init

process_data.py

@@ -0,0 +1,84 @@
+import datetime
+import os
+import cv2
+import joblib
+import numpy as np
+from skimage.feature import hog
+from sklearn.svm import SVC
+from sklearn.model_selection import train_test_split, GridSearchCV
+from sklearn.metrics import classification_report, accuracy_score
+
+# Parameters for HOG
+hog_params = {
+    'orientations': 9,
+    'pixels_per_cell': (8, 8),
+    'cells_per_block': (2, 2),
+    'block_norm': 'L2-Hys'
+}
+
+# Path to your dataset (ensure it is extracted and organized into subfolders by class)
+dataset_dir = 'natural_images'  # update with your actual path
+
+# Prepare lists for features and labels
+features = []
+labels = []
+
+# Iterate over each class folder in the dataset
+for label in os.listdir(dataset_dir):
+    label_folder = os.path.join(dataset_dir, label)
+    if not os.path.isdir(label_folder):
+        continue
+    # Process each image in the folder
+    for file in os.listdir(label_folder):
+        file_path = os.path.join(label_folder, file)
+        # Read the image in grayscale
+        image = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
+        if image is None:
+            continue
+
+
+        # Resize the image to a fixed size (optional, adjust based on your dataset)
+        image = cv2.resize(image, (64, 64))
+
+        # Extract HOG features from the image
+        hog_features = hog(image, **hog_params)
+
+        features.append(hog_features)
+        labels.append(label)
+
+# Convert lists to NumPy arrays
+features = np.array(features)
+labels = np.array(labels)
+
+# Split the data into training and testing sets
+X_train, X_test, y_train, y_test = train_test_split(features, labels, test_size=0.2, random_state=42)
+
+param_grid = [
+   # {'kernel': ['linear'], 'C': [0.1, 1, 10, 100]},
+    {'kernel': ['poly'], 'C': [0.1, 1, 10, 100], 'degree': [2, 3, 4], 'gamma': ['scale', 'auto']},
+    {'kernel': ['rbf'], 'C': [0.1, 1, 10, 50, 100], 'gamma': ['scale', 'auto']},
+   #{'kernel': ['sigmoid'], 'C': [0.1, 1, 10, 100], 'gamma': ['scale', 'auto']}
+]
+
+svm_model = SVC(probability=True)
+grid_search = GridSearchCV(svm_model, param_grid, cv=5, n_jobs=-1, verbose=3)
+
+grid_search.fit(X_train, y_train)
+
+
+print("Best parameters found:", grid_search.best_params_)
+print("Best cross-validation score:", grid_search.best_score_)
+
+# Use the best estimator to predict on the test set
+best_model = grid_search.best_estimator_
+y_pred = best_model.predict(X_test)
+
+print("Test Accuracy:", accuracy_score(y_test, y_pred))
+print(classification_report(y_test, y_pred))
+
+# Evaluate the model on the test set
+y_pred = grid_search.predict(X_test)
+print("Accuracy:", accuracy_score(y_test, y_pred))
+
+# Save the trained model for later use
+joblib.dump(grid_search, f'svm_natural_images_model{datetime.UTC}.pkl')