faceserver/vectorizer/identification/anchors.py

# -*- coding: utf-8 -*-
"""
   Copyright 2019 Petr Masopust, Aprar s.r.o.

   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.

   Adopted code from https://github.com/rainofmine/Face_Attention_Network
"""

import numpy as np
import torch
import torch.nn as nn


class Anchors(nn.Module):
    def __init__(self, pyramid_levels=None, strides=None, sizes=None, ratios=None, scales=None, is_cuda=True):
        super(Anchors, self).__init__()

        self.is_cuda = is_cuda
        if pyramid_levels is None:
            self.pyramid_levels = [3, 4, 5, 6, 7]
        if strides is None:
            self.strides = [2 ** x for x in self.pyramid_levels]
        if sizes is None:
            self.sizes = [2 ** (x + 2) for x in self.pyramid_levels]
        if ratios is None:
            # self.ratios = np.array([1., 1.5, 2., 2.5, 3.])
            self.ratios = np.array([0.5, 1., 2.])
        if scales is None:
            self.scales = np.array([2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)])

    def forward(self, image):

        image_shape = image.shape[2:]
        image_shape = np.array(image_shape)
        image_shapes = [(image_shape + 2 ** x - 1) // (2 ** x) for x in self.pyramid_levels]

        # compute anchors over all pyramid levels
        all_anchors = np.zeros((0, 4)).astype(np.float32)

        for idx, p in enumerate(self.pyramid_levels):
            anchors = generate_anchors(base_size=self.sizes[idx], ratios=self.ratios, scales=self.scales)
            shifted_anchors = shift(image_shapes[idx], self.strides[idx], anchors)
            all_anchors = np.append(all_anchors, shifted_anchors, axis=0)

        all_anchors = np.expand_dims(all_anchors, axis=0)
        all_anchors = torch.from_numpy(all_anchors.astype(np.float32))
        if self.is_cuda:
            all_anchors = all_anchors.cuda()

        return all_anchors


def generate_anchors(base_size=16, ratios=None, scales=None):
    """
    Generate anchor (reference) windows by enumerating aspect ratios X
    scales w.r.t. a reference window.
    """

    if ratios is None:
        ratios = np.array([0.5, 1, 2])

    if scales is None:
        scales = np.array([2 ** 0, 2 ** (1.0 / 3.0), 2 ** (2.0 / 3.0)])

    num_anchors = len(ratios) * len(scales)

    # initialize output anchors
    anchors = np.zeros((num_anchors, 4))

    # scale base_size
    anchors[:, 2:] = base_size * np.tile(scales, (2, len(ratios))).T

    # compute areas of anchors
    areas = anchors[:, 2] * anchors[:, 3]

    # correct for ratios
    anchors[:, 2] = np.sqrt(areas / np.repeat(ratios, len(scales)))
    anchors[:, 3] = anchors[:, 2] * np.repeat(ratios, len(scales))

    # transform from (x_ctr, y_ctr, w, h) -> (x1, y1, x2, y2)
    anchors[:, 0::2] -= np.tile(anchors[:, 2] * 0.5, (2, 1)).T
    anchors[:, 1::2] -= np.tile(anchors[:, 3] * 0.5, (2, 1)).T

    return anchors


def compute_shape(image_shape, pyramid_levels):
    """Compute shapes based on pyramid levels.

    :param image_shape:
    :param pyramid_levels:
    :return:
    """
    image_shape = np.array(image_shape[:2])
    image_shapes = [(image_shape + 2 ** x - 1) // (2 ** x) for x in pyramid_levels]
    return image_shapes


def anchors_for_shape(
        image_shape,
        pyramid_levels=None,
        ratios=None,
        scales=None,
        strides=None,
        sizes=None,
):
    image_shapes = compute_shape(image_shape, pyramid_levels)

    # compute anchors over all pyramid levels
    all_anchors = np.zeros((0, 4))
    for idx, p in enumerate(pyramid_levels):
        anchors = generate_anchors(base_size=sizes[idx], ratios=ratios, scales=scales)
        shifted_anchors = shift(image_shapes[idx], strides[idx], anchors)
        all_anchors = np.append(all_anchors, shifted_anchors, axis=0)

    return all_anchors


def shift(shape, stride, anchors):
    shift_x = (np.arange(0, shape[1]) + 0.5) * stride
    shift_y = (np.arange(0, shape[0]) + 0.5) * stride

    shift_x, shift_y = np.meshgrid(shift_x, shift_y)

    shifts = np.vstack((
        shift_x.ravel(), shift_y.ravel(),
        shift_x.ravel(), shift_y.ravel()
    )).transpose()

    # add A anchors (1, A, 4) to
    # cell K shifts (K, 1, 4) to get
    # shift anchors (K, A, 4)
    # reshape to (K*A, 4) shifted anchors
    A = anchors.shape[0]
    K = shifts.shape[0]
    all_anchors = (anchors.reshape((1, A, 4)) + shifts.reshape((1, K, 4)).transpose((1, 0, 2)))
    all_anchors = all_anchors.reshape((K * A, 4))

    return all_anchors