docker 下配置Faster RCNN

dockers安装和Nvidia-docker安装

Ubuntu从头开始使用Docker运行OpenPose

获取镜像

找到一个合适的dockers
https://hub.docker.com/r/jimmyli/faster-rcnn-gpu
Dockerfile 修改sources.list源

docker pull jimmyli/faster-rcnn-gpu

镜像创建好了之后在用docker run命令建立容器

创建容器

这是docker hub上写的方法，是有问题的，因为英伟达docker改版了

sudo nvidia-docker run --rm -it jimmyli/faster-rcnn-gpu /bin/bash 

要改成

docker run --gpus all --shm-size 16g -v $(pwd)/sharedfolder:/code_current -v /data/:/data/ -p 6006:6006  -t -i jimmyli/faster-rcnn-gpu /bin/bash

docker run 命令大全

安装Faster RCNN

https://github.com/rbgirshick/py-faster-rcnn

# 训练自Pascal VOC Dataset的模型
cd /workspace/py-faster-rcnn/tools/ python demo.py
# 训练自COCO的模型
python demo_coco.py

改编demo

改进demo函数，实现：

1. 在data/demo文件夹下放如图片就可以运行，运行结果放入tools/demo_results。
2. 可选择是否输出画框的图片使用命令–draw
3. 输出json结果在tools/demo_results

def demo(net, image_name, args):
    """Detect object classes in an image using pre-computed object proposals."""
    all_data = []
    thresh = 0.5
    # Load the demo image
    im_file = os.path.join(cfg.DATA_DIR, 'demo', image_name)
    im = cv2.imread(im_file)

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(net, im)
    timer.toc()
    print ('Detection took {:.3f}s for '
           '{:d} object proposals').format(timer.total_time, boxes.shape[0])

    # Visualize detections for each class
    CONF_THRESH = 0.8
    NMS_THRESH = 0.3
    for cls_ind, cls in enumerate(CLASSES[1:]):
        cls_ind += 1 # because we skipped background
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        dets = np.hstack((cls_boxes,
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        inds = np.where(dets[:, -1] >= thresh)[0]  # 选框置信度大于0.5的才导入数据
        if len(inds) != 0:
            json_data = {'dets': str(dets), 'image_name': image_name, 'class': cls}
            all_data.append(json_data)
        if args.draw_boxes:
            vis_detections(im, cls, dets, image_name, thresh=CONF_THRESH)
    return all_data

def parse_args():
    """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)
    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')
    parser.add_argument('--draw', dest='draw_boxes', help='Draw detected bounding boxes yes or no',
                        action='store_true',
                        default=False)  # 增加选项，是否输出画框后的图像
    args = parser.parse_args()
    return args

# 开头加入下面代码，用来显示中文
# -*- coding: UTF-8 -*-
# 改进MAIN下面的代码
if __name__ == '__main__':

    cfg.TEST.HAS_RPN = True  # Use RPN for proposals

    args = parse_args()

    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.\nDid 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('\n\nLoaded 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)
    print(cfg.DATA_DIR+'/demo')
    
    # 改进为可以直接在py-faster-rcnn/data/demo下放入想要检测的图片，运行结果在py-faster-rcnn/tools/demo_results下
    images_dir = os.listdir(cfg.DATA_DIR + '/demo')
    count = 0
    start_time = time.time()
    for images_name in images_dir:
        count += 1
        print('~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~')
        print('第', count,'张', 'Demo for data/demo/{}'.format(images_name))
        demo(net, images_name)
    current_time = time.time()
    sum_time = datetime.timedelta(seconds=current_time - start_time )
    print('总时间：', sum_time)  # 运行总时长
    
    #plt.show()
    #plt.figure().savefig('demo.png')