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
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 = 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 v2 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)

    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()
    
    if args.dataset == "pascal":
        inp_dim = 416
        num_classes = 20
        classes = load_classes('data/voc.names')
        weightsfile = 'yolo-voc.weights'
        cfgfile = "cfg/yolo-voc.cfg"

    
    elif args.dataset == "coco":
        inp_dim = 544
        num_classes = 80
        classes = load_classes('data/coco.names')
        weightsfile = 'yolo.weights'
        cfgfile = "cfg/yolo.cfg" 
        
    else: 
        print("Invalid dataset")
        exit()

        
    stride = 32

    CUDA = torch.cuda.is_available()
    
    bbox_attrs = 5 + num_classes
    
    print("Loading network.....")
    model = Darknet(cfgfile)
    model.load_weights(weightsfile)
    print("Network successfully loaded")
    num_anchors = len(model.anchors)

    
    if CUDA:
        model.cuda()
        
    model(get_test_input(inp_dim, 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()
            
            
            output = model(Variable(img, volatile = True)).data
            output = predict_transform(output, inp_dim, stride, model.anchors, num_classes, confidence, CUDA)
           
            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 = output.float()
            

            
            output = write_results(output, num_classes, nms = True, nms_conf = nms_thresh)
        
            output[:,1:5] = torch.clamp(output[:,1:5], 0.0, float(inp_dim))
            
            im_dim = im_dim.repeat(output.size(0), 1)/inp_dim
            output[:,1:5] *= im_dim
            
            classes = load_classes('data/voc.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