color Coding:** Red = C9 Premium, Blue = Kant Special, Green = Superfine Grade
+            """)
+            
+            with gr.Row():
+                with gr.Column(scale=1):
+                    image_input = gr.Image(type="pil", label="Sample Image")
+                    start_btn = gr.Button("Start Analysis", variant="primary", size="lg")
+                
+                #show the annotated image in specific width and height
+                with gr.Column(scale=1):
+                    annotated_output = gr.Image(label="Annotated Results", height=600, width=600)
+            
+            with gr.Row():
+                report_output = gr.Markdown(label="Distribution Report")
+            
+            with gr.Row():
+                csv_output = gr.Textbox(
+                    label="CSV Export (Copy or Save)",
+                    lines=8,
+                    max_lines=15,
+                )
+            
+            start_btn.click(
+                fn=analyze_rice_image,
+                inputs=image_input,
+                outputs=[annotated_output, report_output, csv_output]
+            )
+        
+        # Documentation Tab
+        with gr.Tab("Documentation"):
+            gr.Markdown("""
+            ## System Overview
+            
+            Rice Classifier uses a deep learning pipeline:
+            
+            1. **Grain Detection:** YOLO-based model identifies rice grains.
+            2. **Grain Classification:** ResNet50 model classifies grains into three varieties.
+            3. **CSV Export:** Detailed grain data available for download or copy.
+            
+            ### Supported Varieties
+            | Variety | Description |
+            |---------|-------------|
+            | C9 Premium | High-quality long grain |
+            | Kant Special | Medium grain specialty |
+            | Superfine Grade | Ultra-refined grain |
+            
+            ### Best Practices
+            - Use well-lit images without shadows
+            - Keep grains separated
+            - Use plain backgrounds
+            - Resolution: 1024x1024 or higher for best results
+            
+            ### Technical Details
+            - Detection: YOLOv8
+            - Classification: ResNet50 fine-tuned
+            - GPU recommended for faster processing
+            """)
+
+    gr.Markdown("---")
+    gr.Markdown("### Sample Gallery")
+    
+    gr.Examples(
+        examples=[
+            "samples/rice1.jpg",
+            "samples/rice2.jpg",
+            "samples/rice4.jpg",
+            "samples/rice5.jpg"
+        ],
+        inputs=image_input,
+        outputs=[annotated_output, report_output, csv_output],
+        fn=analyze_rice_image,
+        label="Click any sample to run analysis"
+    )
+
+if __name__ == "__main__":
+    app.queue()
+    app.launch()

best.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:517d391d3ea5a490c9ef00112d735d85086449a1e8e30840a58183997bec6e48
+size 5520595

requirements.txt

@@ -0,0 +1,8 @@
+numpy<2
+Pillow>=9.0.0
+gradio==3.50.2
+gradio-client==0.6.1
+torch>=2.0.0
+torchvision>=0.15.0
+ultralytics>=8.0.0
+opencv-python-headless>=4.7.0

rice_resnet_model.pth

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:789b26cc9b71852782ba037086806ef006c83f931ccd9a37e7ee65eb28ce5575
+size 94377562