Implement to Python for Darknet/YOLO model using DNN module. Sample code

Python-Darknet-DNN-Sample.py

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

target_model = "yolov3-tiny-janken_final.weights"
target_config = "yolov3-tiny-janken.cfg"

import cv2 as cv
import numpy as np

MODEL = "./janken_cfg/" + target_model
CFG = "./janken_cfg/" + target_config
SCALE = 0.00392   ##1/255
INP_SHAPE = (416, 416) #input size
MEAN = 0
RGB = True

# Load a network
net = cv.dnn.readNetFromDarknet(CFG, MODEL)
net.setPreferableBackend(cv.dnn.DNN_BACKEND_DEFAULT)
##net.setPreferableTarget(cv.dnn.DNN_TARGET_CPU)
net.setPreferableTarget(cv.dnn.DNN_TARGET_MYRIAD)

confThreshold = 0.8 # Confidence threshold
nmsThreshold = 0.8  # Non-maximum supression threshold

class_names = ['active', 'goo', 'choki', 'pa', 'won', 'lose', 'draw']

def getOutputsNames(net):
    layersNames = net.getLayerNames()
    return [layersNames[i[0] - 1] for i in net.getUnconnectedOutLayers()]

def postprocess(frame, outs):
    frameHeight = frame.shape[0]
    frameWidth = frame.shape[1]

    def drawPred(classId, conf, left, top, right, bottom):
        left = int(left)
        top = int(top)
        right = int(right)
        bottom = int(bottom)
        # Draw a bounding box.
        cv.rectangle(frame, (left, top), (right, bottom), (0, 255, 0))

        label = class_names[classId] + '_%.2f' % conf

        labelSize, baseLine = cv.getTextSize(label, cv.FONT_HERSHEY_SIMPLEX, 0.5, 1)
        top = max(top, labelSize[1])
        cv.rectangle(frame, (left, top - labelSize[1]), (left + labelSize[0], top + baseLine), (255, 255, 255), cv.FILLED)
        cv.putText(frame, label, (left, top), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 0, 0))

    layerNames = net.getLayerNames()
    lastLayerId = net.getLayerId(layerNames[-1])
    lastLayer = net.getLayer(lastLayerId)

    classIds = []
    confidences = []
    boxes = []

    if lastLayer.type == 'Region':
        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 = center_x - width / 2
                    top = center_y - height / 2
                    classIds.append(classId)
                    confidences.append(float(confidence))
                    boxes.append([left, top, width, height])
    else:
        print('Unknown output layer type: ' + lastLayer.type)
        exit()

    indices = cv.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)

c = cv.VideoCapture(0)
c.set(cv.CAP_PROP_FRAME_WIDTH, 640) # カメラ画像の横幅を1280に設定
c.set(cv.CAP_PROP_FRAME_HEIGHT, 480) # カメラ画像の縦幅を720に設定
c.read()

r, frame = c.read()

frameHeight = frame.shape[0]
frameWidth = frame.shape[1]
# Create a 4D blob from a frame.
inpWidth = INP_SHAPE[0]
inpHeight = INP_SHAPE[1]
blob = cv.dnn.blobFromImage(frame, SCALE, (inpWidth, inpHeight), MEAN, RGB, crop=False)
   
# Run a model
net.setInput(blob)
outs = net.forward(getOutputsNames(net))
   
##print(outs)
postprocess(frame, outs)
# Put efficiency information.
t, _ = net.getPerfProfile()
label = 'Inference time: %.2f ms' % (t * 1000.0 / cv.getTickFrequency())
cv.putText(frame, label, (0, 15), cv.FONT_HERSHEY_SIMPLEX, 0.5, (0, 255, 0))
#対象ファイルコピー保存
target_filepath = './result.jpg'
cv.imwrite(target_filepath, frame)