使用opencv調用YOLOv3 tiny

#!/usr/bin/env python
# coding: utf-8

import cv2
import numpy as np
import matplotlib.pyplot as plt
from tqdm import tqdm_notebook as tqdm

confThreshold = 0.5  #Confidence threshold
nmsThreshold = 0.4   #Non-maximum suppression threshold
inpWidth = 320       #Width of network's input image
inpHeight = 320      #Height of network's input image

# Get the names of the output layers
def getOutputsNames(net):
    # Get the names of all the layers in the network
    layersNames = net.getLayerNames()
    # Get the names of the output layers, i.e. the layers with unconnected outputs
    return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]


# Draw the predicted bounding box
def drawPred(classId, conf, left, top, right, bottom):
    # Draw a bounding box.
    cv2.rectangle(frame, (left, top), (right, bottom), (0, 0, 255))
    
    label = '%.2f' % conf
        
    # Get the label for the class name and its confidence
    if classes:
        assert(classId < len(classes))
        label = '%s:%s' % (classes[classId], label)
 
    #Display the label at the top of the bounding box
    labelSize, baseLine = cv2.getTextSize(label, cv2.FONT_HERSHEY_SIMPLEX, 0.5, 1)
    top = max(top, labelSize[1])
    cv2.putText(frame, label, (left, top), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (255,255,255))


# Remove the bounding boxes with low confidence using non-maxima suppression
def postprocess(frame, outs):
    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]
 
    classIds = []
    confidences = []
    boxes = []
    # Scan through all the bounding boxes output from the network and keep only the
    # ones with high confidence scores. Assign the box's class label as the class with the highest score.
    classIds = []
    confidences = []
    boxes = []
    for out in outs:
        for detection in out:
            scores = detection[5:]
            classId = np.argmax(scores)
            confidence = scores[classId]
            if confidence > confThreshold:
                center_x = int(detection[0] * frameWidth)
                center_y = int(detection[1] * frameHeight)
                width = int(detection[2] * frameWidth)
                height = int(detection[3] * frameHeight)
                left = int(center_x - width / 2)
                top = int(center_y - height / 2)
                classIds.append(classId)
                confidences.append(float(confidence))
                boxes.append([left, top, width, height])
 
    # Perform non maximum suppression to eliminate redundant overlapping boxes with
    # lower confidences.
    indices = cv2.dnn.NMSBoxes(boxes, confidences, confThreshold, nmsThreshold)
    for i in indices:
        i = i[0]
        box = boxes[i]
        left = box[0]
        top = box[1]
        width = box[2]
        height = box[3]
        drawPred(classIds[i], confidences[i], left, top, left + width, top + height)

# Load names of classes
classesFile = "data/pig.names";
classes = None
with open(classesFile, 'rt') as f:
    classes = f.read().rstrip('\n').split('\n')
 
# Give the configuration and weight files for the model and load the network using them.
modelConfiguration = "cfg/yolov3-tiny-pig.cfg";
modelWeights = "backup/yolov3-tiny-pig_50000.weights";
 
net = cv2.dnn.readNetFromDarknet(modelConfiguration, modelWeights)
net.setPreferableBackend(cv2.dnn.DNN_BACKEND_OPENCV)
net.setPreferableTarget(cv2.dnn.DNN_TARGET_CPU)

video = cv2.VideoCapture('/home/xmj/mycipan3/卸豬臺/demo_none.mp4')

output_names = getOutputsNames(net)
for i in tqdm(range(200)):
    ret, frame = video.read()
    # Create a 4D blob from a frame.
    blob = cv2.dnn.blobFromImage(frame, 1/255, (inpWidth, inpHeight), [0,0,0], 1, crop=False)
 
    # Sets the input to the network
    net.setInput(blob)
 
    # Runs the forward pass to get output of the output layers
    outs = net.forward(output_names)
 
    # Remove the bounding boxes with low confidence
#     print(len(outs), outs)
    postprocess(frame, outs)
#     print(len(outs), outs)
    # Put efficiency information. The function getPerfProfile returns the 
    # overall time for inference(t) and the timings for each of the layers(in layersTimes)
    t, _ = net.getPerfProfile()
    label = 'Inference time: %.2f ms' % (t * 1000.0 / cv2.getTickFrequency())
    print(label)
    cv2.putText(frame, label, (0, 15), cv2.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 255))
#     plt.imshow(frame)
#     plt.show()