import cv2
import torch
# Load YOLO model (replace with your chosen YOLO version)
model = [Link]('ultralytics/yolov5', 'yolov5s') # Example using yolov5s
#model = [Link]('ultralytics/yolov8', 'yolov8s') # Example using yolov8s
# Define classes to detect (e.g., "weapon", "person")
class_names = ["weapon", "person"] # Replace with your specific classes
# Load an image or video stream
#image_path = "path/to/your/[Link]"
#img = [Link](image_path)
cap = [Link](0) # 0 for default camera, or path to video
# Detection loop
while True:
ret, frame = [Link]()
if not ret:
break
# Convert to RGB for YOLO
img_rgb = [Link](frame, cv2.COLOR_BGR2RGB)
# Perform inference
results = model(img_rgb)
# Process results
for result in [Link][0]:
#result is a tensor with [x1, y1, x2, y2, confidence, class_id]
# Extract bounding box coordinates and class ID
x1, y1, x2, y2, confidence, class_id = [Link]()
# Convert to integer for drawing
x1, y1, x2, y2 = int(x1), int(y1), int(x2), int(y2)
class_id = int(class_id)
# Draw bounding box and label
[Link](frame, (x1, y1), (x2, y2), (0, 255, 0), 2)
label = f"{class_names[class_id]}: {confidence:.2f}"
[Link](frame, label, (x1, y1 - 10), cv2.FONT_HERSHEY_SIMPLEX, 0.7, (0, 255, 0),
2)
# Display the image/video
[Link]("Weapon Detection", frame)
# Break loop on 'q' key press
if [Link](1) & 0xFF == ord('q'):
break
# Clean up
[Link]()
[Link]()
Yolo
import numpy as np
import cv2
import imutils
import datetime
gun_cascade = [Link]('[Link]')
camera = [Link](0)
firstFrame = None
gun_exist = False
while True:
ret, frame = [Link]()
if frame is None:
break
frame = [Link](frame, width=500)
gray = [Link](frame, cv2.COLOR_BGR2GRAY)
gun = gun_cascade.detectMultiScale(gray, 1.3, 20, minSize=(100, 100))
if len(gun) > 0:
gun_exist = True
for (x, y, w, h) in gun:
frame = [Link](frame, (x, y), (x + w, y + h), (255, 0, 0), 2)
roi_gray = gray[y:y + h, x:x + w]
roi_color = frame[y:y + h, x:x + w]
if firstFrame is None:
firstFrame = gray
continue
[Link](frame, [Link]().strftime("%A %d %B %Y %I:%M:%S %p"),
(10, [Link][0] - 10),
cv2.FONT_HERSHEY_SIMPLEX,
0.35, (0, 0, 255), 1)
if gun_exist:
print("Guns detected")
[Link](frame)
break
else:
[Link]("Security Feed", frame)
key = [Link](1) & 0xFF
if key == ord('q'):
break
[Link]()
[Link]()
Jupytyer notebook
import os
import numpy as np
import [Link] as plt
import tensorflow as tf
from [Link] import ImageDataGenerator
from [Link] import MobileNetV2
from [Link] import Dense, GlobalAveragePooling2D, Dropout
from [Link] import Model
from [Link] import classification_report, confusion_matrix
Setup and import
IMAGE_SIZE = (224, 224)
BATCH_SIZE = 32
train_datagen = ImageDataGenerator(rescale=1./255,
rotation_range=20,
zoom_range=0.15,
width_shift_range=0.2,
height_shift_range=0.2,
shear_range=0.15,
horizontal_flip=True,
fill_mode="nearest")
val_test_datagen = ImageDataGenerator(rescale=1./255)
train_generator = train_datagen.flow_from_directory(
'dataset/train',
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode='binary'
)
val_generator = val_test_datagen.flow_from_directory(
'dataset/val',
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode='binary'
)
test_generator = val_test_datagen.flow_from_directory(
'dataset/test',
target_size=IMAGE_SIZE,
batch_size=BATCH_SIZE,
class_mode='binary',
shuffle=False
)
Data preprocessing
base_model = MobileNetV2(weights='imagenet', include_top=False, input_shape=(224, 224, 3))
base_model.trainable = False # Freeze base
x = base_model.output
x = GlobalAveragePooling2D()(x)
x = Dropout(0.5)(x)
predictions = Dense(1, activation='sigmoid')(x)
model = Model(inputs=base_model.input, outputs=predictions)
[Link](optimizer='adam', loss='binary_crossentropy', metrics=['accuracy'])
Build the model
history = [Link](
train_generator,
validation_data=val_generator,
epochs=10
)
Train the model
# Test accuracy
loss, accuracy = [Link](test_generator)
print(f'Test accuracy: {accuracy:.2f}')
# Predictions and confusion matrix
y_pred = [Link](test_generator)
y_pred_classes = (y_pred > 0.5).astype("int32").flatten()
y_true = test_generator.classes
print("Classification Report:")
print(classification_report(y_true, y_pred_classes, target_names=['Non-Weapon', 'Weapon']))
print("Confusion Matrix:")
print(confusion_matrix(y_true, y_pred_classes))
Evaluate the model
[Link]('weapon_detection_model.h5')
Save the model
