modeller

crop_desease_detection.py

@@ -1,18 +1,3 @@
-# -*- coding: utf-8 -*-
-"""crop_desease_detection.ipynb
-
-Automatically generated by Colab.
-
-Original file is located at
-    https://colab.research.google.com/drive/1PCO8YxMl3tqzsbMVP1iiSylwED-u_VfW
-"""
-
-
-
-
-
-
-
 # Complete Pipeline for Tree Disease Detection with PDT Dataset
 
 # Cell 1: Install required packages
@@ -64,7 +49,7 @@ else:
     # Extract the zip file
     extract_path = '/content/PDT_dataset_extracted'
     os.makedirs(extract_path, exist_ok=True)
-
+    
     print(f"Extracting {zip_file_path} to {extract_path}")
     with zipfile.ZipFile(zip_file_path, 'r') as zip_ref:
         zip_ref.extractall(extract_path)
@@ -82,25 +67,25 @@ def explore_dataset_structure(base_path):
         'val_path': None,
         'test_path': None
     }
-
+    
     for root, dirs, files in os.walk(base_path):
         # Look for YOLO_txt directory
         if 'YOLO_txt' in root:
             dataset_info['yolo_txt_path'] = root
             print(f"Found YOLO_txt at: {root}")
-
+            
             # Check for train/val/test
             for split in ['train', 'val', 'test']:
                 split_path = os.path.join(root, split)
                 if os.path.exists(split_path):
                     dataset_info[f'{split}_path'] = split_path
                     print(f"Found {split} at: {split_path}")
-
+        
         # Look for VOC_xml directory
         if 'VOC_xml' in root:
             dataset_info['voc_xml_path'] = root
             print(f"Found VOC_xml at: {root}")
-
+    
     return dataset_info
 
 dataset_info = explore_dataset_structure('/content/PDT_dataset_extracted')
@@ -109,57 +94,57 @@ dataset_info = explore_dataset_structure('/content/PDT_dataset_extracted')
 def setup_yolo_dataset(dataset_info, output_dir='/content/PDT_yolo'):
     """Setup YOLO dataset from the extracted PDT dataset"""
     print(f"\nSetting up YOLO dataset to {output_dir}")
-
+    
     # Clean output directory
     if os.path.exists(output_dir):
         shutil.rmtree(output_dir)
     os.makedirs(output_dir, exist_ok=True)
-
+    
     # Create directory structure
     for split in ['train', 'val', 'test']:
         os.makedirs(os.path.join(output_dir, 'images', split), exist_ok=True)
         os.makedirs(os.path.join(output_dir, 'labels', split), exist_ok=True)
-
+    
     total_copied = 0
-
+    
     # Process each split
     for split in ['train', 'val', 'test']:
         split_path = dataset_info[f'{split}_path']
-
+        
         if not split_path or not os.path.exists(split_path):
             print(f"Warning: {split} split not found")
             continue
-
+        
         print(f"\nProcessing {split} from: {split_path}")
-
+        
         # Find images and labels directories
         img_dir = os.path.join(split_path, 'images')
         lbl_dir = os.path.join(split_path, 'labels')
-
+        
         if not os.path.exists(img_dir) or not os.path.exists(lbl_dir):
             print(f"Warning: Could not find images or labels for {split}")
             continue
-
+        
         # Copy images and labels
         img_files = [f for f in os.listdir(img_dir) if f.endswith(('.jpg', '.jpeg', '.png'))]
         print(f"Found {len(img_files)} images in {split}")
-
+        
         for img_file in img_files:
             # Copy image
             src_img = os.path.join(img_dir, img_file)
             dst_img = os.path.join(output_dir, 'images', split, img_file)
             shutil.copy2(src_img, dst_img)
-
+            
             # Copy corresponding label
             base_name = os.path.splitext(img_file)[0]
             txt_file = base_name + '.txt'
             src_txt = os.path.join(lbl_dir, txt_file)
             dst_txt = os.path.join(output_dir, 'labels', split, txt_file)
-
+            
             if os.path.exists(src_txt):
                 shutil.copy2(src_txt, dst_txt)
                 total_copied += 1
-
+    
     # Create data.yaml
     data_yaml_content = f"""# PDT dataset configuration
 path: {os.path.abspath(output_dir)}
@@ -172,14 +157,14 @@ names:
   0: unhealthy
 nc: 1
 """
-
+    
     yaml_path = os.path.join(output_dir, 'data.yaml')
     with open(yaml_path, 'w') as f:
         f.write(data_yaml_content)
-
+    
     print(f"\nDataset setup completed!")
     print(f"Total images copied: {total_copied}")
-
+    
     # Verify the dataset
     for split in ['train', 'val', 'test']:
         img_dir = os.path.join(output_dir, 'images', split)
@@ -188,7 +173,7 @@ nc: 1
             img_count = len([f for f in os.listdir(img_dir) if f.endswith(('.jpg', '.jpeg', '.png'))])
             lbl_count = len([f for f in os.listdir(lbl_dir) if f.endswith('.txt')])
             print(f"{split}: {img_count} images, {lbl_count} labels")
-
+    
     return yaml_path
 
 # Setup the dataset
@@ -252,10 +237,10 @@ axes = axes.ravel()
 
 for i, img_name in enumerate(val_images[:6]):
     img_path = os.path.join(val_img_dir, img_name)
-
+    
     # Run inference
     results = model(img_path, conf=0.25)
-
+    
     # Plot results
     img_with_boxes = results[0].plot()
     axes[i].imshow(cv2.cvtColor(img_with_boxes, cv2.COLOR_BGR2RGB))
@@ -273,7 +258,7 @@ plt.show()
 def detect_tree_disease(image_path, conf_threshold=0.25):
     """Detect unhealthy trees in an image"""
     results = model(image_path, conf=conf_threshold)
-
+    
     detections = []
     for result in results:
         boxes = result.boxes
@@ -285,7 +270,7 @@ def detect_tree_disease(image_path, conf_threshold=0.25):
                     'class': 'unhealthy'
                 }
                 detections.append(detection)
-
+    
     # Visualize
     img_with_boxes = results[0].plot()
     plt.figure(figsize=(12, 8))
@@ -293,7 +278,7 @@ def detect_tree_disease(image_path, conf_threshold=0.25):
     plt.axis('off')
     plt.title(f'Detected {len(detections)} unhealthy tree(s)')
     plt.show()
-
+    
     return detections
 
 # Cell 10: Save the model
@@ -307,19 +292,19 @@ from google.colab import drive
 
 try:
     drive.mount('/content/drive')
-
+    
     save_dir = '/content/drive/MyDrive/tree_disease_detection'
     os.makedirs(save_dir, exist_ok=True)
-
+    
     # Copy files
     shutil.copy(best_model_path, os.path.join(save_dir, 'best_model.pt'))
     shutil.copy(final_model_path, os.path.join(save_dir, 'tree_disease_detector.pt'))
-
+    
     # Copy training results
     results_png = 'runs/train/yolov8s_pdt/results.png'
     if os.path.exists(results_png):
         shutil.copy(results_png, os.path.join(save_dir, 'training_results.png'))
-
+    
     print(f"Results saved to Google Drive: {save_dir}")
 except:
     print("Google Drive not mounted. Results saved locally.")
@@ -333,269 +318,4 @@ print("The model is ready for tree disease detection!")
 
 # Test with your own image
 print("\nTo test with your own image:")
-print("detections = detect_tree_disease('path/to/your/image.jpg')")
-
-
-
-
-
-
-
-
-
-# Cell 1: Install Hugging Face Hub
-!pip install huggingface_hub
-
-# Cell 2: Login to Hugging Face
-from huggingface_hub import login, HfApi, create_repo
-import os
-import shutil
-
-# Login to Hugging Face (you'll need your token)
-# Get your token from: https://huggingface.co/settings/tokens
-login()
-
-# Cell 3: Prepare model files for upload
-# Create a directory for model files
-model_dir = "pdt_tree_disease_model"
-os.makedirs(model_dir, exist_ok=True)
-
-# Copy the trained model
-best_model_path = 'runs/train/yolov8s_pdt/weights/best.pt'
-if os.path.exists(best_model_path):
-    shutil.copy(best_model_path, os.path.join(model_dir, "best.pt"))
-
-# Copy the final saved model
-if os.path.exists('tree_disease_detector.pt'):
-    shutil.copy('tree_disease_detector.pt', os.path.join(model_dir, "tree_disease_detector.pt"))
-
-# Copy training results
-results_path = 'runs/train/yolov8s_pdt/results.png'
-if os.path.exists(results_path):
-    shutil.copy(results_path, os.path.join(model_dir, "training_results.png"))
-
-# Copy confusion matrix if exists
-confusion_matrix_path = 'runs/train/yolov8s_pdt/confusion_matrix.png'
-if os.path.exists(confusion_matrix_path):
-    shutil.copy(confusion_matrix_path, os.path.join(model_dir, "confusion_matrix.png"))
-
-# Copy other training plots
-for plot_file in ['F1_curve.png', 'P_curve.png', 'R_curve.png', 'PR_curve.png']:
-    plot_path = f'runs/train/yolov8s_pdt/{plot_file}'
-    if os.path.exists(plot_path):
-        shutil.copy(plot_path, os.path.join(model_dir, plot_file))
-
-# Cell 4: Create model card (README.md)
-model_card = """---
-tags:
-- object-detection
-- yolov8
-- tree-disease-detection
-- pdt-dataset
-library_name: ultralytics
-datasets:
-- qwer0213/PDT_dataset
-metrics:
-- mAP50
-- mAP50-95
----
-
-# YOLOv8 Tree Disease Detection Model
-
-This model is trained on the PDT (Pests and Diseases Tree) dataset for detecting unhealthy trees using YOLOv8.
-
-## Model Description
-
-- **Architecture**: YOLOv8s
-- **Task**: Object Detection (Tree Disease Detection)
-- **Classes**: 1 (unhealthy)
-- **Input Size**: 640x640
-- **Framework**: Ultralytics YOLOv8
-
-## Training Details
-
-- **Dataset**: PDT (Pests and Diseases Tree) dataset
-- **Training Images**: 4,536
-- **Validation Images**: 567
-- **Test Images**: 567
-- **Epochs**: 50
-- **Batch Size**: 16
-- **Optimizer**: SGD
-- **Learning Rate**: 0.01
-
-## Performance Metrics
-
-| Metric | Value |
-|--------|-------|
-| mAP50 | 0.xxx |
-| mAP50-95 | 0.xxx |
-| Precision | 0.xxx |
-| Recall | 0.xxx |
-
-## Usage
-
-```python
-from ultralytics import YOLO
-
-# Load model
-model = YOLO('tree_disease_detector.pt')
-
-# Run inference
-results = model('path/to/image.jpg')
-
-# Process results
-for result in results:
-    boxes = result.boxes
-    if boxes is not None:
-        for box in boxes:
-            confidence = box.conf[0]
-            bbox = box.xyxy[0].tolist()
-            print(f"Unhealthy tree detected with confidence: {confidence}")
-Dataset
-This model was trained on the PDT dataset, which contains high-resolution UAV images of trees with pest and disease annotations.
-Citation
-bibtex@dataset{pdt_dataset,
-  title={PDT: UAV Pests and Diseases Tree Dataset},
-  author={Zhou et al.},
-  year={2024},
-  publisher={HuggingFace}
-}
-License
-MIT License
-"""
-Fill in the actual metrics
-if 'metrics' in globals() and metrics is not None:
-model_card = model_card.replace('0.xxx', f'{metrics.box.map50:.3f}')
-model_card = model_card.replace('0.xxx', f'{metrics.box.map:.3f}')
-model_card = model_card.replace('0.xxx', f'{metrics.box.p.mean():.3f}')
-model_card = model_card.replace('0.xxx', f'{metrics.box.r.mean():.3f}')
-Save model card
-with open(os.path.join(model_dir, "README.md"), "w") as f:
-f.write(model_card)
-Cell 5: Create config file
-config_content = """# YOLOv8 Tree Disease Detection Configuration
-model_type: yolov8s
-task: detect
-nc: 1  # number of classes
-names: ['unhealthy']  # class names
-Input
-imgsz: 640
-Inference settings
-conf: 0.25  # confidence threshold
-iou: 0.45   # IoU threshold for NMS
-"""
-with open(os.path.join(model_dir, "config.yaml"), "w") as f:
-f.write(config_content)
-Cell 6: Push to Hugging Face Hub
-from huggingface_hub import HfApi
-Initialize API
-api = HfApi()
-Create repository (replace 'your-username' with your HuggingFace username)
-repo_id = "your-username/yolov8-tree-disease-detection"  # Change this!
-Create the repository
-try:
-create_repo(
-repo_id=repo_id,
-repo_type="model",
-exist_ok=True
-)
-print(f"Repository created: https://huggingface.co/{repo_id}")
-except Exception as e:
-print(f"Repository might already exist or error: {e}")
-Upload all files in the model directory
-api.upload_folder(
-folder_path=model_dir,
-repo_id=repo_id,
-repo_type="model",
-)
-print(f"Model uploaded successfully to: https://huggingface.co/{repo_id}")
-Cell 7: Create a simple inference script for users
-inference_script = """# Tree Disease Detection Inference
-from ultralytics import YOLO
-import cv2
-import matplotlib.pyplot as plt
-Download and load model from Hugging Face
-model = YOLO('https://huggingface.co/{}/resolve/main/tree_disease_detector.pt')
-def detect_tree_disease(image_path):
-# Run inference
-results = model(image_path, conf=0.25)
-# Process results
-detections = []
-for result in results:
-    boxes = result.boxes
-    if boxes is not None:
-        for box in boxes:
-            detection = {
-                'confidence': float(box.conf[0]),
-                'bbox': box.xyxy[0].tolist(),
-                'class': 'unhealthy'
-            }
-            detections.append(detection)
-
-# Visualize
-annotated_img = results[0].plot()
-plt.figure(figsize=(12, 8))
-plt.imshow(cv2.cvtColor(annotated_img, cv2.COLOR_BGR2RGB))
-plt.axis('off')
-plt.title(f'Detected {len(detections)} unhealthy tree(s)')
-plt.show()
-
-return detections
-Example usage
-if name == "main":
-detections = detect_tree_disease('path/to/your/image.jpg')
-print(f"Found {len(detections)} unhealthy trees")
-""".format(repo_id)
-with open(os.path.join(model_dir, "inference.py"), "w") as f:
-f.write(inference_script)
-Upload the inference script
-api.upload_file(
-path_or_fileobj=os.path.join(model_dir, "inference.py"),
-path_in_repo="inference.py",
-repo_id=repo_id,
-repo_type="model",
-)
-Cell 8: Create requirements.txt
-requirements = """ultralytics>=8.0.0
-torch>=2.0.0
-opencv-python>=4.8.0
-matplotlib>=3.7.0
-pillow>=10.0.0
-"""
-with open(os.path.join(model_dir, "requirements.txt"), "w") as f:
-f.write(requirements)
-Upload requirements
-api.upload_file(
-path_or_fileobj=os.path.join(model_dir, "requirements.txt"),
-path_in_repo="requirements.txt",
-repo_id=repo_id,
-repo_type="model",
-)
-print("\nModel successfully uploaded to Hugging Face!")
-print(f"View your model at: https://huggingface.co/{repo_id}")
-print("\nTo use your model:")
-print(f"model = YOLO('https://huggingface.co/{repo_id}/resolve/main/tree_disease_detector.pt')")
-
-## Steps to upload your model:
-
-1. **Get a Hugging Face token**:
-   - Go to https://huggingface.co/settings/tokens
-   - Create a new token with write permissions
-   - Copy the token
-
-2. **Replace placeholder values**:
-   - Change `your-username` to your actual Hugging Face username
-   - Update the metrics in the model card with actual values
-
-3. **Run the cells** in order
-
-## After uploading, others can use your model like this:
-
-```python
-from ultralytics import YOLO
-
-# Load model directly from Hugging Face
-model = YOLO('https://huggingface.co/your-username/yolov8-tree-disease-detection/resolve/main/tree_disease_detector.pt')
-
-# Run inference
-results = model('image.jpg')
+print("detections = detect_tree_disease('path/to/your/image.jpg')")