# Copyright (c) 2022 PaddlePaddle Authors. All Rights Reserved. 
#   
# Licensed under the Apache License, Version 2.0 (the "License");   
# you may not use this file except in compliance with the License.  
# You may obtain a copy of the License at   
#   
#     http://www.apache.org/licenses/LICENSE-2.0    
#   
# Unless required by applicable law or agreed to in writing, software   
# distributed under the License is distributed on an "AS IS" BASIS, 
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.  
# See the License for the specific language governing permissions and   
# limitations under the License.

import logging
import numpy as np
import cv2
import copy
from paddleslim.common import get_logger

logger = get_logger(__name__, level=logging.INFO)

__all__ = ['keypoint_post_process']


def flip_back(output_flipped, matched_parts):
    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 get_affine_transform(center,
                         input_size,
                         rot,
                         output_size,
                         shift=(0., 0.),
                         inv=False):
    """Get the affine transform matrix, given the center/scale/rot/output_size.
    Args:
        center (np.ndarray[2, ]): Center of the bounding box (x, y).
        input_size (np.ndarray[2, ]): Size of input feature (width, height).
        rot (float): Rotation angle (degree).
        output_size (np.ndarray[2, ]): Size of the destination heatmaps.
        shift (0-100%): Shift translation ratio wrt the width/height.
            Default (0., 0.).
        inv (bool): Option to inverse the affine transform direction.
            (inv=False: src->dst or inv=True: dst->src)
    Returns:
        np.ndarray: The transform matrix.
    """
    assert len(center) == 2
    assert len(output_size) == 2
    assert len(shift) == 2

    if not isinstance(input_size, (np.ndarray, list)):
        input_size = np.array([input_size, input_size], dtype=np.float32)
    scale_tmp = input_size

    shift = np.array(shift)
    src_w = scale_tmp[0]
    dst_w = output_size[0]
    dst_h = output_size[1]

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

    src = np.zeros((3, 2), dtype=np.float32)

    src[0, :] = center + scale_tmp * shift
    src[1, :] = center + src_dir + scale_tmp * shift
    src[2, :] = _get_3rd_point(src[0, :], src[1, :])

    dst = np.zeros((3, 2), dtype=np.float32)
    dst[0, :] = [dst_w * 0.5, dst_h * 0.5]
    dst[1, :] = np.array([dst_w * 0.5, dst_h * 0.5]) + dst_dir
    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 _get_3rd_point(a, b):
    """To calculate the affine matrix, three pairs of points are required. This
    function is used to get the 3rd point, given 2D points a & b.
    The 3rd point is defined by rotating vector `a - b` by 90 degrees
    anticlockwise, using b as the rotation center.
    Args:
        a (np.ndarray): point(x,y)
        b (np.ndarray): point(x,y)
    Returns:
        np.ndarray: The 3rd point.
    """
    assert len(
        a) == 2, 'input of _get_3rd_point should be point with length of 2'
    assert len(
        b) == 2, 'input of _get_3rd_point should be point with length of 2'
    direction = a - b
    third_pt = b + np.array([-direction[1], direction[0]], dtype=np.float32)

    return third_pt


def rotate_point(pt, angle_rad):
    """Rotate a point by an angle.
    Args:
        pt (list[float]): 2 dimensional point to be rotated
        angle_rad (float): rotation angle by radian
    Returns:
        list[float]: Rotated point.
    """
    assert len(pt) == 2
    sn, cs = np.sin(angle_rad), np.cos(angle_rad)
    new_x = pt[0] * cs - pt[1] * sn
    new_y = pt[0] * sn + pt[1] * cs
    rotated_pt = [new_x, new_y]

    return rotated_pt


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


def transform_preds(coords, center, scale, output_size):
    target_coords = np.zeros(coords.shape)
    trans = get_affine_transform(center, scale * 200, 0, output_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


class HRNetPostProcess(object):
    def __init__(self, use_dark=True):
        self.use_dark = use_dark

    def get_max_preds(self, heatmaps):
        '''get predictions from score maps
        Args:
            heatmaps: numpy.ndarray([batch_size, num_joints, height, width])
        Returns:
            preds: numpy.ndarray([batch_size, num_joints, 2]), keypoints coords
            maxvals: numpy.ndarray([batch_size, num_joints, 2]), the maximum confidence of the keypoints
        '''
        assert isinstance(heatmaps,
                          np.ndarray), 'heatmaps should be numpy.ndarray'
        assert heatmaps.ndim == 4, 'batch_images should be 4-ndim'

        batch_size = heatmaps.shape[0]
        num_joints = heatmaps.shape[1]
        width = heatmaps.shape[3]
        heatmaps_reshaped = heatmaps.reshape((batch_size, num_joints, -1))
        idx = np.argmax(heatmaps_reshaped, 2)
        maxvals = np.amax(heatmaps_reshaped, 2)

        maxvals = maxvals.reshape((batch_size, num_joints, 1))
        idx = idx.reshape((batch_size, num_joints, 1))

        preds = np.tile(idx, (1, 1, 2)).astype(np.float32)

        preds[:, :, 0] = (preds[:, :, 0]) % width
        preds[:, :, 1] = np.floor((preds[:, :, 1]) / width)

        pred_mask = np.tile(np.greater(maxvals, 0.0), (1, 1, 2))
        pred_mask = pred_mask.astype(np.float32)

        preds *= pred_mask

        return preds, maxvals

    def gaussian_blur(self, heatmap, kernel):
        border = (kernel - 1) // 2
        batch_size = heatmap.shape[0]
        num_joints = heatmap.shape[1]
        height = heatmap.shape[2]
        width = heatmap.shape[3]
        for i in range(batch_size):
            for j in range(num_joints):
                origin_max = np.max(heatmap[i, j])
                dr = np.zeros((height + 2 * border, width + 2 * border))
                dr[border:-border, border:-border] = heatmap[i, j].copy()
                dr = cv2.GaussianBlur(dr, (kernel, kernel), 0)
                heatmap[i, j] = dr[border:-border, border:-border].copy()
                heatmap[i, j] *= origin_max / np.max(heatmap[i, j])
        return heatmap

    def dark_parse(self, hm, coord):
        heatmap_height = hm.shape[0]
        heatmap_width = hm.shape[1]
        px = int(coord[0])
        py = int(coord[1])
        if 1 < px < heatmap_width - 2 and 1 < py < heatmap_height - 2:
            dx = 0.5 * (hm[py][px + 1] - hm[py][px - 1])
            dy = 0.5 * (hm[py + 1][px] - hm[py - 1][px])
            dxx = 0.25 * (hm[py][px + 2] - 2 * hm[py][px] + hm[py][px - 2])
            dxy = 0.25 * (hm[py+1][px+1] - hm[py-1][px+1] - hm[py+1][px-1] \
                + hm[py-1][px-1])
            dyy = 0.25 * (
                hm[py + 2 * 1][px] - 2 * hm[py][px] + hm[py - 2 * 1][px])
            derivative = np.matrix([[dx], [dy]])
            hessian = np.matrix([[dxx, dxy], [dxy, dyy]])
            if dxx * dyy - dxy**2 != 0:
                hessianinv = hessian.I
                offset = -hessianinv * derivative
                offset = np.squeeze(np.array(offset.T), axis=0)
                coord += offset
        return coord

    def dark_postprocess(self, hm, coords, kernelsize):
        '''
        DARK postpocessing, Zhang et al. Distribution-Aware Coordinate
        Representation for Human Pose Estimation (CVPR 2020).
        '''
        hm = self.gaussian_blur(hm, kernelsize)
        hm = np.maximum(hm, 1e-10)
        hm = np.log(hm)
        for n in range(coords.shape[0]):
            for p in range(coords.shape[1]):
                coords[n, p] = self.dark_parse(hm[n][p], coords[n][p])
        return coords

    def get_final_preds(self, heatmaps, center, scale, kernelsize=3):
        """
        The highest heatvalue location with a quarter offset in the
        direction from the highest response to the second highest response.
        Args:
            heatmaps (numpy.ndarray): The predicted heatmaps
            center (numpy.ndarray): The boxes center
            scale (numpy.ndarray): The scale factor
        Returns:
            preds: numpy.ndarray([batch_size, num_joints, 2]), keypoints coords
            maxvals: numpy.ndarray([batch_size, num_joints, 1]), the maximum confidence of the keypoints
        """
        coords, maxvals = self.get_max_preds(heatmaps)

        heatmap_height = heatmaps.shape[2]
        heatmap_width = heatmaps.shape[3]

        if self.use_dark:
            coords = self.dark_postprocess(heatmaps, coords, kernelsize)
        else:
            for n in range(coords.shape[0]):
                for p in range(coords.shape[1]):
                    hm = heatmaps[n][p]
                    px = int(math.floor(coords[n][p][0] + 0.5))
                    py = int(math.floor(coords[n][p][1] + 0.5))
                    if 1 < px < heatmap_width - 1 and 1 < py < heatmap_height - 1:
                        diff = np.array([
                            hm[py][px + 1] - hm[py][px - 1],
                            hm[py + 1][px] - hm[py - 1][px]
                        ])
                        coords[n][p] += np.sign(diff) * .25
        preds = coords.copy()

        # Transform back
        for i in range(coords.shape[0]):
            preds[i] = transform_preds(coords[i], center[i], scale[i],
                                       [heatmap_width, heatmap_height])

        return preds, maxvals

    def __call__(self, output, center, scale):
        preds, maxvals = self.get_final_preds(np.array(output), center, scale)
        outputs = [[
            np.concatenate(
                (preds, maxvals), axis=-1), np.mean(
                    maxvals, axis=1)
        ]]
        return outputs


def keypoint_post_process(data, data_input, exe, val_program, fetch_targets,
                          outs):
    data_input['image'] = np.flip(data_input['image'], [3])
    output_flipped = exe.run(val_program,
                             feed=data_input,
                             fetch_list=fetch_targets,
                             return_numpy=False)

    output_flipped = np.array(output_flipped[0])
    flip_perm = [[1, 2], [3, 4], [5, 6], [7, 8], [9, 10], [11, 12], [13, 14],
                 [15, 16]]
    output_flipped = flip_back(output_flipped, flip_perm)
    output_flipped[:, :, :, 1:] = copy.copy(output_flipped)[:, :, :, 0:-1]
    hrnet_outputs = (np.array(outs[0]) + output_flipped) * 0.5
    imshape = (
        np.array(data['im_shape']))[:, ::-1] if 'im_shape' in data else None
    center = np.array(data['center']) if 'center' in data else np.round(
        imshape / 2.)
    scale = np.array(data['scale']) if 'scale' in data else imshape / 200.
    post_process = HRNetPostProcess()
    outputs = post_process(hrnet_outputs, center, scale)
    return {'keypoint': outputs}