Ejemplo n.º 1
0
    net = net
    # cudnn.benchmark = True
    torch.set_default_tensor_type('torch.FloatTensor')

    x = torch.zeros((1, 3, cfg.max_size, cfg.max_size))
    y = net(x)

    for p in net.prediction_layers:
        print(p.last_conv_size)

    print()
    for k, a in y.items():
        print(k + ': ', a.size(), torch.sum(a))
    exit()

    net(x)
    # timer.disable('pass2')
    avg = MovingAverage()
    try:
        while True:
            timer.reset()
            with timer.env('everything else'):
                net(x)
            avg.add(timer.total_time())
            print('\033[2J')  # Moves console cursor to 0,0
            timer.print_stats()
            print('Avg fps: %.2f\tAvg ms: %.2f         ' %
                  (1 / avg.get_avg(), avg.get_avg() * 1000))
    except KeyboardInterrupt:
        pass
Ejemplo n.º 2
0
def evaluate(net: Yolact, dataset, train_mode=False):
    net.detect.use_fast_nms = args.fast_nms
    net.detect.use_cross_class_nms = args.cross_class_nms
    cfg.mask_proto_debug = args.mask_proto_debug

    # TODO Currently we do not support Fast Mask Re-scroing in evalimage, evalimages, and evalvideo
    if args.image is not None:
        if ':' in args.image:
            inp, out = args.image.split(':')
            evalimage(net, inp, out)
        else:
            evalimage(net, args.image)
        return
    elif args.images is not None:
        inp, out = args.images.split(':')
        evalimages(net, inp, out)
        return
    elif args.video is not None:
        if ':' in args.video:
            inp, out = args.video.split(':')
            evalvideo(net, inp, out)
        else:
            evalvideo(net, args.video)
        return

    frame_times = MovingAverage()
    dataset_size = len(dataset) if args.max_images < 0 else min(
        args.max_images, len(dataset))
    progress_bar = ProgressBar(30, dataset_size)

    print()

    if not args.display and not args.benchmark:
        # For each class and iou, stores tuples (score, isPositive)
        # Index ap_data[type][iouIdx][classIdx]
        ap_data = {
            'box': [[APDataObject() for _ in cfg.dataset.class_names]
                    for _ in iou_thresholds],
            'mask': [[APDataObject() for _ in cfg.dataset.class_names]
                     for _ in iou_thresholds]
        }
        detections = Detections()
    else:
        timer.disable('Load Data')

    dataset_indices = list(range(len(dataset)))

    if args.shuffle:
        random.shuffle(dataset_indices)
    elif not args.no_sort:
        # Do a deterministic shuffle based on the image ids
        #
        # I do this because on python 3.5 dictionary key order is *random*, while in 3.6 it's
        # the order of insertion. That means on python 3.6, the images come in the order they are in
        # in the annotations file. For some reason, the first images in the annotations file are
        # the hardest. To combat this, I use a hard-coded hash function based on the image ids
        # to shuffle the indices we use. That way, no matter what python version or how pycocotools
        # handles the data, we get the same result every time.
        hashed = [badhash(x) for x in dataset.ids]
        dataset_indices.sort(key=lambda x: hashed[x])

    dataset_indices = dataset_indices[:dataset_size]

    try:
        # Main eval loop
        for it, image_idx in enumerate(dataset_indices):
            timer.reset()

            with timer.env('Load Data'):
                img, gt, gt_masks, h, w, num_crowd = dataset.pull_item(
                    image_idx)

                # Test flag, do not upvote
                if cfg.mask_proto_debug:
                    with open('scripts/info.txt', 'w') as f:
                        f.write(str(dataset.ids[image_idx]))
                    np.save('scripts/gt.npy', gt_masks)

                batch = Variable(img.unsqueeze(0))
                if args.cuda:
                    batch = batch.cuda()

            with timer.env('Network Extra'):
                preds = net(batch)
            # Perform the meat of the operation here depending on our mode.
            if args.display:
                img_numpy = prep_display(preds, img, h, w)
            elif args.benchmark:
                prep_benchmark(preds, h, w)
            else:
                prep_metrics(ap_data, preds, img, gt, gt_masks, h, w,
                             num_crowd, dataset.ids[image_idx], detections)

            # First couple of images take longer because we're constructing the graph.
            # Since that's technically initialization, don't include those in the FPS calculations.
            if it > 1:
                frame_times.add(timer.total_time())

            if args.display:
                if it > 1:
                    print('Avg FPS: %.4f' % (1 / frame_times.get_avg()))
                plt.imshow(img_numpy)
                plt.title(str(dataset.ids[image_idx]))
                plt.show()
            elif not args.no_bar:
                if it > 1: fps = 1 / frame_times.get_avg()
                else: fps = 0
                progress = (it + 1) / dataset_size * 100
                progress_bar.set_val(it + 1)
                print(
                    '\rProcessing Images  %s %6d / %6d (%5.2f%%)    %5.2f fps        '
                    %
                    (repr(progress_bar), it + 1, dataset_size, progress, fps),
                    end='')

        if not args.display and not args.benchmark:
            print()
            if args.output_coco_json:
                print('Dumping detections...')
                if args.output_web_json:
                    detections.dump_web()
                else:
                    detections.dump()
            else:
                if not train_mode:
                    print('Saving data...')
                    with open(args.ap_data_file, 'wb') as f:
                        pickle.dump(ap_data, f)

                return calc_map(ap_data)
        elif args.benchmark:
            print()
            print()
            print('Stats for the last frame:')
            timer.print_stats()
            avg_seconds = frame_times.get_avg()
            print('Average: %5.2f fps, %5.2f ms' %
                  (1 / frame_times.get_avg(), 1000 * avg_seconds))

    except KeyboardInterrupt:
        print('Stopping...')