module.py

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

class BBoxTransform(nn.Module):
    
    def __init__(self, mean=None, std=None):
        super(BBoxTransform, self).__init__()
        if mean is None:
            self.mean = torch.from_numpy(np.array([0, 0, 0, 0]).astype(np.float32))
        else:
            self.mean = mean
        if std is None:
            self.std = torch.from_numpy(np.array([0.1, 0.1, 0.2, 0.2]).astype(np.float32))
        else:
            self.std = std

    def forward(self, boxes, deltas):

        widths  = boxes[:, :, 2] - boxes[:, :, 0]
        heights = boxes[:, :, 3] - boxes[:, :, 1]
        ctr_x   = boxes[:, :, 0] + 0.5 * widths
        ctr_y   = boxes[:, :, 1] + 0.5 * heights

        dx = deltas[:, :, 0] * self.std[0] + self.mean[0]
        dy = deltas[:, :, 1] * self.std[1] + self.mean[1]
        dw = deltas[:, :, 2] * self.std[2] + self.mean[2]
        dh = deltas[:, :, 3] * self.std[3] + self.mean[3]

        pred_ctr_x = ctr_x + dx * widths
        pred_ctr_y = ctr_y + dy * heights
        pred_w     = torch.exp(dw) * widths
        pred_h     = torch.exp(dh) * heights

        pred_boxes_x1 = pred_ctr_x - 0.5 * pred_w
        pred_boxes_y1 = pred_ctr_y - 0.5 * pred_h
        pred_boxes_x2 = pred_ctr_x + 0.5 * pred_w
        pred_boxes_y2 = pred_ctr_y + 0.5 * pred_h

        pred_boxes = torch.stack([pred_boxes_x1, pred_boxes_y1, pred_boxes_x2, pred_boxes_y2], dim=2)

        return pred_boxes

class ClipBoxes(nn.Module):

    def __init__(self, width=None, height=None):
        super(ClipBoxes, self).__init__()

    def forward(self, boxes, img):

        batch_size, num_channels, height, width = img.shape

        boxes[:, :, 0] = torch.clamp(boxes[:, :, 0], min=0)
        boxes[:, :, 1] = torch.clamp(boxes[:, :, 1], min=0)

        boxes[:, :, 2] = torch.clamp(boxes[:, :, 2], max=width)
        boxes[:, :, 3] = torch.clamp(boxes[:, :, 3], max=height)
      
        return boxes

class RegressionModel(nn.Module):
    def __init__(self, num_features_in, num_anchors=9, feature_size=256):
        super(RegressionModel, self).__init__()
        
        self.conv1 = nn.Conv2d(num_features_in, feature_size, kernel_size=3, padding=1)
        self.act1 = nn.ReLU()
        self.conv2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act2 = nn.ReLU()
        self.conv3 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act3 = nn.ReLU()
        self.conv4 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act4 = nn.ReLU()
        self.output = nn.Conv2d(feature_size, num_anchors*4, kernel_size=3, padding=1)
    def forward(self, x):
        out = self.conv1(x)
        out = self.act1(out)
        out = self.conv2(out)
        out = self.act2(out)
        out = self.conv3(out)
        out = self.act3(out)
        out = self.conv4(out)
        out = self.act4(out)
        out = self.output(out)
        # out is B x C x W x H, with C = 4*num_anchors
        out = out.permute(0, 2, 3, 1)
        return out.contiguous().view(out.shape[0], -1, 4)

class ClassificationModel(nn.Module):
    def __init__(self, num_features_in, num_anchors=9, num_classes=80, prior=0.01, feature_size=256):
        super(ClassificationModel, self).__init__()
        self.num_classes = num_classes
        self.num_anchors = num_anchors
        
        self.conv1 = nn.Conv2d(num_features_in, feature_size, kernel_size=3, padding=1)
        self.act1 = nn.ReLU()
        self.conv2 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act2 = nn.ReLU()
        self.conv3 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act3 = nn.ReLU()
        self.conv4 = nn.Conv2d(feature_size, feature_size, kernel_size=3, padding=1)
        self.act4 = nn.ReLU()
        self.output = nn.Conv2d(feature_size, num_anchors*num_classes, kernel_size=3, padding=1)
        self.output_act = nn.Sigmoid()
    def forward(self, x):
        out = self.conv1(x)
        out = self.act1(out)
        out = self.conv2(out)
        out = self.act2(out)
        out = self.conv3(out)
        out = self.act3(out)
        out = self.conv4(out)
        out = self.act4(out)
        out = self.output(out)
        out = self.output_act(out)
        # out is B x C x W x H, with C = n_classes + n_anchors
        out1 = out.permute(0, 2, 3, 1)
        batch_size, width, height, channels = out1.shape
        out2 = out1.view(batch_size, width, height, self.num_anchors, self.num_classes)
        return out2.contiguous().view(x.shape[0], -1, self.num_classes)

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

        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([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)

        return torch.from_numpy(all_anchors.astype(np.float32)).to(image.device)

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,
    shapes_callback=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