【论文复现】FCOS：2D目标检测算法

def prepare_targets(self, points, targets):
        object_sizes_of_interest = [ 
            [-1, 64], # 不同的FPN层每层需要规定检测目标的大小
            [64, 128],
            [128, 256],
            [256, 512],
            [512, INF],
        ]
        # 扩展感兴趣区域的事情
        expanded_object_sizes_of_interest = []
        # points指代的是坐标，针对每一个坐标都应该有一个bbox
        for l, points_per_level in enumerate(points):
            object_sizes_of_interest_per_level = \
                points_per_level.new_tensor(object_sizes_of_interest[l])
            expanded_object_sizes_of_interest.append(
                object_sizes_of_interest_per_level[None].expand(len(points_per_level), -1)
            )
        # [22400,2]
        expanded_object_sizes_of_interest = torch.cat(expanded_object_sizes_of_interest, dim=0)
        # [num_points_per_level] 获取不同特征图上具有的点的个数
        num_points_per_level = [len(points_per_level) for points_per_level in points]
        self.num_points_per_level = num_points_per_level
        # 确定5个FPN结构上有多少个点，此时的个数和上述的Iou一致，对于每个点都需要规定一个回归大小的数值
        points_all_level = torch.cat(points, dim=0)
        # 为每个特征图上的点预定义label的bbox的情况
        labels, reg_targets = self.compute_targets_for_locations(
            points_all_level, targets, expanded_object_sizes_of_interest
        )
        # 针对于batch_size个图片，经过backbone，每个图片具有n个点
        for i in range(len(labels)):
            # 按照FPN结构的网格生成相应地结构
            labels[i] = torch.split(labels[i], num_points_per_level, dim=0)
            reg_targets[i] = torch.split(reg_targets[i], num_points_per_level, dim=0)

        labels_level_first = []
        reg_targets_level_first = []
        # points表示不同的特征图
        for level in range(len(points)):
            # 是将不同的batch_size，但是一个层上面的所有点进行拼接
            labels_level_first.append(
                torch.cat([labels_per_im[level] for labels_per_im in labels], dim=0)
            )

            reg_targets_per_level = torch.cat([
                reg_targets_per_im[level]
                for reg_targets_per_im in reg_targets
            ], dim=0)

            if self.norm_reg_targets:
                reg_targets_per_level = reg_targets_per_level / self.fpn_strides[level]
            reg_targets_level_first.append(reg_targets_per_level)
        # 返回一个batch_size中不同特征层上所有的点的拼接，也就是返回五层特征图结构
        return labels_level_first, reg_targets_level_first

# 为每个位置生成一个target bbox的情况
    def compute_targets_for_locations(self, locations, targets, object_sizes_of_interest):
        labels = []
        reg_targets = []
        xs, ys = locations[:, 0], locations[:, 1] # 分别获得每个x,y的取值

        for im_i in range(len(targets)):
            targets_per_im = targets[im_i] # 获取每张图片上的真实bbox有多少个
            # 此时确定的是真值框的模式
            assert targets_per_im.mode == "xyxy"
            bboxes = targets_per_im.bbox # 获得bbox的坐标形式
            labels_per_im = targets_per_im.get_field("labels") # 获取标签
            area = targets_per_im.area() # 获取面积，这里应该都是COCO数据集自带的
            # 预测的是ltrb，来进行计算，此时取值为正
            l = xs[:, None] - bboxes[:, 0][None]
            t = ys[:, None] - bboxes[:, 1][None]
            r = bboxes[:, 2][None] - xs[:, None]
            b = bboxes[:, 3][None] - ys[:, None]
            # [20267,17,4] 17表示此时有多少个bbox，针对于20267个像素，每个像素上可能有17个bbox
            reg_targets_per_im = torch.stack([l, t, r, b], dim=2)

            if self.center_sampling_radius > 0:
                is_in_boxes = self.get_sample_region(
                    bboxes,
                    self.fpn_strides,
                    self.num_points_per_level,
                    xs, ys,
                    radius=self.center_sampling_radius
                )
            else:
                # ltrb本身每个取值都应该是正的，min选取它们的最小值，dim=2表明是在坐标的维度上进行选择
                is_in_boxes = reg_targets_per_im.min(dim=2)[0] > 0
            # 获取四个坐标中最大的一个，其中要保证最大的一个坐标处于确定的坐标范围内
            max_reg_targets_per_im = reg_targets_per_im.max(dim=2)[0]
            # limit the regression range for each location
            is_cared_in_the_level = \
                (max_reg_targets_per_im >= object_sizes_of_interest[:, [0]]) & \
                (max_reg_targets_per_im <= object_sizes_of_interest[:, [1]])
            # 针对于每一个坐标都规定需要回归的面积有area个
            locations_to_gt_area = area[None].repeat(len(locations), 1)
            # 对于不符合要求的将其定义为INF，也就是背景区域
            locations_to_gt_area[is_in_boxes == 0] = INF
            locations_to_gt_area[is_cared_in_the_level == 0] = INF
            # if there are still more than one objects for a location,
            # we choose the one with minimal area
            locations_to_min_area, locations_to_gt_inds = locations_to_gt_area.min(dim=1)
            # 如果还有多个bbox的时候，选取bbox数值最小的一个来进行回归
            reg_targets_per_im = reg_targets_per_im[range(len(locations)), locations_to_gt_inds]
            labels_per_im = labels_per_im[locations_to_gt_inds] # 选择数值最小的标签
            labels_per_im[locations_to_min_area == INF] = 0 # 对不存在的区域设置为背景区域

            labels.append(labels_per_im)
            reg_targets.append(reg_targets_per_im)
        # 此时返回的是所有位置上需要回归的bbox和cls
        
        return labels, reg_targets

conda create --name FCOS
conda activate FCOS

# this installs the right pip and dependencies for the fresh python
conda install ipython

# FCOS and coco api dependencies
pip install ninja yacs cython matplotlib tqdm

# follow PyTorch installation in https://pytorch.org/get-started/locally/
# we give the instructions for CUDA 10.2
conda install pytorch torchvision cudatoolkit=10.2 -c pytorch

export INSTALL_DIR=$PWD

# install pycocotools. Please make sure you have installed cython.
cd $INSTALL_DIR
git clone https://github.com/cocodataset/cocoapi.git
cd cocoapi/PythonAPI
python setup.py build_ext install

# install PyTorch Detection
cd $INSTALL_DIR
git clone https://github.com/tianzhi0549/FCOS.git
cd FCOS

# the following will install the lib with
# symbolic links, so that you can modify
# the files if you want and won't need to
# re-build it
python setup.py build develop --no-deps


unset INSTALL_DIR