yolov5/utils/segment/general.py

import cv2
import torch
import torch.nn.functional as F


def crop_mask(masks, boxes):
    """
    "Crop" predicted masks by zeroing out everything not in the predicted bbox.
    Vectorized by Chong (thanks Chong).

    Args:
        - masks should be a size [h, w, n] tensor of masks
        - boxes should be a size [n, 4] tensor of bbox coords in relative point form
    """

    n, h, w = masks.shape
    x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1)  # x1 shape(1,1,n)
    r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :]  # rows shape(1,w,1)
    c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None]  # cols shape(h,1,1)

    return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))


def process_mask_upsample(protos, masks_in, bboxes, shape):
    """
    Crop after upsample.
    proto_out: [mask_dim, mask_h, mask_w]
    out_masks: [n, mask_dim], n is number of masks after nms
    bboxes: [n, 4], n is number of masks after nms
    shape:input_image_size, (h, w)

    return: h, w, n
    """

    c, mh, mw = protos.shape  # CHW
    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)
    masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0]  # CHW
    masks = crop_mask(masks, bboxes)  # CHW
    return masks.gt_(0.5)


def process_mask(protos, masks_in, bboxes, shape, upsample=False):
    """
    Crop before upsample.
    proto_out: [mask_dim, mask_h, mask_w]
    out_masks: [n, mask_dim], n is number of masks after nms
    bboxes: [n, 4], n is number of masks after nms
    shape:input_image_size, (h, w)

    return: h, w, n
    """

    c, mh, mw = protos.shape  # CHW
    ih, iw = shape
    masks = (masks_in @ protos.float().view(c, -1)).sigmoid().view(-1, mh, mw)  # CHW

    downsampled_bboxes = bboxes.clone()
    downsampled_bboxes[:, 0] *= mw / iw
    downsampled_bboxes[:, 2] *= mw / iw
    downsampled_bboxes[:, 3] *= mh / ih
    downsampled_bboxes[:, 1] *= mh / ih

    masks = crop_mask(masks, downsampled_bboxes)  # CHW
    if upsample:
        masks = F.interpolate(masks[None], shape, mode='bilinear', align_corners=False)[0]  # CHW
    return masks.gt_(0.5)


def scale_image(im1_shape, masks, im0_shape, ratio_pad=None):
    """
    img1_shape: model input shape, [h, w]
    img0_shape: origin pic shape, [h, w, 3]
    masks: [h, w, num]
    """
    # Rescale coordinates (xyxy) from im1_shape to im0_shape
    if ratio_pad is None:  # calculate from im0_shape
        gain = min(im1_shape[0] / im0_shape[0], im1_shape[1] / im0_shape[1])  # gain  = old / new
        pad = (im1_shape[1] - im0_shape[1] * gain) / 2, (im1_shape[0] - im0_shape[0] * gain) / 2  # wh padding
    else:
        pad = ratio_pad[1]
    top, left = int(pad[1]), int(pad[0])  # y, x
    bottom, right = int(im1_shape[0] - pad[1]), int(im1_shape[1] - pad[0])

    if len(masks.shape) < 2:
        raise ValueError(f'"len of masks shape" should be 2 or 3, but got {len(masks.shape)}')
    masks = masks[top:bottom, left:right]
    # masks = masks.permute(2, 0, 1).contiguous()
    # masks = F.interpolate(masks[None], im0_shape[:2], mode='bilinear', align_corners=False)[0]
    # masks = masks.permute(1, 2, 0).contiguous()
    masks = cv2.resize(masks, (im0_shape[1], im0_shape[0]))

    if len(masks.shape) == 2:
        masks = masks[:, :, None]
    return masks


def mask_iou(mask1, mask2, eps=1e-7):
    """
    mask1: [N, n] m1 means number of predicted objects
    mask2: [M, n] m2 means number of gt objects
    Note: n means image_w x image_h

    return: masks iou, [N, M]
    """
    intersection = torch.matmul(mask1, mask2.t()).clamp(0)
    union = (mask1.sum(1)[:, None] + mask2.sum(1)[None]) - intersection  # (area1 + area2) - intersection
    return intersection / (union + eps)


def masks_iou(mask1, mask2, eps=1e-7):
    """
    mask1: [N, n] m1 means number of predicted objects
    mask2: [N, n] m2 means number of gt objects
    Note: n means image_w x image_h

    return: masks iou, (N, )
    """
    intersection = (mask1 * mask2).sum(1).clamp(0)  # (N, )
    union = (mask1.sum(1) + mask2.sum(1))[None] - intersection  # (area1 + area2) - intersection
    return intersection / (union + eps)