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 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, classes, your_class):
    c1 = tuple(x[1:3].int())
    c2 = tuple(x[3:5].int())
    cls = int(x[-1])
    label = "{0}".format(classes[cls])
    if label in your_class:
        color = (0,255,0)
        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 yolo_output(frame, model, your_class, confidence, nms_thesh, CUDA, inp_dim):
    num_classes = 80
    bbox_attrs = 5 + num_classes
    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)



    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')


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

    return orig_im

if __name__ == '__main__':

    cfgfile = "cfg/yolov3.cfg"
    weightsfile = "yolov3.weights"
    confidence = 0.25
    nms_thesh = 0.4
    CUDA = torch.cuda.is_available()
    model = Darknet(cfgfile)
    model.load_weights(weightsfile)

    model.net_info["height"] = 160
    inp_dim = int(model.net_info["height"])

    assert inp_dim % 32 == 0
    assert inp_dim > 32

    if CUDA:
        model.cuda()

    model.eval()

    videofile = '/home/rex/Videos/Webcam/2019-09-02-164142.webm'
    videofile = 0
    cap = cv2.VideoCapture(videofile)

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

    frames = 0
    start = time.time()
    while(1):

        ret, frame = cap.read()
        img = yolo_output(frame,model,['cell phone', 'person'], confidence, nms_thesh, CUDA, inp_dim)
        cv2.imshow("frame", img)
        key = cv2.waitKey(1)
        if key & 0xFF == ord('q'):
            break
        frames += 1
            # print("FPS of the video is {:5.2f}".format( frames / (time.time() )))