yolo.py

'''
PRE-REQUISITES:

Install the packages:

I am using opencv 3.4.2, intall it by using the below command. Use the same opencv version
pip install opencv-python==3.4.2

We also need numpy
pip install numpy

Install argparse
pip install argparse

Download the files from the below URLs and have it inside the folder yolo-coco:

https://github.com/pjreddie/darknet/blob/master/data/coco.names
https://github.com/pjreddie/darknet/blob/master/cfg/yolov3.cfg
https://pjreddie.com/media/files/yolov3.weights
'''

'''
You can run the file by using 

python yolo.py --image images/ipl.jpeg
'''


# importing the necessary packages
import numpy as np
import argparse
import time
import cv2
import os

# construct the argument parse and parse the arguments
ap = argparse.ArgumentParser()
ap.add_argument("-i", "--image", required=True,
	help="path to input image")
ap.add_argument("-c", "--confidence", type=float, default=0.5,
	help="minimum probability to filter weak detections, IoU threshold")
ap.add_argument("-t", "--threshold", type=float, default=0.3,
	help="threshold when applying non-maxima suppression")
args = vars(ap.parse_args())

# load the COCO class labels our YOLO model was trained on
labelsPath = 'yolo-coco\\coco.names'
LABELS = open(labelsPath).read().strip().split("\n")

# initialize a list of colors to represent each possible class label
COLORS = np.random.randint(0, 255, size=(len(LABELS), 3),
	dtype="uint8")

# paths to the YOLO weights and model configuration
weightsPath = 'yolo-coco\\yolov3.weights'
configPath = 'yolo-coco\\yolov3.cfg'

# load our YOLO object detector trained on COCO dataset (80 classes)
net = cv2.dnn.readNetFromDarknet(configPath, weightsPath)

# load our input image and grab its spatial dimensions
image = cv2.imread(args["image"])
(H, W) = image.shape[:2]

# determine only the *output* layer names that we need from YOLO
ln = net.getLayerNames()
ln = [ln[i[0] - 1] for i in net.getUnconnectedOutLayers()]

# construct a blob from the input image and then perform a forward
# pass of the YOLO object detector, giving us our bounding boxes and
# associated probabilities
blob = cv2.dnn.blobFromImage(image, 1 / 255.0, (416, 416),
	swapRB=True, crop=False)
net.setInput(blob)
layerOutputs = net.forward(ln)

# initialize our lists of detected bounding boxes, confidences, and
# class IDs, respectively
boxes = []
confidences = []
classIDs = []

# loop over each of the layer outputs
for output in layerOutputs:
	# loop over each of the detections
	for detection in output:
		# extract the class ID and confidence (i.e., probability) of
		# the current object detection
		scores = detection[5:]
		classID = np.argmax(scores)
		confidence = scores[classID]

		# filter out weak predictions by ensuring the detected
		# probability is greater than the minimum probability
		if confidence > args["confidence"]:
			# scale the bounding box coordinates back relative to the
			# size of the image, keeping in mind that YOLO actually
			# returns the center (x, y)-coordinates of the bounding
			# box followed by the boxes' width and height
			box = detection[0:4] * np.array([W, H, W, H])
			(centerX, centerY, width, height) = box.astype("int")

			# use the center (x, y)-coordinates to derive the top and
			# and left corner of the bounding box
			x = int(centerX - (width / 2))
			y = int(centerY - (height / 2))

			# update our list of bounding box coordinates, confidences,
			# and class IDs
			boxes.append([x, y, int(width), int(height)])
			confidences.append(float(confidence))
			classIDs.append(classID)

# apply non-maxima suppression to suppress weak, overlapping bounding boxes
idxs = cv2.dnn.NMSBoxes(boxes, confidences, args["confidence"],
	args["threshold"])

# ensure at least one detection exists
if len(idxs) > 0:
	# loop over the indexes we are keeping
	for i in idxs.flatten():
		# extract the bounding box coordinates
		(x, y) = (boxes[i][0], boxes[i][1])
		(w, h) = (boxes[i][2], boxes[i][3])

		# draw a bounding box rectangle and label on the image
		color = [int(c) for c in COLORS[classIDs[i]]]
		cv2.rectangle(image, (x, y), (x + w, y + h), color, 2)
		text = "{}: {:.4f}".format(LABELS[classIDs[i]], confidences[i])
		cv2.putText(image, text, (x, y - 5), cv2.FONT_HERSHEY_SIMPLEX,
			0.5, color, 2)

# show the output image
cv2.imshow("Image", image)
cv2.waitKey(0)