LoginSignup
9
17

More than 3 years have passed since last update.

@KEy2376(key)

YOLOv3　をwindows10で動かす

Last updated at Posted at 2019-06-24

背景

Googleやfacebookなどで使用されているGANやYOLOやVSLAMなど気になる技術が増えてきました。そこでまずYOLOを実際に手元で動かしてみました。結論、PCスペックが低い為重かったですがプログラム自体の稼働は正常確認する事ができました。機会があればスペックを高めにしたPCを用意し再度コードを流してみたいと思います。

開発環境

win10
x201

ステップ１管理者権限　anaconda設定した仮想環境を起動

まずwindowsのコマンドプロンプトを管理者権限で開きます。

activate yolo_v3

上記コマンドにより、作成したアナコンダ仮想環境に入ることができます。yolo_v3の部分はご自身で設定したanacondaナビゲータで設定した名前に変更してください。

ステップ２　ライブラリインポート

以下３つのライブラリをインポートしてください。

command
conda install pandas opencv
conda install pytorch torchvision -c pytorch
pip install matplotlib cython

ステップ３　Yolov3インストール及び詳細設定

以下gitから　緑のボタンを押してファイルをデスクトップにダウンロードしましょう。
https://github.com/ayooshkathuria/pytorch-yolo-v3.git
098.jpg

ダウンロードが終了したらもう１ファイル
以下サイトから　yolov3.weights　ファイルをデスクトップにダウンロードしましょう。

command
https://pjreddie.com/media/files/yolov3.weights

yolov3.weightsのダウンロードが終わりましたら、
pytorch-yolo-v3-masterフォルダの中にyolov3.weightsを格納してください。

ステップ４　動画ファイルを格納

動画認識したいあなたのサンプル動画をsamplemovie.mp4という名前で
pytorch-yolo-v3-masterの中に保存してください。

ステップ５　YOLOv3の実行

以下コマンドでYOLOを立ち上げてください。

command
C:\github\pytorch-yolo-v3>python video_demo.py --video samplemovie.mp4

実際のソースは以下になります。

video_demo.py
from __future__ import division
import time
import torch 
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import cv2 
from util import *
from darknet import Darknet
from preprocess import prep_image, inp_to_image, letterbox_image
import pandas as pd
import random 
import pickle as pkl
import argparse


def get_test_input(input_dim, CUDA):
    img = cv2.imread("dog-cycle-car.png")
    img = cv2.resize(img, (input_dim, input_dim)) 
    img_ =  img[:,:,::-1].transpose((2,0,1))
    img_ = img_[np.newaxis,:,:,:]/255.0
    img_ = torch.from_numpy(img_).float()
    img_ = Variable(img_)

    if CUDA:
        img_ = img_.cuda()

    return img_

def prep_image(img, inp_dim):
    """
    Prepare image for inputting to the neural network. 

    Returns a Variable 
    """

    orig_im = img
    dim = orig_im.shape[1], orig_im.shape[0]
    img = (letterbox_image(orig_im, (inp_dim, inp_dim)))
    img_ = img[:,:,::-1].transpose((2,0,1)).copy()
    img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
    return img_, orig_im, dim

def write(x, img):
    c1 = tuple(x[1:3].int())
    c2 = tuple(x[3:5].int())
    cls = int(x[-1])
    label = "{0}".format(classes[cls])
    color = random.choice(colors)
    cv2.rectangle(img, c1, c2,color, 1)
    t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 1 , 1)[0]
    c2 = c1[0] + t_size[0] + 3, c1[1] + t_size[1] + 4
    cv2.rectangle(img, c1, c2,color, -1)
    cv2.putText(img, label, (c1[0], c1[1] + t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1, [225,255,255], 1);
    return img

def arg_parse():
    """
    Parse arguements to the detect module

    """


    parser = argparse.ArgumentParser(description='YOLO v3 Video Detection Module')

    parser.add_argument("--video", dest = 'video', help = 
                        "Video to run detection upon",
                        default = "video.avi", type = str)
    parser.add_argument("--dataset", dest = "dataset", help = "Dataset on which the network has been trained", default = "pascal")
    parser.add_argument("--confidence", dest = "confidence", help = "Object Confidence to filter predictions", default = 0.5)
    parser.add_argument("--nms_thresh", dest = "nms_thresh", help = "NMS Threshhold", default = 0.4)
    parser.add_argument("--cfg", dest = 'cfgfile', help = 
                        "Config file",
                        default = "cfg/yolov3.cfg", type = str)
    parser.add_argument("--weights", dest = 'weightsfile', help = 
                        "weightsfile",
                        default = "yolov3.weights", type = str)
    parser.add_argument("--reso", dest = 'reso', help = 
                        "Input resolution of the network. Increase to increase accuracy. Decrease to increase speed",
                        default = "416", type = str)
    return parser.parse_args()


if __name__ == '__main__':
    args = arg_parse()
    confidence = float(args.confidence)
    nms_thesh = float(args.nms_thresh)
    start = 0

    CUDA = torch.cuda.is_available()

    num_classes = 80

    CUDA = torch.cuda.is_available()

    bbox_attrs = 5 + num_classes

    print("Loading network.....")
    model = Darknet(args.cfgfile)
    model.load_weights(args.weightsfile)
    print("Network successfully loaded")

    model.net_info["height"] = args.reso
    inp_dim = int(model.net_info["height"])
    assert inp_dim % 32 == 0 
    assert inp_dim > 32

    if CUDA:
        model.cuda()

    model(get_test_input(inp_dim, CUDA), CUDA)

    model.eval()

    videofile = args.video

    cap = cv2.VideoCapture(videofile)

    assert cap.isOpened(), 'Cannot capture source'

    frames = 0
    start = time.time()    
    while cap.isOpened():

        ret, frame = cap.read()
        if ret:


            img, orig_im, dim = prep_image(frame, inp_dim)

            im_dim = torch.FloatTensor(dim).repeat(1,2)                        


            if CUDA:
                im_dim = im_dim.cuda()
                img = img.cuda()

            with torch.no_grad():   
                output = model(Variable(img), CUDA)
            output = write_results(output, confidence, num_classes, nms = True, nms_conf = nms_thesh)

            if type(output) == int:
                frames += 1
                print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))
                cv2.imshow("frame", orig_im)
                key = cv2.waitKey(1)
                if key & 0xFF == ord('q'):
                    break
                continue




            im_dim = im_dim.repeat(output.size(0), 1)
            scaling_factor = torch.min(inp_dim/im_dim,1)[0].view(-1,1)

            output[:,[1,3]] -= (inp_dim - scaling_factor*im_dim[:,0].view(-1,1))/2
            output[:,[2,4]] -= (inp_dim - scaling_factor*im_dim[:,1].view(-1,1))/2

            output[:,1:5] /= scaling_factor

            for i in range(output.shape[0]):
                output[i, [1,3]] = torch.clamp(output[i, [1,3]], 0.0, im_dim[i,0])
                output[i, [2,4]] = torch.clamp(output[i, [2,4]], 0.0, im_dim[i,1])

            classes = load_classes('data/coco.names')
            colors = pkl.load(open("pallete", "rb"))

            list(map(lambda x: write(x, orig_im), output))


            cv2.imshow("frame", orig_im)
            key = cv2.waitKey(1)
            if key & 0xFF == ord('q'):
                break
            frames += 1
            print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))


        else:
            break

補足　動画ではなくカメラを利用したい時

いきなりcam_demo.py　ファイルを実行すると以下のようなエラーが発生します。

command
python cam_demo.py

Traceback (most recent call last):
  File "cam_demo.py", line 123, in <module>
    im_dim = im_dim.cuda()
NameError: name 'im_dim' is not defined

119 行目(cam_demo.py)がコメントアウトされていますのでここを有効に変更するとカメラ入力が有効になります。
ターゲットは以下になります。

command
im_dim = torch.FloatTensor(dim).repeat(1,2)

ちなみにcam_demo.pyは以下となりますので参考にしてください。

cam_demo.py
from __future__ import division
import time
import torch 
import torch.nn as nn
from torch.autograd import Variable
import numpy as np
import cv2 
from util import *
from darknet import Darknet
from preprocess import prep_image, inp_to_image
import pandas as pd
import random 
import argparse
import pickle as pkl

def get_test_input(input_dim, CUDA):
    img = cv2.imread("imgs/messi.jpg")
    img = cv2.resize(img, (input_dim, input_dim)) 
    img_ =  img[:,:,::-1].transpose((2,0,1))
    img_ = img_[np.newaxis,:,:,:]/255.0
    img_ = torch.from_numpy(img_).float()
    img_ = Variable(img_)

    if CUDA:
        img_ = img_.cuda()

    return img_

def prep_image(img, inp_dim):
    """
    Prepare image for inputting to the neural network. 

    Returns a Variable 
    """

    orig_im = img
    dim = orig_im.shape[1], orig_im.shape[0]
    img = cv2.resize(orig_im, (inp_dim, inp_dim))
    img_ = img[:,:,::-1].transpose((2,0,1)).copy()
    img_ = torch.from_numpy(img_).float().div(255.0).unsqueeze(0)
    return img_, orig_im, dim

def write(x, img):
    c1 = tuple(x[1:3].int())
    c2 = tuple(x[3:5].int())
    cls = int(x[-1])
    label = "{0}".format(classes[cls])
    color = random.choice(colors)
    cv2.rectangle(img, c1, c2,color, 1)
    t_size = cv2.getTextSize(label, cv2.FONT_HERSHEY_PLAIN, 1 , 1)[0]
    c2 = c1[0] + t_size[0] + 3, c1[1] + t_size[1] + 4
    cv2.rectangle(img, c1, c2,color, -1)
    cv2.putText(img, label, (c1[0], c1[1] + t_size[1] + 4), cv2.FONT_HERSHEY_PLAIN, 1, [225,255,255], 1);
    return img

def arg_parse():
    """
    Parse arguements to the detect module

    """


    parser = argparse.ArgumentParser(description='YOLO v3 Cam Demo')
    parser.add_argument("--confidence", dest = "confidence", help = "Object Confidence to filter predictions", default = 0.25)
    parser.add_argument("--nms_thresh", dest = "nms_thresh", help = "NMS Threshhold", default = 0.4)
    parser.add_argument("--reso", dest = 'reso', help = 
                        "Input resolution of the network. Increase to increase accuracy. Decrease to increase speed",
                        default = "160", type = str)
    return parser.parse_args()



if __name__ == '__main__':
    cfgfile = "cfg/yolov3.cfg"
    weightsfile = "yolov3.weights"
    num_classes = 80

    args = arg_parse()
    confidence = float(args.confidence)
    nms_thesh = float(args.nms_thresh)
    start = 0
    CUDA = torch.cuda.is_available()




    num_classes = 80
    bbox_attrs = 5 + num_classes

    model = Darknet(cfgfile)
    model.load_weights(weightsfile)

    model.net_info["height"] = args.reso
    inp_dim = int(model.net_info["height"])

    assert inp_dim % 32 == 0 
    assert inp_dim > 32

    if CUDA:
        model.cuda()

    model.eval()

    videofile = 'video.avi'

    cap = cv2.VideoCapture(0)

    assert cap.isOpened(), 'Cannot capture source'

    frames = 0
    start = time.time()    
    while cap.isOpened():

        ret, frame = cap.read()
        if ret:

            img, orig_im, dim = prep_image(frame, inp_dim)

#            im_dim = torch.FloatTensor(dim).repeat(1,2)                        


            if CUDA:
                im_dim = im_dim.cuda()
                img = img.cuda()


            output = model(Variable(img), CUDA)
            output = write_results(output, confidence, num_classes, nms = True, nms_conf = nms_thesh)

            if type(output) == int:
                frames += 1
                print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))
                cv2.imshow("frame", orig_im)
                key = cv2.waitKey(1)
                if key & 0xFF == ord('q'):
                    break
                continue



            output[:,1:5] = torch.clamp(output[:,1:5], 0.0, float(inp_dim))/inp_dim

#            im_dim = im_dim.repeat(output.size(0), 1)
            output[:,[1,3]] *= frame.shape[1]
            output[:,[2,4]] *= frame.shape[0]


            classes = load_classes('data/coco.names')
            colors = pkl.load(open("pallete", "rb"))

            list(map(lambda x: write(x, orig_im), output))


            cv2.imshow("frame", orig_im)
            key = cv2.waitKey(1)
            if key & 0xFF == ord('q'):
                break
            frames += 1
            print("FPS of the video is {:5.2f}".format( frames / (time.time() - start)))


        else:
            break

※ref　
https://qiita.com/daiarg/items/03c55c82fdc6e623bf07
https://qiita.com/goodboy_max/items/b75bb9eea52831fcdf15

9
17
2

Register as a new user and use Qiita more conveniently

  1. You get articles that match your needs
  2. You can efficiently read back useful information
  3. You can use dark theme
What you can do with signing up
Sign upLogin
9
17