SCHP/utils/transforms.py

# ------------------------------------------------------------------------------
# Copyright (c) Microsoft
# Licensed under the MIT License.
# Written by Bin Xiao (Bin.Xiao@microsoft.com)
# ------------------------------------------------------------------------------

from __future__ import absolute_import, division, print_function

import cv2

import numpy as np
import torch


class BRG2Tensor_transform(object):
    def __call__(self, pic):
        img = torch.from_numpy(pic.transpose((2, 0, 1)))
        if isinstance(img, torch.ByteTensor):
            return img.float()
        else:
            return img


class BGR2RGB_transform(object):
    def __call__(self, tensor):
        return tensor[[2, 1, 0], :, :]


def flip_back(output_flipped, matched_parts):
    """
    ouput_flipped: numpy.ndarray(batch_size, num_joints, height, width)
    """
    assert (
        output_flipped.ndim == 4
    ), "output_flipped should be [batch_size, num_joints, height, width]"

    output_flipped = output_flipped[:, :, :, ::-1]

    for pair in matched_parts:
        tmp = output_flipped[:, pair[0], :, :].copy()
        output_flipped[:, pair[0], :, :] = output_flipped[:, pair[1], :, :]
        output_flipped[:, pair[1], :, :] = tmp

    return output_flipped


def fliplr_joints(joints, joints_vis, width, matched_parts):
    """
    flip coords
    """
    # Flip horizontal
    joints[:, 0] = width - joints[:, 0] - 1

    # Change left-right parts
    for pair in matched_parts:
        joints[pair[0], :], joints[pair[1], :] = (
            joints[pair[1], :],
            joints[pair[0], :].copy(),
        )
        joints_vis[pair[0], :], joints_vis[pair[1], :] = (
            joints_vis[pair[1], :],
            joints_vis[pair[0], :].copy(),
        )

    return joints * joints_vis, joints_vis


def transform_preds(coords, center, scale, input_size):
    target_coords = np.zeros(coords.shape)
    trans = get_affine_transform(center, scale, 0, input_size, inv=1)
    for p in range(coords.shape[0]):
        target_coords[p, 0:2] = affine_transform(coords[p, 0:2], trans)
    return target_coords


def transform_parsing(pred, center, scale, width, height, input_size):

    trans = get_affine_transform(center, scale, 0, input_size, inv=1)
    target_pred = cv2.warpAffine(
        pred,
        trans,
        (int(width), int(height)),  # (int(width), int(height)),
        flags=cv2.INTER_NEAREST,
        borderMode=cv2.BORDER_CONSTANT,
        borderValue=(0),
    )

    return target_pred


def transform_logits(logits, center, scale, width, height, input_size):

    trans = get_affine_transform(center, scale, 0, input_size, inv=1)
    channel = logits.shape[2]
    target_logits = []
    for i in range(channel):
        target_logit = cv2.warpAffine(
            logits[:, :, i],
            trans,
            (int(width), int(height)),  # (int(width), int(height)),
            flags=cv2.INTER_LINEAR,
            borderMode=cv2.BORDER_CONSTANT,
            borderValue=(0),
        )
        target_logits.append(target_logit)
    target_logits = np.stack(target_logits, axis=2)

    return target_logits


def get_affine_transform(
    center, scale, rot, output_size, shift=np.array([0, 0], dtype=np.float32), inv=0
):
    if not isinstance(scale, np.ndarray) and not isinstance(scale, list):
        print(scale)
        scale = np.array([scale, scale])

    scale_tmp = scale

    src_w = scale_tmp[0]
    dst_w = output_size[1]
    dst_h = output_size[0]

    rot_rad = np.pi * rot / 180
    src_dir = get_dir([0, src_w * -0.5], rot_rad)
    dst_dir = np.array([0, (dst_w - 1) * -0.5], np.float32)

    src = np.zeros((3, 2), dtype=np.float32)
    dst = np.zeros((3, 2), dtype=np.float32)
    src[0, :] = center + scale_tmp * shift
    src[1, :] = center + src_dir + scale_tmp * shift
    dst[0, :] = [(dst_w - 1) * 0.5, (dst_h - 1) * 0.5]
    dst[1, :] = np.array([(dst_w - 1) * 0.5, (dst_h - 1) * 0.5]) + dst_dir

    src[2:, :] = get_3rd_point(src[0, :], src[1, :])
    dst[2:, :] = get_3rd_point(dst[0, :], dst[1, :])

    if inv:
        trans = cv2.getAffineTransform(np.float32(dst), np.float32(src))
    else:
        trans = cv2.getAffineTransform(np.float32(src), np.float32(dst))

    return trans


def affine_transform(pt, t):
    new_pt = np.array([pt[0], pt[1], 1.0]).T
    new_pt = np.dot(t, new_pt)
    return new_pt[:2]


def get_3rd_point(a, b):
    direct = a - b
    return b + np.array([-direct[1], direct[0]], dtype=np.float32)


def get_dir(src_point, rot_rad):
    sn, cs = np.sin(rot_rad), np.cos(rot_rad)

    src_result = [0, 0]
    src_result[0] = src_point[0] * cs - src_point[1] * sn
    src_result[1] = src_point[0] * sn + src_point[1] * cs

    return src_result


def crop(img, center, scale, output_size, rot=0):
    trans = get_affine_transform(center, scale, rot, output_size)

    dst_img = cv2.warpAffine(
        img, trans, (int(output_size[1]), int(output_size[0])), flags=cv2.INTER_LINEAR
    )

    return dst_img