Python timer.Timer类代码示例

def demo(sess, net, im_file, result_dir, viz=False, oriented=False):
    """Detect object classes in an image using pre-computed object proposals."""

    # Load the demo image
    im = helper.read_rgb_img(im_file)

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes, resized_im_shape, im_scale = im_detect(sess, net, im)
    timer.toc()

    im = cv2.cvtColor(im, cv2.COLOR_RGB2BGR)
    img_name = im_file.split('/')[-1]

    draw_rpn_boxes(im, img_name, boxes, scores[:, np.newaxis], im_scale, True, result_dir)
    draw_rpn_boxes(im, img_name, boxes, scores[:, np.newaxis], im_scale, False, result_dir)

    # Run TextDetector to merge small box
    line_detector = TextDetector(oriented)

    # line_detector 的输入必须是在 scale 之后的图片上！！，
    # 如果还原了以后再进行行构建，原图可能太大，导致每个 anchor 的 width 很大，导致 MAX_HORIZONTAL_GAP 太小
    # text_lines point order: left-top, right-top, left-bottom, right-bottom
    text_lines = line_detector.detect(boxes, scores[:, np.newaxis], resized_im_shape)
    print("Image %s, detect %d text lines in %.3fs" % (im_file, len(text_lines), timer.diff))

    if len(text_lines) != 0:
        text_lines = recover_scale(text_lines, im_scale)
        save_result(im, img_name, text_lines, result_dir)

    # Visualize detections
    if viz:
        vis_detections(im, CLASSES[1], text_lines)

    def train_with_hard_negatives(self):
        _t = Timer()
        roidb = self.imdb.roidb
        num_images = len(roidb)
        # num_images = 100
        for i in xrange(num_images):
            im = cv2.imread(self.imdb.image_path_at(i))
            if roidb[i]['flipped']:
                im = im[:, ::-1, :]
            _t.tic()
            scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])
            _t.toc()
            feat = self.net.blobs[self.layer].data
            for j in xrange(1, self.imdb.num_classes):
                hard_inds = \
                    np.where((scores[:, j] > self.hard_thresh) &
                             (roidb[i]['gt_overlaps'][:, j].toarray().ravel() <
                              self.neg_iou_thresh))[0]
                if len(hard_inds) > 0:
                    hard_feat = feat[hard_inds, :].copy()
                    new_w_b = \
                        self.trainers[j].append_neg_and_retrain(feat=hard_feat)
                    if new_w_b is not None:
                        self.update_net(j, new_w_b[0], new_w_b[1])

            print(('train_with_hard_negatives: '
                   '{:d}/{:d} {:.3f}s').format(i + 1, len(roidb),
                                               _t.average_time))

def load_model_h5(weight_file):
    darknet = DarkNet()
    model = SimpleNet(darknet)
    model.load_weights(weight_file)
    sgd = SGD(lr=0.1, decay=1e-6, momentum=0.9, nesterov=True)
    timer = Timer()
    timer.tic()
    model.compile(optimizer=sgd, loss='categorical_crossentropy')
    timer.toc()
    print 'Total compile time is {:.3f}s'.format(timer.total_time)
    for i in xrange(len(model.layers)):
        print model.layers[i]
        print model.layers[i].input_shape, model.layers[i].output_shape
        weights = model.layers[i].get_weights()
        if not weights is None and len(weights) > 0:
            print weights[0].shape, weights[0].max(), weights[0].min()
            # if len(weights) > 1:
            #     # print weights[0].shape, weights[0].max(), weights[0].min()
            #     # print "layer: %d" % (i)
            #     # w = weights[0].transpose()
            #     # w = weights[1]
            #     # print w.shape
            #     # cnt = 0
            #     # for val in w.flatten():
            #     # #     print >> f, val
            #     #     print 'weights[1]', cnt, ':', val
            #     #     cnt += 1
            #     #     raw_input()
            #     # print model.layers[4].get_weights()[0].shape, model.layers[4].get_weights()[1].shape
            #     # weights = model.layers[4].get_weights()[0]
            #     weights = weights[0]
            #     vis_square(weights.reshape((weights.shape[0]*weights.shape[1], weights.shape[2], weights.shape[3])))
    return model

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

    # Load the demo image as gray scale
    gim = cv2.imread(im_file, flags= cv2.CV_LOAD_IMAGE_GRAYSCALE)
    # convert to rgb repeated in each channel
    im = cv2.cvtColor(gim, cv2.COLOR_GRAY2BGR)
    # 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, :]
        vis_detections(im, cls, dets, thresh=CONF_THRESH)

def Detect(net, image_path):
    
    """Detect object classes in an image assuming the whole image is an object."""
    # Load the image
    im = cv2.imread(image_path)
    h, w, c = im.shape
    
    # TODO: Run selective search first
    # 

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(net, im, np.array([[0, 0, w, h]]))
    timer.toc()
    scores = scores[0]
 
    # get top 6 prediction
    pred_classes = [CLASSES[idx] for idx in ((-scores).argsort()[:6]).tolist()]
    conf = [ (-1) * prob for prob in np.sort(-scores)[:6].tolist()]
    
    img_blob = {}
    img_blob['image_path'] = image_path
    img_blob['pred'] = {'text': pred_classes, 'conf': conf}
    img_blob['rcnn_time'] = timer.total_time

    return img_blob

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.ROOT_DIR, 'data', '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)
        order = cls_scores.argsort()[::-1]
        sorted_dets = dets[order, :]
        keep = nms(dets, NMS_THRESH)
        with open('/home/xyy/Desktop/doing/Object Detection/py-faster-rcnn/test_python.txt','w') as f:
            dets = dets[keep, :]
            for i in dets:
                for j in i:
                    f.write(str(j)+ ' ')
                f.write('\n')
        vis_detections(im, cls, dets, thresh=CONF_THRESH)

    def _get_feature_scale(self, num_images=100):
        TARGET_NORM = 20.0  # Magic value from traditional R-CNN
        _t = Timer()
        roidb = self.imdb.roidb
        total_norm = 0.0
        count = 0.0
        inds = npr.choice(
            range(self.imdb.num_images), size=num_images,
            replace=False
        )

        for i_, i in enumerate(inds):
            im = cv2.imread(self.imdb.image_path_at(i))

            if roidb[i]['flipped']:
                im = im[:, ::-1, :]

            _t.tic()
            scores, boxes = im_detect(self.net, im, roidb[i]['boxes'])
            _t.toc()
            feat = self.net.blobs[self.layer].data
            total_norm += np.sqrt((feat ** 2).sum(axis=1)).sum()
            count += feat.shape[0]
            print('{}/{}: avg feature norm: {:.3f}'.format(
                    i_ + 1, num_images,
                    total_norm / count
                )
            )

        return TARGET_NORM * 1.0 / (total_norm / count)

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

    im_in = cv2.imread(image_name)

    if im_in is None:
        print('cannot open %s for read' % image_name )
        exit(-1)

    rows,cols = im_in.shape[:2]
    print([rows,cols])

    scale=1.0
    if rows >= cols:
        scale = float(args.longdim) / float(rows)
        im = cv2.resize( im_in, (int(0.5 + float(cols)*scale), args.longdim) )
    else:
        scale = float(args.longdim) / float(cols)
        im = cv2.resize( im_in, (args.longdim, int(0.5 + float(rows)*scale)) )

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

    max_scores = scores.max(axis=0)
    print(max_scores)
    print(boxes.shape)

    # Visualize detections for each class
    CONF_THRESH = args.threshold
    NMS_THRESH  = args.nms_thresh

    tattoo_dets=[]
    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] >= CONF_THRESH)[0]
        dets_filter = dets[inds]

        vis_detections(im, cls, dets_filter, thresh=CONF_THRESH)

        if cls == 'tattoo' and len(dets_filter)>0:
            plt.savefig(os.path.join(args.output, os.path.splitext(os.path.basename(image_name))[0] + '_det.png'))
            tattoo_dets = dets_filter

    if args.inspect == 'v':
        plt.show()
    plt.clf()

    return tattoo_dets, max_scores, seconds, scale

def demo(sess, 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 = os.path.join('/home/corgi/Lab/label/pos_frame/ACCV/training/000001/',image_name)
    im = cv2.imread(im_file)

    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(sess, 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
    im = im[:, :, (2, 1, 0)]
    fig, ax = plt.subplots(figsize=(12, 12))
    ax.imshow(im, aspect='equal')

    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, :]
        vis_detections(im, cls, dets, ax, thresh=CONF_THRESH)

def demoRest(net, image_name, classes, box_file, obj_proposals, im_file, im):
    # Detect all object classes and regress object bounds
    timer = Timer()
    timer.tic()
    scores, boxes = im_detect(net, im, obj_proposals)
    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 in classes:
        cls_ind = CLASSES.index(cls)
        cls_boxes = boxes[:, 4*cls_ind:4*(cls_ind + 1)]
        cls_scores = scores[:, cls_ind]
        keep = np.where(cls_scores >= CONF_THRESH)[0]
        cls_boxes = cls_boxes[keep, :]
        cls_scores = cls_scores[keep]
        dets = np.hstack((cls_boxes,
                          cls_scores[:, np.newaxis])).astype(np.float32)
        keep = nms(dets, NMS_THRESH)
        dets = dets[keep, :]
        print 'All {} detections with p({} | box) >= {:.1f}'.format(cls, cls,
                                                                    CONF_THRESH)
        vis_detections(im, cls, dets, thresh=CONF_THRESH)

    def train_whole_model(self, tester=None):
        '''
        test the performance using all the features
        may be memory consuming.
        '''
        self.comm.barrier()
        mpi.rootprint('*'*46)
        mpi.rootprint('*'*15+'whole featureset'+'*'*15)
        mpi.rootprint('*'*46)

        if tester is not None:
            # normalize the test data with the stats of the training data
            tester.normalize_data(self.mLocal, self.stdLocal)

        timer = Timer()
        timer.reset()
        if self.maxGraftDim != self.nMetabins*self.nCodes:
            mpi.rootprint('Please initialize with maxGraftDim=nMetabins*nCodes')
            return
        self.nSelFeats = 0
        self.isSelected[:] = False
        mpi.rootprint('Generating Features...')
        for code in range(self.nCodes):
            for metabin in range(self.nMetabins):
                self.append_feature(code, metabin)
                if tester is not None:
                    tester.append_feature(code, metabin)
        mpi.rootprint('Feature generation took {} secs'.format(timer.lap()))
        mpi.rootprint('Training...')
        loss = self.retrain_model(None)
        mpi.rootprint('Training took {} secs'.format(timer.lap()))
        mpi.rootprint('Training accuracy: {}'.format(self.compute_current_accuracy()))
        if tester is not None:
            mpi.rootprint('Current Testing accuracy: {}'.format(tester.compute_test_accuracy(self.weights, self.b)))

def detect(net, image_set, image_name, output_file):
    """Detect object classes in an image using pre-computed object proposals."""
    # Load pre-computed Selected Search object proposals
    #box_file = os.path.join(coco_root, 'boxes', image_set, image_name + '.mat')
    box_file = os.path.join(coco_root, 'boxes_full', image_set, image_name + '.mat')
    
    if not os.path.exists(box_file):
        print 'File does not exist', box_file
        return
        
    obj_proposals = sio.loadmat(box_file)['boxes']

    # Load the demo image
    im_file = os.path.join(coco_root, 'images', image_set, image_name + '.jpg')
    im = cv2.imread(im_file)

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

    def train_model(self, max_iters):
        #display = self.solver_param.display #40
        #test_iter = 1
        #test_interval = 1
        #_accuracy = 0
        #accuracy = 0

        timer = Timer()
        while self.solver.iter < max_iters:
            #print self.solver.iter
            #make one SGD update
            timer.tic()
            self.solver.step(1)
            timer.toc()
            """
            _train_loss += self.solver.net.blobs['euclidean_loss'].data
            if (self.solver.iter-1) % display == 0:
                train_loss[(self.solver.iter-1) // display] = _train_loss / display
                _train_loss = 0
            """
            if self.solver.iter % (self.solver_param.display) == 0:
                print ('speed {:.3f}s / iter').format(timer.average_time)
            """
            if self.solver.iter % test_interval == 0:
                for test_it in range(test_iter):
                    self.solver.test_nets[0].forward()
                    _accuracy += self.solver.test_nets[0].blobs['loss3/top-5'].data
                accuracy = _accuracy / test_iter
                f.write(str(self.solver.iter) + ' ' + str(accuracy) + '\n')
                _accuracy = 0
            """
                
            
        """

def detect_bboxes(net, im_names, subset_classes):
    """Detect object classes in an image using pre-computed object proposals."""
    df = cnn_utils.create_bbox_data_frame(with_object_index=False)

    for im_name in im_names:
        print '~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~'
        print 'Demo for {}'.format(im_name)

        # Load the input image.
        im_file = os.path.join(FLAGS.data_dir, 'images', im_name)
        im = cv2.imread(im_file)
        im_size_x = im.shape[1]
        im_size_y = im.shape[0]

        # 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])

        # Detect for each class
        for subset_cls_ind in range(len(class_names_to_be_detected)):
            cls = class_names_to_be_detected[subset_cls_ind]
            try:
                cls_ind = CLASSES.index(cls)
            except:
                print('error: class does not exist in training data: '
                      '{0}'.format(cls))
                exit(-1)

            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, FLAGS.nms_thresh)
            dets = dets[keep, :]
            inds = np.where(dets[:, -1] >= FLAGS.conf_thresh)[0]
            if len(inds) > 0:
                print ('{} {}(s) are detected.'.format(len(inds), cls))

            for i in inds:
                # ['image_name', 'class_index', 'x1', 'y1', 'x2', 'y2', 'score']
                x1 = dets[i, 0]
                y1 = dets[i, 1]
                x2 = dets[i, 2]
                y2 = dets[i, 3]
                score = dets[i, -1]
                if FLAGS.ignore_bbox_on_boundary:
                    # Ignore bounding boxes on the frame boundary.
                    if x1 <= 0 or x2 >= (im_size_x - 1) or \
                            y1 <= 0 or y2 >= (im_size_y - 1):
                        continue
                # Append a row.
                df.loc[len(df)] = [
                    im_name, subset_cls_ind, x1, y1, x2, y2, score]

    return df

def imdb_proposals(net, imdb):
    """Generate RPN proposals on all images in an imdb."""

    _t = Timer()
    imdb_boxes = [[] for _ in xrange(imdb.num_images)]
    for i in xrange(imdb.num_images):
        im = None
        if cfg.TRAIN.FORMAT == 'pickle':
            with open(imdb.image_path_at(i), 'rb') as f:
                im = cPickle.load(f)
        else:
            im = cv2.imread(imdb.image_path_at(i))

        _t.tic()
        imdb_boxes[i], scores = im_proposals(net, im)
        _t.toc()
        print 'im_proposals: {:d}/{:d} {:.3f}s' \
              .format(i + 1, imdb.num_images, _t.average_time)
        if 0:
            dets = np.hstack((imdb_boxes[i], scores))
            # from IPython import embed; embed()
            _vis_proposals(im, dets[:3, :], thresh=0.9)
            plt.show()

    return imdb_boxes