Untitled

mail@pastecode.io avatar
unknown
python
3 years ago
5.3 kB
2
Indexable
Never
def prep_display(dets_out, img, h, w, undo_transform=True, class_color=False, mask_alpha=0.45):
    """
    Note: If undo_transform=False then im_h and im_w are allowed to be None.
    """
    if undo_transform:
        img_numpy = undo_image_transformation(img, w, h)
        img_gpu = torch.Tensor(img_numpy).cuda()
    else:
        img_gpu = img / 255.0
        h, w, _ = img.shape

    with timer.env('Postprocess'):
        t = postprocess(dets_out, w, h, visualize_lincomb=args.display_lincomb,
                        crop_masks=args.crop,
                        score_threshold=args.score_threshold)
        torch.cuda.synchronize()

    with timer.env('Copy'):
        if cfg.eval_mask_branch:
            # Masks are drawn on the GPU, so don't copy
            masks = t[3][:args.top_k]
            image_mask = masks
            # print(len(image_mask))
            #print('masks: ', masks, '\n')
        # here
        classes, scores, boxes = [x[:args.top_k].cpu().numpy() for x in t[:3]]
        # print(classes, scores)

    num_dets_to_consider = min(args.top_k, classes.shape[0])
    for j in range(num_dets_to_consider):
        if scores[j] < args.score_threshold:
            num_dets_to_consider = j
            break

    if num_dets_to_consider == 0:
        # No detections found so just output the original image
        return (img_gpu * 255).byte().cpu().numpy()

    # Quick and dirty lambda for selecting the color for a particular index
    # Also keeps track of a per-gpu color cache for maximum speed
    def get_color(j, on_gpu=None):
        global color_cache
        color_idx = (classes[j] * 5 if class_color else j * 5) % len(COLORS)

        if on_gpu is not None and color_idx in color_cache[on_gpu]:
            return color_cache[on_gpu][color_idx]
        else:
            color = COLORS[color_idx]
            if not undo_transform:
                # The image might come in as RGB or BRG, depending
                color = (color[2], color[1], color[0])
            if on_gpu is not None:
                color = torch.Tensor(color).to(on_gpu).float() / 255.
                color_cache[on_gpu][color_idx] = color
            # print('Color from yolact bottom: ', color)
            return color

    # First, draw the masks on the GPU where we can do it really fast
    # Beware: very fast but possibly unintelligible mask-drawing code ahead
    # I wish I had access to OpenGL or Vulkan but alas, I guess Pytorch tensor operations will have to suffice
    if args.display_masks and cfg.eval_mask_branch:
        # After this, mask is of size [num_dets, h, w, 1]
        masks = masks[:num_dets_to_consider, :, :, None]

        # Prepare the RGB images for each mask given their color (size [num_dets, h, w, 1])
        colors = torch.cat([get_color(j, on_gpu=img_gpu.device.index).view(
            1, 1, 1, 3) for j in range(num_dets_to_consider)], dim=0)
        masks_color = masks.repeat(1, 1, 1, 3) * colors * mask_alpha

        # This is 1 everywhere except for 1-mask_alpha where the mask is
        inv_alph_masks = masks * (-mask_alpha) + 1

        # I did the math for this on pen and paper. This whole block should be equivalent to:
        #    for j in range(num_dets_to_consider):
        #        img_gpu = img_gpu * inv_alph_masks[j] + masks_color[j]
        masks_color_summand = masks_color[0]
        if num_dets_to_consider > 1:
            inv_alph_cumul = inv_alph_masks[:(
                num_dets_to_consider-1)].cumprod(dim=0)
            masks_color_cumul = masks_color[1:] * inv_alph_cumul
            masks_color_summand += masks_color_cumul.sum(dim=0)

        img_gpu = img_gpu * inv_alph_masks.prod(dim=0) + masks_color_summand

    # Then draw the stuff that needs to be done on the cpu
    # Note, make sure this is a uint8 tensor or opencv will not anti alias text for whatever reason
    img_numpy = (img_gpu * 255).byte().cpu().numpy()
    args.display_text, args.display_bboxes, args.display_scores = True, True, True
    if args.display_text or args.display_bboxes:
        for j in reversed(range(num_dets_to_consider)):
            x1, y1, x2, y2 = boxes[j, :]
            color = get_color(j)
            score = scores[j]

            if args.display_bboxes:
                cv2.rectangle(img_numpy, (x1, y1), (x2, y2), color, 1)

            if args.display_text:
                _class = cfg.dataset.class_names[classes[j]]
                text_str = '%s: %.2f' % (
                    _class, score) if args.display_scores else _class

                font_face = cv2.FONT_HERSHEY_DUPLEX
                font_scale = 0.6
                font_thickness = 1

                text_w, text_h = cv2.getTextSize(
                    text_str, font_face, font_scale, font_thickness)[0]

                text_pt = (x1, y1 - 3)
                text_color = [255, 255, 255]

                cv2.rectangle(img_numpy, (x1, y1),
                              (x1 + text_w, y1 - text_h - 4), color, -1)
                cv2.putText(img_numpy, text_str, text_pt, font_face,
                            font_scale, text_color, font_thickness, cv2.LINE_AA)
    # print('image_mask shape', image_mask.cpu().numpy().shape)
    return img_numpy, image_mask.cpu().numpy(), classes, scores, boxes