rpn.py

# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved.
import torch
from torch.nn import functional as F
from torch import nn

from torchvision.ops import boxes as box_ops

from . import _utils as det_utils


class AnchorGenerator(nn.Module):
    """
    For a set of image sizes and feature maps, computes a set
    of anchors
    """

    def __init__(
        self,
        sizes=(128, 256, 512),
        aspect_ratios=(0.5, 1.0, 2.0),
    ):
        super(AnchorGenerator, self).__init__()

        if not isinstance(sizes[0], (list, tuple)):
            # TODO change this
            sizes = tuple((s,) for s in sizes)
        if not isinstance(aspect_ratios[0], (list, tuple)):
            aspect_ratios = (aspect_ratios,) * len(sizes)

        assert len(sizes) == len(aspect_ratios)

        self.sizes = sizes
        self.aspect_ratios = aspect_ratios
        self.cell_anchors = None
        self._cache = {}

    @staticmethod
    def generate_anchors(scales, aspect_ratios, device="cpu"):
        scales = torch.as_tensor(scales, dtype=torch.float32, device=device)
        aspect_ratios = torch.as_tensor(aspect_ratios, dtype=torch.float32, device=device)
        h_ratios = torch.sqrt(aspect_ratios)
        w_ratios = 1 / h_ratios

        ws = (w_ratios[:, None] * scales[None, :]).view(-1)
        hs = (h_ratios[:, None] * scales[None, :]).view(-1)

        base_anchors = torch.stack([-ws, -hs, ws, hs], dim=1) / 2
        return base_anchors.round()

    def set_cell_anchors(self, device):
        if self.cell_anchors is not None:
            return self.cell_anchors
        cell_anchors = [
            self.generate_anchors(
                sizes,
                aspect_ratios,
                device
            )
            for sizes, aspect_ratios in zip(self.sizes, self.aspect_ratios)
        ]
        self.cell_anchors = cell_anchors

    def num_anchors_per_location(self):
        return [len(s) * len(a) for s, a in zip(self.sizes, self.aspect_ratios)]

    def grid_anchors(self, grid_sizes, strides):
        anchors = []
        for size, stride, base_anchors in zip(
            grid_sizes, strides, self.cell_anchors
        ):
            grid_height, grid_width = size
            stride_height, stride_width = stride
            device = base_anchors.device
            shifts_x = torch.arange(
                0, grid_width, dtype=torch.float32, device=device
            ) * stride_width
            shifts_y = torch.arange(
                0, grid_height, dtype=torch.float32, device=device
            ) * stride_height
            shift_y, shift_x = torch.meshgrid(shifts_y, shifts_x)
            shift_x = shift_x.reshape(-1)
            shift_y = shift_y.reshape(-1)
            shifts = torch.stack((shift_x, shift_y, shift_x, shift_y), dim=1)

            anchors.append(
                (shifts.view(-1, 1, 4) + base_anchors.view(1, -1, 4)).reshape(-1, 4)
            )

        return anchors

    def cached_grid_anchors(self, grid_sizes, strides):
        key = tuple(grid_sizes) + tuple(strides)
        if key in self._cache:
            return self._cache[key]
        anchors = self.grid_anchors(grid_sizes, strides)
        self._cache[key] = anchors
        return anchors

    def forward(self, image_list, feature_maps):
        grid_sizes = tuple([feature_map.shape[-2:] for feature_map in feature_maps])
        image_size = image_list.tensors.shape[-2:]
        strides = tuple((image_size[0] / g[0], image_size[1] / g[1]) for g in grid_sizes)
        self.set_cell_anchors(feature_maps[0].device)
        anchors_over_all_feature_maps = self.cached_grid_anchors(grid_sizes, strides)
        anchors = []
        for i, (image_height, image_width) in enumerate(image_list.image_sizes):
            anchors_in_image = []
            for anchors_per_feature_map in anchors_over_all_feature_maps:
                anchors_in_image.append(anchors_per_feature_map)
            anchors.append(anchors_in_image)
        anchors = [torch.cat(anchors_per_image) for anchors_per_image in anchors]
        return anchors


class RPNHead(nn.Module):
    """
    Adds a simple RPN Head with classification and regression heads
    """

    def __init__(self, in_channels, num_anchors):
        """
        Arguments:
            in_channels (int): number of channels of the input feature
            num_anchors (int): number of anchors to be predicted
        """
        super(RPNHead, self).__init__()
        self.conv = nn.Conv2d(
            in_channels, in_channels, kernel_size=3, stride=1, padding=1
        )
        self.cls_logits = nn.Conv2d(in_channels, num_anchors, kernel_size=1, stride=1)
        self.bbox_pred = nn.Conv2d(
            in_channels, num_anchors * 4, kernel_size=1, stride=1
        )

        for l in self.children():
            torch.nn.init.normal_(l.weight, std=0.01)
            torch.nn.init.constant_(l.bias, 0)

    def forward(self, x):
        logits = []
        bbox_reg = []
        for feature in x:
            t = F.relu(self.conv(feature))
            logits.append(self.cls_logits(t))
            bbox_reg.append(self.bbox_pred(t))
        return logits, bbox_reg


def permute_and_flatten(layer, N, A, C, H, W):
    layer = layer.view(N, -1, C, H, W)
    layer = layer.permute(0, 3, 4, 1, 2)
    layer = layer.reshape(N, -1, C)
    return layer


def concat_box_prediction_layers(box_cls, box_regression):
    box_cls_flattened = []
    box_regression_flattened = []
    # for each feature level, permute the outputs to make them be in the
    # same format as the labels. Note that the labels are computed for
    # all feature levels concatenated, so we keep the same representation
    # for the objectness and the box_regression
    for box_cls_per_level, box_regression_per_level in zip(
        box_cls, box_regression
    ):
        N, AxC, H, W = box_cls_per_level.shape
        Ax4 = box_regression_per_level.shape[1]
        A = Ax4 // 4
        C = AxC // A
        box_cls_per_level = permute_and_flatten(
            box_cls_per_level, N, A, C, H, W
        )
        box_cls_flattened.append(box_cls_per_level)

        box_regression_per_level = permute_and_flatten(
            box_regression_per_level, N, A, 4, H, W
        )
        box_regression_flattened.append(box_regression_per_level)
    # concatenate on the first dimension (representing the feature levels), to
    # take into account the way the labels were generated (with all feature maps
    # being concatenated as well)
    box_cls = torch.cat(box_cls_flattened, dim=1).reshape(-1, C)
    box_regression = torch.cat(box_regression_flattened, dim=1).reshape(-1, 4)
    return box_cls, box_regression


class RegionProposalNetwork(torch.nn.Module):

    def __init__(self,
                 anchor_generator,
                 head,
                 #
                 fg_iou_thresh, bg_iou_thresh,
                 batch_size_per_image, positive_fraction,
                 #
                 pre_nms_top_n, post_nms_top_n, nms_thresh):
        """
        Arguments:
        """
        super(RegionProposalNetwork, self).__init__()
        self.anchor_generator = anchor_generator
        self.head = head
        self.box_coder = det_utils.BoxCoder(weights=(1.0, 1.0, 1.0, 1.0))

        # used during training
        self.box_similarity = box_ops.box_iou

        self.proposal_matcher = det_utils.Matcher(
            fg_iou_thresh,
            bg_iou_thresh,
            allow_low_quality_matches=True,
        )

        self.fg_bg_sampler = det_utils.BalancedPositiveNegativeSampler(
            batch_size_per_image, positive_fraction
        )
        # used during testing
        self._pre_nms_top_n = pre_nms_top_n
        self._post_nms_top_n = post_nms_top_n
        self.nms_thresh = nms_thresh
        self.min_size = 0

    @property
    def pre_nms_top_n(self):
        if self.training:
            return self._pre_nms_top_n['training']
        return self._pre_nms_top_n['testing']

    @property
    def post_nms_top_n(self):
        if self.training:
            return self._post_nms_top_n['training']
        return self._post_nms_top_n['testing']

    def assign_targets_to_anchors(self, anchors, targets):
        labels = []
        matched_gt_boxes = []
        for anchors_per_image, targets_per_image in zip(anchors, targets):
            gt_boxes = targets_per_image["boxes"]
            match_quality_matrix = self.box_similarity(gt_boxes, anchors_per_image)
            matched_idxs = self.proposal_matcher(match_quality_matrix)
            # get the targets corresponding GT for each proposal
            # NB: need to clamp the indices because we can have a single
            # GT in the image, and matched_idxs can be -2, which goes
            # out of bounds
            matched_gt_boxes_per_image = gt_boxes[matched_idxs.clamp(min=0)]

            labels_per_image = matched_idxs >= 0
            labels_per_image = labels_per_image.to(dtype=torch.float32)

            # Background (negative examples)
            bg_indices = matched_idxs == self.proposal_matcher.BELOW_LOW_THRESHOLD
            labels_per_image[bg_indices] = 0

            # discard indices that are between thresholds
            inds_to_discard = matched_idxs == self.proposal_matcher.BETWEEN_THRESHOLDS
            labels_per_image[inds_to_discard] = -1

            labels.append(labels_per_image)
            matched_gt_boxes.append(matched_gt_boxes_per_image)
        return labels, matched_gt_boxes

    def _get_top_n_idx(self, objectness, num_anchors_per_level):
        r = []
        offset = 0
        for ob in objectness.split(num_anchors_per_level, 1):
            num_anchors = ob.shape[1]
            pre_nms_top_n = min(self.pre_nms_top_n, num_anchors)
            _, top_n_idx = ob.topk(pre_nms_top_n, dim=1)
            r.append(top_n_idx + offset)
            offset += num_anchors
        return torch.cat(r, dim=1)

    def filter_proposals(self, proposals, objectness, image_shapes, num_anchors_per_level):
        num_images = proposals.shape[0]
        device = proposals.device
        # do not backprop throught objectness
        objectness = objectness.detach()
        objectness = objectness.reshape(num_images, -1)

        levels = [
            torch.full((n,), idx, dtype=torch.int64, device=device)
            for idx, n in enumerate(num_anchors_per_level)
        ]
        levels = torch.cat(levels, 0)
        levels = levels.reshape(1, -1).expand_as(objectness)

        # select top_n boxes independently per level before applying nms
        top_n_idx = self._get_top_n_idx(objectness, num_anchors_per_level)
        batch_idx = torch.arange(num_images, device=device)[:, None]
        objectness = objectness[batch_idx, top_n_idx]
        levels = levels[batch_idx, top_n_idx]
        proposals = proposals[batch_idx, top_n_idx]

        final_boxes = []
        final_scores = []
        for boxes, scores, lvl, img_shape in zip(proposals, objectness, levels, image_shapes):
            boxes = box_ops.clip_boxes_to_image(boxes, img_shape)
            keep = box_ops.remove_small_boxes(boxes, self.min_size)
            boxes, scores, lvl = boxes[keep], scores[keep], lvl[keep]
            # non-maximum suppression, independently done per level
            keep = box_ops.batched_nms(boxes, scores, lvl, self.nms_thresh)
            # keep only topk scoring predictions
            keep = keep[:self.post_nms_top_n]
            boxes, scores = boxes[keep], scores[keep]
            final_boxes.append(boxes)
            final_scores.append(scores)
        return final_boxes, final_scores

    def compute_loss(self, objectness, pred_bbox_deltas, labels, regression_targets):
        """
        Arguments:
            anchors (list[list[BoxList]])
            objectness (list[Tensor])
            pred_bbox_deltas (list[Tensor])
            targets (list[BoxList])

        Returns:
            objectness_loss (Tensor)
            box_loss (Tensor
        """

        sampled_pos_inds, sampled_neg_inds = self.fg_bg_sampler(labels)
        sampled_pos_inds = torch.nonzero(torch.cat(sampled_pos_inds, dim=0)).squeeze(1)
        sampled_neg_inds = torch.nonzero(torch.cat(sampled_neg_inds, dim=0)).squeeze(1)

        sampled_inds = torch.cat([sampled_pos_inds, sampled_neg_inds], dim=0)

        objectness = objectness.flatten()

        labels = torch.cat(labels, dim=0)
        regression_targets = torch.cat(regression_targets, dim=0)

        box_loss = F.l1_loss(
            pred_bbox_deltas[sampled_pos_inds],
            regression_targets[sampled_pos_inds],
            reduction="sum",
        ) / (sampled_inds.numel())

        objectness_loss = F.binary_cross_entropy_with_logits(
            objectness[sampled_inds], labels[sampled_inds]
        )

        return objectness_loss, box_loss

    def forward(self, images, features, targets=None):
        """
        Arguments:
            images (ImageList): images for which we want to compute the predictions
            features (list[Tensor]): features computed from the images that are
                used for computing the predictions. Each tensor in the list
                correspond to different feature levels
            targets (list[BoxList): ground-truth boxes present in the image (optional)

        Returns:
            boxes (list[BoxList]): the predicted boxes from the RPN, one BoxList per
                image.
            losses (dict[Tensor]): the losses for the model during training. During
                testing, it is an empty dict.
        """
        # RPN uses all feature maps that are available
        features = list(features.values())
        objectness, pred_bbox_deltas = self.head(features)
        anchors = self.anchor_generator(images, features)

        num_images = len(anchors)
        num_anchors_per_level = [o[0].numel() for o in objectness]
        objectness, pred_bbox_deltas = \
            concat_box_prediction_layers(objectness, pred_bbox_deltas)
        # apply pred_bbox_deltas to anchors to obtain the decoded proposals
        # note that we detach the deltas because Faster R-CNN do not backprop through
        # the proposals
        proposals = self.box_coder.decode(pred_bbox_deltas.detach(), anchors)
        proposals = proposals.view(num_images, -1, 4)
        boxes, scores = self.filter_proposals(proposals, objectness, images.image_sizes, num_anchors_per_level)

        losses = {}
        if self.training:
            labels, matched_gt_boxes = self.assign_targets_to_anchors(anchors, targets)
            regression_targets = self.box_coder.encode(matched_gt_boxes, anchors)
            loss_objectness, loss_rpn_box_reg = self.compute_loss(
                objectness, pred_bbox_deltas, labels, regression_targets)
            losses = {
                "loss_objectness": loss_objectness,
                "loss_rpn_box_reg": loss_rpn_box_reg,
            }
        return boxes, losses