first working version

.gradio/certificate.pem

@@ -0,0 +1,31 @@
+-----BEGIN CERTIFICATE-----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=
+-----END CERTIFICATE-----

app.py

@@ -1,13 +1,197 @@
+import os
+import cv2
 import gradio as gr
+import numpy as np
+from PIL import Image
+import torch
+from ultralytics import YOLO
 
-def hello(image):
-    return "Coffee rust analysis coming soon!"
+############################################
+# Configuration
+############################################
+
+YOLO_MODEL_PATH = "clr_YOLOV8.pt"
+DEVICE = "cuda" if torch.cuda.is_available() else "cpu"
+
+############################################
+# Load YOLO Model
+############################################
+
+print("Loading YOLO model...")
+
+try:
+    yolo_model = YOLO(YOLO_MODEL_PATH)
+    print("YOLO model loaded.")
+except Exception as e:
+    yolo_model = None
+    print("YOLO loading error:", e)
+
+############################################
+# Helper Functions
+############################################
+
+def segment_rust_simple(leaf_img):
+    """
+    Simple rust segmentation using HSV color threshold.
+    Works as fallback when SAM is unavailable.
+    """
+
+    hsv = cv2.cvtColor(leaf_img, cv2.COLOR_BGR2HSV)
+
+    # Rust-like colors
+    lower = np.array([10, 80, 80])
+    upper = np.array([35, 255, 255])
+
+    mask = cv2.inRange(hsv, lower, upper)
+
+    kernel = np.ones((3,3), np.uint8)
+    mask = cv2.morphologyEx(mask, cv2.MORPH_OPEN, kernel)
+
+    return mask
+
+
+def calculate_leaf_area(leaf_img):
+    """
+    Estimate leaf pixels via threshold.
+    """
+    gray = cv2.cvtColor(leaf_img, cv2.COLOR_BGR2GRAY)
+    _, mask = cv2.threshold(gray, 10, 255, cv2.THRESH_BINARY)
+
+    return mask
+
+
+############################################
+# Main Processing Function
+############################################
+
+def process_coffee_leaf(image):
+
+    if image is None:
+        return None, "Upload an image."
+
+    if yolo_model is None:
+        return image, "YOLO model not loaded."
+
+    image_np = np.array(image)
+    image_cv = cv2.cvtColor(image_np, cv2.COLOR_RGB2BGR)
+
+    results = yolo_model(image_cv, verbose=False)
+
+    boxes = results[0].boxes.xyxy.cpu().numpy()
+
+    if len(boxes) == 0:
+        return image_np, "No leaves detected."
+
+    annotated = image_np.copy()
+
+    severities = []
+
+    h, w = image_cv.shape[:2]
+
+    for i, box in enumerate(boxes):
+
+        x1, y1, x2, y2 = box.astype(int)
+
+        x1, x2 = max(0, x1), min(w, x2)
+        y1, y2 = max(0, y1), min(h, y2)
+
+        leaf_crop = image_cv[y1:y2, x1:x2]
+
+        if leaf_crop.size == 0:
+            continue
+
+        ################################
+        # Leaf mask
+        ################################
+
+        leaf_mask = calculate_leaf_area(leaf_crop)
+        leaf_pixels = cv2.countNonZero(leaf_mask)
+
+        ################################
+        # Rust segmentation
+        ################################
+
+        rust_mask = segment_rust_simple(leaf_crop)
+        rust_pixels = cv2.countNonZero(rust_mask)
+
+        ################################
+        # Severity calculation
+        ################################
+
+        severity = 0
+
+        if leaf_pixels > 0:
+            severity = (rust_pixels / leaf_pixels) * 100
+
+        severities.append(f"Leaf {i+1}: {severity:.2f}%")
+
+        ################################
+        # Visualization
+        ################################
+
+        # draw leaf bbox
+        cv2.rectangle(annotated,(x1,y1),(x2,y2),(0,255,0),2)
+
+        cv2.putText(
+            annotated,
+            f"{severity:.1f}%",
+            (x1,y1-5),
+            cv2.FONT_HERSHEY_SIMPLEX,
+            0.6,
+            (0,255,0),
+            2
+        )
+
+        # resize rust mask to image coords
+        rust_mask = cv2.resize(
+            rust_mask,
+            (x2-x1, y2-y1),
+            interpolation=cv2.INTER_NEAREST
+        )
+
+        overlay = np.zeros_like(annotated)
+
+        overlay[y1:y2, x1:x2][rust_mask > 0] = [255,0,0]
+
+        alpha = 0.4
+        mask_indices = overlay[:,:,0] > 0
+
+        annotated[mask_indices] = (
+            annotated[mask_indices]*(1-alpha) +
+            overlay[mask_indices]*alpha
+        ).astype(np.uint8)
+
+    report = f"Detected {len(boxes)} leaves\n\n"
+    report += "\n".join(severities)
+
+    return annotated, report
+
+
+############################################
+# Gradio Interface
+############################################
 
 demo = gr.Interface(
-    fn=hello,
-    inputs=gr.Image(),
-    outputs="text",
-    title="Coffee Leaf Rust Severity Estimator"
+    fn=process_coffee_leaf,
+    inputs=gr.Image(type="pil", label="Upload Coffee Leaf Image"),
+    outputs=[
+        gr.Image(label="Analyzed Image"),
+        gr.Textbox(label="Severity Report")
+    ],
+    title="☕ Coffee Leaf Rust Severity Estimator",
+    description="""
+Upload a coffee leaf image.  
+The system detects leaves using YOLOv8 and estimates rust severity by segmenting rust-colored lesions.
+""",
 )
 
-demo.launch()
+
+############################################
+# Launch
+############################################
+
+if __name__ == "__main__":
+    demo.launch(
+        server_name="0.0.0.0",
+        server_port=7860
+    )

clr_YOLOV8.pt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2480dc0328856e904fabe1f695b7b583dfbf601eb91f54c0c2566237d7a515c9
+size 6758388

requirements.txt

@@ -1 +1,10 @@
-gradio
+gradio
+ultralytics
+torch
+torchvision
+numpy
+opencv-python
+pandas
+Pillow
+huggingface_hub
+sam3