[목표 검출] faster - rcnn demo. py 분석

#!/usr/bin/env python

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""
Demo script showing detections in sample images.

See README.md for installation instructions before running.
"""

import _init_paths
from fast_rcnn.config import cfg
from fast_rcnn.test import im_detect
from fast_rcnn.nms_wrapper import nms
from utils.timer import Timer
import matplotlib.pyplot as plt  #          
import numpy as np  # numpy:      
import scipy.io as sio  # scipy.io： matlab mat         (     )
import caffe, os, sys, cv2
import argparse  # argparse： python                 

# CLASSES = ('__background__',
#           '10', '16', '17', '20',
#           '22', '23', '30')
CLASSES = ('__background__',  #   +       
           'car', 'truck')
'''   vgg16   demo.py     ,   ./demo.py --net vgg16
VGG16   ，       , .caffemodel      model   
'''
NETS = {'vgg16': ('VGG16',
                  'VGG16_faster_rcnn_final.caffemodel'),
        'vgg_m': ('VGG_CNN_M_1024',
                  'VGG_CNN_M_1024_faster_rcnn_final.caffemodel'),
        'zf': ('ZF',
               'ZF_faster_rcnn_final.caffemodel')}


def vis_detections(im, class_name, dets, thresh=0.5):
    """Draw detected bounding boxes."""
    inds = np.where(dets[:, -1] >= thresh)[0]  #               
    if len(inds) == 0:
        return

    im = im[:, :, (2, 1, 0)]
    fig, ax = plt.subplots(figsize=(12, 12))
    ax.imshow(im, aspect='equal')
    for i in inds:
        bbox = dets[i, :4]  #     （Xmin,Ymin,Xmax,Ymax）
        score = dets[i, -1]  #      
        # bbox[0]:x, bbox[1]:y, bbox[2]:x+w, bbox[3]:y+h
        ax.add_patch(
            plt.Rectangle((bbox[0], bbox[1]),
                          bbox[2] - bbox[0],
                          bbox[3] - bbox[1], fill=False,
                          edgecolor='red', linewidth=3.5)
        )
        ax.text(bbox[0], bbox[1] - 2,
                '{:s} {:.3f}'.format(class_name, score),
                bbox=dict(facecolor='blue', alpha=0.5),
                fontsize=14, color='white')

    ax.set_title(('{} detections with '
                  'p({} | box) >= {:.1f}').format(class_name, class_name,
                                                  thresh),
                 fontsize=14)
    plt.axis('off')
    plt.tight_layout()
    plt.draw()


def demo(net, image_name):
    #      ，        
    """Detect object classes in an image using pre-computed object proposals."""

    # Load the demo image
    # im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)#    
    im_file = image_name
    # print(im_file)
    # print('
')
    im = cv2.imread(im_file)  #     
    # cv2.imshow("1",im)
    # cv2.waitKey()
    # Detect all object classes and regress object bounds
    timer = Timer()  # time.time()      
    timer.tic()  #       ， 'time.py' 
    scores, boxes = im_detect(net, im)  #   ，           
    timer.toc()  #       ，'time.py'   
    print ('Detection took {:.3f}s for '
           '{:d} object proposals').format(timer.total_time, boxes.shape[0])

    # Visualize detections for each class
    CONF_THRESH = 0.5  #      
    # CONF_THRESH = 0.7
    NMS_THRESH = 0.2  #          
    for cls_ind, cls in enumerate(CLASSES[1:]):  # enumerate:               
        cls_ind += 1  # because we skipped background ， cls_ind:  ，cls:  
        cls_boxes = boxes[:, 4 * cls_ind:4 * (cls_ind + 1)]  #       
        cls_scores = scores[:, cls_ind]  #       
        dets = np.hstack((cls_boxes,  # hstack:  ，    
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH)  #     


def parse_args():  #   demo.py   ,  
    """Parse input arguments."""
    parser = argparse.ArgumentParser(description='Faster R-CNN demo')
    parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
                        default=0, type=int)  #    GPU 0
    parser.add_argument('--cpu', dest='cpu_mode',
                        help='Use CPU mode (overrides --gpu)',
                        action='store_true')
    parser.add_argument('--net', dest='demo_net', help='Network to use [vgg16]',
                        choices=NETS.keys(), default='vgg16')  #    vgg16

    args = parser.parse_args()

    return args


if __name__ == '__main__':
    cfg.TEST.HAS_RPN = True  # Use RPN for proposals

    args = parse_args()
    #     ，  prototxt  
    prototxt = os.path.join(cfg.MODELS_DIR, NETS[args.demo_net][0],
                            'faster_rcnn_alt_opt', 'faster_rcnn_test.pt')
    caffemodel = os.path.join(cfg.DATA_DIR, 'faster_rcnn_models',
                              NETS[args.demo_net][1])

    if not os.path.isfile(caffemodel):
        raise IOError(('{:s} not found.
Did you run ./data/script/'
                       'fetch_faster_rcnn_models.sh?').format(caffemodel))

    if args.cpu_mode:
        caffe.set_mode_cpu()
    else:
        caffe.set_mode_gpu()
        caffe.set_device(args.gpu_id)
        cfg.GPU_ID = args.gpu_id
    net = caffe.Net(prototxt, caffemodel, caffe.TEST)  #     

    print '

Loaded network {:s}'.format(caffemodel)

    # Warmup on a dummy image
    im = 128 * np.ones((300, 500, 3), dtype=np.uint8)
    for i in xrange(2):
        _, _ = im_detect(net, im)  #    
    #     ， txt      
    f = open("./resize.txt")
    lines = f.readlines()
    for line in lines:
        line = line[:-2] + ".jpg"  #          windows    ，   \r
，   -2
        # line=line[:-1]
        line = os.path.join("/home/txl/Data/resize", line)#            
        print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
        print 'Demo for {}'.format(line)
        demo(net, line)
    plt.show()"""    """

    """
    im_names = ['1.jpg', '2.jpg','3.jpg','4.jpg','5.jpg','6.jpg','DJI_0269.JPG','DJI_0178.JPG']
    for im_name in im_names:
        print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
        print 'Demo for data/demo/{}'.format(im_name)
        demo(net, im_name)
    plt.show()
    """