Python data.VOC_CLASSES属性代码示例

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_voc():
    # load net
    num_classes = len(VOC_CLASSES) + 1 # +1 background
    net = build_ssd('test', 300, num_classes) # initialize SSD
    net.load_state_dict(torch.load(args.trained_model))
    net.eval()
    print('Finished loading model!')
    # load data
    testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform())
    if args.cuda:
        net = net.cuda()
        cudnn.benchmark = True
    # evaluation
    test_net(args.save_folder, net, args.cuda, testset,
             BaseTransform(net.size, (104, 117, 123)),
             thresh=args.visual_threshold) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_voc():
    # load net
    num_classes = len(VOC_CLASSES) + 1 # +1 background
    net = build_ssd('test',args.model, 300, num_classes) # initialize SSD
    net.load_state_dict(torch.load(args.trained_model))
    net.eval()
    print('Finished loading model!')
    # load data
    testset = VOCDetection(args.voc_root, [('2007', 'test')], None, VOCAnnotationTransform())
    if args.cuda:
        net = net.cuda()
        cudnn.benchmark = True
    # evaluation
    test_net(args.save_folder, net, args.cuda, testset,
             BaseTransform(net.size, (104, 117, 123)),
             thresh=args.visual_threshold) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def write_voc_results_file(all_boxes, dataset):
    for cls_ind, cls in enumerate(labelmap):
        print('Writing {:s} VOC results file'.format(cls))
        filename = get_voc_results_file_template(set_type, cls)
        with open(filename, 'wt') as f:
            for im_ind, index in enumerate(dataset.ids):
                dets = all_boxes[cls_ind+1][im_ind]
                if dets == []:
                    continue
                # the VOCdevkit expects 1-based indices
                for k in range(dets.shape[0]):
                    f.write('{:s} {:.3f} {:.1f} {:.1f} {:.1f} {:.1f}\n'.
                            format(index[1], dets[k, -1],
                                   dets[k, 0] + 1, dets[k, 1] + 1,
                                   dets[k, 2] + 1, dets[k, 3] + 1)) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def do_python_eval(output_dir='output', use_07=True):
    cachedir = os.path.join(devkit_path, 'annotations_cache')
    aps = []
    # The PASCAL VOC metric changed in 2010
    use_07_metric = use_07
    print('VOC07 metric? ' + ('Yes' if use_07_metric else 'No'))
    if not os.path.isdir(output_dir):
        os.mkdir(output_dir)
    for i, cls in enumerate(labelmap):
        filename = get_voc_results_file_template(set_type, cls)
        rec, prec, ap = voc_eval(
           filename, annopath, imgsetpath.format(set_type), cls, cachedir,
           ovthresh=0.5, use_07_metric=use_07_metric)
        aps += [ap]
        print('AP for {} = {:.4f}'.format(cls, ap))
        with open(os.path.join(output_dir, cls + '_pr.pkl'), 'wb') as f:
            pickle.dump({'rec': rec, 'prec': prec, 'ap': ap}, f)
    print('Mean AP = {:.4f}'.format(np.mean(aps)))
    print('~~~~~~~~')
    print('Results:')
    for ap in aps:
        print('{:.3f}'.format(ap))
    print('{:.3f}'.format(np.mean(aps)))
    print('~~~~~~~~')
    print('')
    print('--------------------------------------------------------------')
    print('Results computed with the **unofficial** Python eval code.')
    print('Results should be very close to the official MATLAB eval code.')
    print('--------------------------------------------------------------') 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def cv2_demo(net, transform):
    def predict(frame):
        height, width = frame.shape[:2]
        x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1)
        x = Variable(x.unsqueeze(0))
        y = net(x)  # forward pass
        detections = y.data
        # scale each detection back up to the image
        scale = torch.Tensor([width, height, width, height])
        for i in range(detections.size(1)):
            j = 0
            while detections[0, i, j, 0] >= 0.6:
                pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
                cv2.rectangle(frame,
                              (int(pt[0]), int(pt[1])),
                              (int(pt[2]), int(pt[3])),
                              COLORS[i % 3], 2)
                cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])),
                            FONT, 2, (255, 255, 255), 2, cv2.LINE_AA)
                j += 1
        return frame

    # start video stream thread, allow buffer to fill
    print("[INFO] starting threaded video stream...")
    stream = WebcamVideoStream(src=0).start()  # default camera
    time.sleep(1.0)
    # start fps timer
    # loop over frames from the video file stream
    while True:
        # grab next frame
        frame = stream.read()
        key = cv2.waitKey(1) & 0xFF

        # update FPS counter
        fps.update()
        frame = predict(frame)

        # keybindings for display
        if key == ord('p'):  # pause
            while True:
                key2 = cv2.waitKey(1) or 0xff
                cv2.imshow('frame', frame)
                if key2 == ord('p'):  # resume
                    break
        cv2.imshow('frame', frame)
        if key == 27:  # exit
            break 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_net(save_folder, net, cuda, dataset, transform, top_k,
             im_size=512, thresh=0.05):
    num_images = len(dataset)
    # all detections are collected into:
    #    all_boxes[cls][image] = N x 5 array of detections in
    #    (x1, y1, x2, y2, score)
    all_boxes = [[[] for _ in range(num_images)]
                 for _ in range(len(labelmap)+1)]

    # timers
    _t = {'im_detect': Timer(), 'misc': Timer()}
    output_dir = get_output_dir('ssd300_120000', set_type)
    det_file = os.path.join(output_dir, 'detections.pkl')

    for i in range(num_images):
        im, gt, h, w = dataset.pull_item(i)

        x = Variable(im.unsqueeze(0))
        if args.cuda:
            x = x.cuda()
        _t['im_detect'].tic()
        detections = net(x).data
        detect_time = _t['im_detect'].toc(average=False)

        # skip j = 0, because it's the background class
        for j in range(1, detections.size(1)):
            dets = detections[0, j, :]
            mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t()
            dets = torch.masked_select(dets, mask).view(-1, 5)
            if dets.dim() == 0:
                continue
            boxes = dets[:, 1:]
            boxes[:, 0] *= w
            boxes[:, 2] *= w
            boxes[:, 1] *= h
            boxes[:, 3] *= h
            scores = dets[:, 0].cpu().numpy()
            cls_dets = np.hstack((boxes.cpu().numpy(),
                                  scores[:, np.newaxis])).astype(np.float32,
                                                                 copy=False)
            all_boxes[j][i] = cls_dets

        print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1,
                                                    num_images, detect_time))

    with open(det_file, 'wb') as f:
        pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

    print('Evaluating detections')
    evaluate_detections(all_boxes, output_dir, dataset) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_net(save_folder, net, cuda, dataset, transform, top_k,
             im_size=300, thresh=0.05):
    num_images = len(dataset)
    # all detections are collected into:
    #    all_boxes[cls][image] = N x 5 array of detections in
    #    (x1, y1, x2, y2, score)
    all_boxes = [[[] for _ in range(num_images)]
                 for _ in range(len(labelmap)+1)]

    # timers
    _t = {'im_detect': Timer(), 'misc': Timer()}
    output_dir = get_output_dir('ssd300_120000', set_type)
    det_file = os.path.join(output_dir, 'detections.pkl')

    for i in range(num_images):
        im, gt, h, w = dataset.pull_item(i)

        x = Variable(im.unsqueeze(0))
        if args.cuda:
            x = x.cuda()
        _t['im_detect'].tic()
        detections = net(x).data
        detect_time = _t['im_detect'].toc(average=False)

        # skip j = 0, because it's the background class
        for j in range(1, detections.size(1)):
            dets = detections[0, j, :]
            mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t()
            dets = torch.masked_select(dets, mask).view(-1, 5)
            if dets.dim() == 0:
                continue
            boxes = dets[:, 1:]
            boxes[:, 0] *= w
            boxes[:, 2] *= w
            boxes[:, 1] *= h
            boxes[:, 3] *= h
            scores = dets[:, 0].cpu().numpy()
            cls_dets = np.hstack((boxes.cpu().numpy(),
                                  scores[:, np.newaxis])).astype(np.float32,
                                                                 copy=False)
            all_boxes[j][i] = cls_dets

        print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1,
                                                    num_images, detect_time))

    with open(det_file, 'wb') as f:
        pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

    print('Evaluating detections')
    evaluate_detections(all_boxes, output_dir, dataset) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_net(save_folder, net, cuda, dataset, transform, top_k,
             im_size=300, thresh=0.05):
    num_images = len(dataset)
    # all detections are collected into:
    #    all_boxes[cls][image] = N x 5 array of detections in
    #    (x1, y1, x2, y2, score)
    all_boxes = [[[] for _ in range(num_images)]
                 for _ in range(len(labelmap)+1)]

    # timers
    _t = {'im_detect': Timer(), 'misc': Timer()}
    output_dir = get_output_dir('ssd300_120000', set_type)
    det_file = os.path.join(output_dir, 'detections.pkl')

    for i in tqdm(range(num_images),ncols= 50 ):
        im, gt, h, w ,ori_img= dataset.pull_item(i)

        x = Variable(im.unsqueeze(0))
        if args.cuda:
            x = x.cuda()
        _t['im_detect'].tic()
        detections = net(x).data
        detect_time = _t['im_detect'].toc(average=False)

        # skip j = 0, because it's the background class
        for j in range(1, detections.size(1)):
            dets = detections[0, j, :]
            mask = dets[:, 0].gt(thresh).expand(5, dets.size(0)).t()
            dets = torch.masked_select(dets, mask).view(-1, 5)
            if dets.size(0) == 0:
                continue
            boxes = dets[:, 1:]
            boxes[:, 0] *= w
            boxes[:, 2] *= w
            boxes[:, 1] *= h
            boxes[:, 3] *= h
            boxes = boxes.cpu().numpy()
            scores = dets[:, 0].cpu().numpy()



            cls_dets = np.hstack((boxes,
                                  scores[:, np.newaxis])).astype(np.float32,
                                                         copy=False)

            vis_detections(ori_img, pascal_classes[j], color_list[j].tolist(),
                           cls_dets, 0.1)


            all_boxes[j][i] = cls_dets
        cv2.imwrite("./result/{}.jpg".format(i),ori_img)
        # print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1,
        #                                             num_images, detect_time))

    with open(det_file, 'wb') as f:
        pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

    print('Evaluating detections')
    evaluate_detections(all_boxes, output_dir, dataset) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def cv2_demo(net, transform):
    def predict(frame):
        height, width = frame.shape[:2]
        x = torch.from_numpy(transform(frame)[0]).permute(2, 0, 1)
        x = Variable(x.unsqueeze(0))
        y = net(x)  # forward pass
        detections = y.data
        # scale each detection back up to the image
        scale = torch.Tensor([width, height, width, height])
        for i in range(detections.size(1)):
            j = 0
            while detections[0, i, j, 0] >= 0.6:
                pt = (detections[0, i, j, 1:] * scale).cpu().numpy()
                cv2.rectangle(frame, (int(pt[0]), int(pt[1])), (int(pt[2]),
                                                                int(pt[3])), COLORS[i % 3], 2)
                cv2.putText(frame, labelmap[i - 1], (int(pt[0]), int(pt[1])), FONT,
                            2, (255, 255, 255), 2, cv2.LINE_AA)
                j += 1
        return frame

    # start video stream thread, allow buffer to fill
    print("[INFO] starting threaded video stream...")
    stream = WebcamVideoStream(src=0).start()  # default camera
    time.sleep(1.0)
    # start fps timer
    # loop over frames from the video file stream
    while True:
        # grab next frame
        frame = stream.read()
        key = cv2.waitKey(1) & 0xFF

        # update FPS counter
        fps.update()
        frame = predict(frame)

        # keybindings for display
        if key == ord('p'):  # pause
            while True:
                key2 = cv2.waitKey(1) or 0xff
                cv2.imshow('frame', frame)
                if key2 == ord('p'):  # resume
                    break
        cv2.imshow('frame', frame)
        if key == 27:  # exit
            break 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def test_net(save_folder, net, cuda, dataset, transform, top_k,
             im_size=300, thresh=0.05):
    num_images = len(dataset)
    # all detections are collected into:
    #    all_boxes[cls][image] = N x 5 array of detections in
    #    (x1, y1, x2, y2, score)
    all_boxes = [[[] for _ in range(num_images)]
                 for _ in range(len(labelmap)+1)]

    # timers
    _t = {'im_detect': Timer(), 'misc': Timer()}
    output_dir = get_output_dir('ssd300_120000', set_type)
    det_file = os.path.join(output_dir, 'detections.pkl')

    for i in range(num_images):
        im, gt, h, w = dataset.pull_item(i)

        x = Variable(im.unsqueeze(0))
        if args.cuda:
            x = x.cuda()
        _t['im_detect'].tic()
        detections = net(x).data
        detect_time = _t['im_detect'].toc(average=False)

        # skip j = 0, because it's the background class
        for j in range(1, detections.size(1)):
            dets = detections[0, j, :]
            mask = dets[:, 0].gt(0.).expand(5, dets.size(0)).t()
            dets = torch.masked_select(dets, mask).view(-1, 5)
            if dets.size(0) == 0:
                continue
            boxes = dets[:, 1:]
            boxes[:, 0] *= w
            boxes[:, 2] *= w
            boxes[:, 1] *= h
            boxes[:, 3] *= h
            scores = dets[:, 0].cpu().numpy()
            cls_dets = np.hstack((boxes.cpu().numpy(),
                                  scores[:, np.newaxis])).astype(np.float32,
                                                                 copy=False)
            all_boxes[j][i] = cls_dets

        print('im_detect: {:d}/{:d} {:.3f}s'.format(i + 1,
                                                    num_images, detect_time))

    with open(det_file, 'wb') as f:
        pickle.dump(all_boxes, f, pickle.HIGHEST_PROTOCOL)

    print('Evaluating detections')
    evaluate_detections(all_boxes, output_dir, dataset) 

# 需要导入模块: import data [as 别名]
# 或者: from data import VOC_CLASSES [as 别名]
def init_det(frame, net):
    # st = time.time()
    # net = build_ssd('test', 300, 21)    # initialize SSD
    # net.load_weights(weights)
    # et = time.time()
    # print ("ssd time", et - st)

    # print (type(net))
    # cv2.imread(frame, cv2.IMREAD_COLOR)  # uncomment if dataset not downloaded
    image = frame 
    # from data import VOCDetection, VOC_ROOT, VOCAnnotationTransform
    # here we specify year (07 or 12) and dataset ('test', 'val', 'train') 
    # testset = VOCDetection(VOC_ROOT, [('2007', 'val')], None, VOCAnnotationTransform())
    # image = testset.pull_image(img_id)
    rgb_image = frame
    # View the sampled input image before transform
    # plt.figure(figsize=(10,10))
    # plt.imshow(rgb_image)
    x = cv2.resize(image, (300, 300)).astype(np.float32)
    x -= (104.0, 117.0, 123.0)
    x = x.astype(np.float32)
    x = x[:, :, ::-1].copy()
    #splt.imshow(x)
    x = torch.from_numpy(x).permute(2, 0, 1)

    xx = Variable(x.unsqueeze(0))     # wrap tensor in Variable
    if torch.cuda.is_available():
        xx = xx.cuda()
    y = net(xx)

    from data import VOC_CLASSES as labels
    top_k=10

    #plt.figure(figsize=(10,10))
    # colors = plt.cm.hsv(np.linspace(0, 1, 21)).tolist()
    #plt.imshow(rgb_image)  # plot the image for matplotlib
    # currentAxis = plt.gca()

    detections = y.data
    # scale each detection back up to the image
    scale = torch.Tensor(rgb_image.shape[1::-1]).repeat(2)
    big_coords = []
    for i in range(detections.size(1)):
        j = 0
        while detections[0,i,j,0] >= 0.6:
            score = detections[0,i,j,0]
            label_name = labels[i-1]
            if (label_name == "person"):
                display_txt = '%s: %.2f'%(label_name, score)
                pt = (detections[0,i,j,1:]*scale).cpu().numpy()
                coords = [int(pt[0]), int(pt[1]), int(pt[2]-pt[0]+1), int(pt[3]-pt[1]+1)]
                big_coords.append(coords)
                # print (coords)
                # color = colors[i]
                # currentAxis.add_patch(plt.Rectangle(*coords, fill=False, edgecolor=color, linewidth=2))
                # currentAxis.text(pt[0], pt[1], display_txt, bbox={'facecolor':color, 'alpha':0.5})
            j+=1
    # plt.show()
    return big_coords