《动手学深度学习》(PyTorch版)代码注释 - 47 【Image_augmentation】

说明

本博客代码来自开源项目：《动手学深度学习》(PyTorch版)
并且在博主学习的理解上对代码进行了大量注释，方便理解各个函数的原理和用途

配置环境

使用环境：python3.8
平台：Windows10
IDE：PyCharm

此节说明

此节对应书本上9.4节
此节功能为：锚框
由于此节相对复杂，代码注释量较多

代码

# 本书链接https://tangshusen.me/Dive-into-DL-PyTorch/#/
# 锚框
# 注释：黄文俊
# E-mail：hurri_cane@qq.com

from matplotlib import pyplot as plt
from PIL import Image
import numpy as np
import math
import torch

import sys
sys.path.append("..")
import d2lzh_pytorch as d2l
print(torch.__version__) # 1.2.0


d2l.set_figsize()
img = Image.open('F:/PyCharm/Learning_pytorch/data/img/catdog.jpg')
w, h = img.size
print("w = %d, h = %d" % (w, h)) # w = 728, h = 561

# 本函数已保存在d2lzh_pytorch包中方便以后使用
def MultiBoxPrior(feature_map, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5]):
    """
        feature_map: torch tensor, Shape: [N, C, H, W].
        sizes: List of sizes (0~1) of generated MultiBoxPriores.
        ratios: List of aspect ratios (non-negative) of generated MultiBoxPriores.
    Returns:
        anchors of shape (1, num_anchors, 4). 由于batch里每个都一样, 所以第一维为1
    """
    pairs = []  # pair of (size, sqrt(ration))
    for r in ratios:
        pairs.append([sizes[0], math.sqrt(r)])
    for s in sizes[1:]:
        pairs.append([s, math.sqrt(ratios[0])])

    pairs = np.array(pairs)

    ss1 = pairs[:, 0] * pairs[:, 1]     # size * sqrt(ration)
    ss2 = pairs[:, 0] / pairs[:, 1]     # size / sqrt(ration)

    base_anchors = np.stack([-ss1, -ss2, ss1, ss2], axis=1) / 2
    # 从中心点出发的半边长度

    h, w = feature_map.shape[-2:]
    shifts_x = np.arange(0, w) / w
    shifts_y = np.arange(0, h) / h
    shift_x, shift_y = np.meshgrid(shifts_x, shifts_y)
    # 生成网格

    shift_x = shift_x.reshape(-1)
    shift_y = shift_y.reshape(-1)
    shifts = np.stack((shift_x, shift_y, shift_x, shift_y), axis=1)

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

    return torch.tensor(anchors, dtype=torch.float32).view(1, -1, 4)


X = torch.Tensor(1, 3, h, w)  # 构造输入数据
Y = MultiBoxPrior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])
print(Y.shape)  # torch.Size([1, 2042040, 4])

boxes = Y.reshape((h, w, 5, 4))
print(boxes[250, 250, 0, :])    # * torch.tensor([w, h, w, h], dtype=torch.float32)


# 在图像上画出多个边界框
# 本函数已保存在d2lzh_pytorch包中方便以后使用
def show_bboxes(axes, bboxes, labels=None, colors=None):
    def _make_list(obj, default_values=None):
        if obj is None:
            obj = default_values
        elif not isinstance(obj, (list, tuple)):
            obj = [obj]
        return obj

    labels = _make_list(labels)
    colors = _make_list(colors, ['b', 'g', 'r', 'm', 'c'])
    for i, bbox in enumerate(bboxes):
        color = colors[i % len(colors)] # 取余
        rect = d2l.bbox_to_rect(bbox.detach().cpu().numpy(), color)
        axes.add_patch(rect)
        if labels and len(labels) > i:
            text_color = 'k' if color == 'w' else 'w'
            axes.text(rect.xy[0], rect.xy[1], labels[i],
                      va='center', ha='center', fontsize=6, color=text_color,
                      bbox=dict(facecolor=color, lw=0))

d2l.set_figsize()
fig = d2l.plt.imshow(img)
bbox_scale = torch.tensor([[w, h, w, h]], dtype=torch.float32)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,
            ['s=0.75, r=1', 's=0.75, r=2', 's=0.55, r=0.5', 's=0.5, r=1', 's=0.25, r=1'])


plt.show()
print("*"*50)


# 9.4.2 交并比（IOU）

# 以下函数已保存在d2lzh_pytorch包中方便以后使用
# 参考https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Object-Detection/blob/master/utils.py#L356
def compute_intersection(set_1, set_2):
    """
    计算anchor之间的交集
    Args:
        set_1: a tensor of dimensions (n1, 4), anchor表示成(xmin, ymin, xmax, ymax)
        set_2: a tensor of dimensions (n2, 4), anchor表示成(xmin, ymin, xmax, ymax)
    Returns:
        intersection of each of the boxes in set 1 with respect to each of the boxes in set 2, shape: (n1, n2)
    """
    # PyTorch auto-broadcasts singleton dimensions
    lower_bounds = torch.max(set_1[:, :2].unsqueeze(1), set_2[:, :2].unsqueeze(0))  # (n1, n2, 2)
    upper_bounds = torch.min(set_1[:, 2:].unsqueeze(1), set_2[:, 2:].unsqueeze(0))  # (n1, n2, 2)
    # 在指定维度上增加一个维度
    intersection_dims = torch.clamp(upper_bounds - lower_bounds, min=0)  # (n1, n2, 2)
    # torch.clamp(input, min, max, out=None) → Tensor
    # 将输入input张量每个元素的夹紧到区间 [min,max][min,max]，并返回结果到一个新张量。
    return intersection_dims[:, :, 0] * intersection_dims[:, :, 1]  # (n1, n2)


def compute_jaccard(set_1, set_2):
    """
    计算anchor之间的Jaccard系数(IoU)
    Args:
        set_1: a tensor of dimensions (n1, 4), anchor表示成(xmin, ymin, xmax, ymax)
        set_2: a tensor of dimensions (n2, 4), anchor表示成(xmin, ymin, xmax, ymax)
    Returns:
        Jaccard Overlap of each of the boxes in set 1 with respect to each of the boxes in set 2, shape: (n1, n2)
    """
    # Find intersections
    intersection = compute_intersection(set_1, set_2)  # (n1, n2)

    # Find areas of each box in both sets
    areas_set_1 = (set_1[:, 2] - set_1[:, 0]) * (set_1[:, 3] - set_1[:, 1])  # (n1)
    areas_set_2 = (set_2[:, 2] - set_2[:, 0]) * (set_2[:, 3] - set_2[:, 1])  # (n2)

    # Find the union
    # PyTorch auto-broadcasts singleton dimensions
    union = areas_set_1.unsqueeze(1) + areas_set_2.unsqueeze(0) - intersection  # (n1, n2)

    return intersection / union  # (n1, n2)




bbox_scale = torch.tensor((w, h, w, h), dtype=torch.float32)
ground_truth = torch.tensor([[0, 0.1, 0.08, 0.52, 0.92],
                            [1, 0.55, 0.2, 0.9, 0.88]])
anchors = torch.tensor([[0, 0.1, 0.2, 0.3], [0.15, 0.2, 0.4, 0.4],
                        [0.63, 0.05, 0.88, 0.98], [0.66, 0.45, 0.8, 0.8],
                        [0.57, 0.3, 0.92, 0.9]])

fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, ground_truth[:, 1:] * bbox_scale, ['dog', 'cat'], 'k')
show_bboxes(fig.axes, anchors * bbox_scale, ['0', '1', '2', '3', '4']);
plt.show()

# 为锚框标注类别和偏移量
# 以下函数已保存在d2lzh_pytorch包中方便以后使用
def assign_anchor(bb, anchor, jaccard_threshold=0.5):
    """
    Args:
        bb: 真实边界框(bounding box), shape:（nb, 4）
        anchor: 待分配的anchor, shape:（na, 4）
        jaccard_threshold: 预先设定的阈值
    Returns:
        assigned_idx: shape: (na, ), 每个anchor分配的真实bb对应的索引, 若未分配任何bb则为-1
    """
    na = anchor.shape[0]
    nb = bb.shape[0]
    jaccard = compute_jaccard(anchor, bb).detach().cpu().numpy()    # shape: (na, nb)
    assigned_idx = np.ones(na) * -1  # 初始全为-1

    # 先为每个bb分配一个anchor(不要求满足jaccard_threshold)
    jaccard_cp = jaccard.copy()
    for j in range(nb):
        i = np.argmax(jaccard_cp[:, j])
        assigned_idx[i] = j
        jaccard_cp[i, :] = float("-inf")    # 赋值为负无穷, 相当于去掉这一行

    # 处理还未被分配的anchor, 要求满足jaccard_threshold
    for i in range(na):
        if assigned_idx[i] == -1:
            j = np.argmax(jaccard[i, :])
            if jaccard[i, j] >= jaccard_threshold:
                assigned_idx[i] = j

    return torch.tensor(assigned_idx, dtype=torch.long)

def xy_to_cxcy(xy):
    """
    Args:
        xy: bounding boxes in boundary coordinates, a tensor of size (n_boxes, 4)
    Returns:
        bounding boxes in center-size coordinates, a tensor of size (n_boxes, 4)
    """
    return torch.cat([(xy[:, 2:] + xy[:, :2]) / 2,  # c_x, c_y
                      xy[:, 2:] - xy[:, :2]], 1)  # w, h

def MultiBoxTarget(anchor, label):
    """
    Args:
        anchor: torch tensor, 输入的锚框, 一般是通过MultiBoxPrior生成, shape:（1，锚框总数，4）
        label: 真实标签, shape为(bn, 每张图片最多的真实锚框数, 5)
               第二维中，如果给定图片没有这么多锚框, 可以先用-1填充空白, 最后一维中的元素为[类别标签, 四个坐标值]
    Returns:
        列表, [bbox_offset, bbox_mask, cls_labels]
        bbox_offset: 每个锚框的标注偏移量，形状为(bn，锚框总数*4)
        bbox_mask: 形状同bbox_offset, 每个锚框的掩码, 一一对应上面的偏移量, 负类锚框(背景)对应的掩码均为0, 正类锚框的掩码均为1
        cls_labels: 每个锚框的标注类别, 其中0表示为背景, 形状为(bn，锚框总数)
    """
    assert len(anchor.shape) == 3 and len(label.shape) == 3
    bn = label.shape[0]

    def MultiBoxTarget_one(anc, lab, eps=1e-6):
        """
        MultiBoxTarget函数的辅助函数, 处理batch中的一个
        Args:
            anc: shape of (锚框总数, 4)
            lab: shape of (真实锚框数, 5), 5代表[类别标签, 四个坐标值]
            eps: 一个极小值, 防止log0
        Returns:
            offset: (锚框总数*4, )
            bbox_mask: (锚框总数*4, ), 0代表背景, 1代表非背景
            cls_labels: (锚框总数, 4), 0代表背景
        """
        an = anc.shape[0]
        assigned_idx = assign_anchor(lab[:, 1:], anc)   # (锚框总数, )
        # 将真实锚框的位置代入assign_anchor函数，而不代入真实锚框的编号
        bbox_mask = ((assigned_idx >= 0).float().unsqueeze(-1)).repeat(1, 4)    # (锚框总数, 4)
        # .repeat(1, 4)第一列元素重复4次

        cls_labels = torch.zeros(an, dtype=torch.long)  # 0表示背景
        assigned_bb = torch.zeros((an, 4), dtype=torch.float32) # 所有anchor对应的bb坐标
        for i in range(an):
            bb_idx = assigned_idx[i]
            if bb_idx >= 0: # 即非背景
                cls_labels[i] = lab[bb_idx, 0].long().item() + 1 # 注意要加一
                assigned_bb[i, :] = lab[bb_idx, 1:]

        center_anc = xy_to_cxcy(anc) # (center_x, center_y, w, h)
        center_assigned_bb = xy_to_cxcy(assigned_bb)

        offset_xy = 10.0 * (center_assigned_bb[:, :2] - center_anc[:, :2]) / center_anc[:, 2:]
        offset_wh = 5.0 * torch.log(eps + center_assigned_bb[:, 2:] / center_anc[:, 2:])
        offset = torch.cat([offset_xy, offset_wh], dim = 1) * bbox_mask # (锚框总数, 4)

        return offset.view(-1), bbox_mask.view(-1), cls_labels

    batch_offset = []
    batch_mask = []
    batch_cls_labels = []
    for b in range(bn):
        offset, bbox_mask, cls_labels = MultiBoxTarget_one(anchor[0, :, :], label[b, :, :])

        batch_offset.append(offset)
        batch_mask.append(bbox_mask)
        batch_cls_labels.append(cls_labels)

    bbox_offset = torch.stack(batch_offset)
    bbox_mask = torch.stack(batch_mask)
    cls_labels = torch.stack(batch_cls_labels)

    return [bbox_offset, bbox_mask, cls_labels]

# 我们通过unsqueeze函数为锚框和真实边界框添加样本维。
labels = MultiBoxTarget(anchors.unsqueeze(dim=0),
                        ground_truth.unsqueeze(dim=0))

print(labels)
print("*"*50)

# 9.4.4 输出预测边界框


# 非极大值抑制
# 以下函数已保存在d2lzh_pytorch包中方便以后使用
from collections import namedtuple
Pred_BB_Info = namedtuple("Pred_BB_Info", ["index", "class_id", "confidence", "xyxy"])

def non_max_suppression(bb_info_list, nms_threshold = 0.5):
    """
    非极大抑制处理预测的边界框
    Args:
        bb_info_list: Pred_BB_Info的列表, 包含预测类别、置信度等信息
        nms_threshold: 阈值
    Returns:
        output: Pred_BB_Info的列表, 只保留过滤后的边界框信息
    """
    output = []
    # 先根据置信度从高到低排序
    sorted_bb_info_list = sorted(bb_info_list, key = lambda x: x.confidence, reverse=True)

    while len(sorted_bb_info_list) != 0:
        best = sorted_bb_info_list.pop(0)
        output.append(best)

        if len(sorted_bb_info_list) == 0:
            break

        bb_xyxy = []
        for bb in sorted_bb_info_list:
            bb_xyxy.append(bb.xyxy)

        iou = compute_jaccard(torch.tensor([best.xyxy]),
                              torch.tensor(bb_xyxy))[0] # shape: (len(sorted_bb_info_list), )

        n = len(sorted_bb_info_list)
        sorted_bb_info_list = [sorted_bb_info_list[i] for i in range(n) if iou[i] <= nms_threshold]
    return output

def MultiBoxDetection(cls_prob, loc_pred, anchor, nms_threshold = 0.5):
    """
    Args:
        cls_prob: 经过softmax后得到的各个锚框的预测概率, shape:(bn, 预测总类别数+1, 锚框个数)
        loc_pred: 预测的各个锚框的偏移量, shape:(bn, 锚框个数*4)
        anchor: MultiBoxPrior输出的默认锚框, shape: (1, 锚框个数, 4)
        nms_threshold: 非极大抑制中的阈值
    Returns:
        所有锚框的信息, shape: (bn, 锚框个数, 6)
        每个锚框信息由[class_id, confidence, xmin, ymin, xmax, ymax]表示
        class_id=-1 表示背景或在非极大值抑制中被移除了
    """
    assert len(cls_prob.shape) == 3 and len(loc_pred.shape) == 2 and len(anchor.shape) == 3
    bn = cls_prob.shape[0]

    def MultiBoxDetection_one(c_p, l_p, anc, nms_threshold = 0.5):
        """
        MultiBoxDetection的辅助函数, 处理batch中的一个
        Args:
            c_p: (预测总类别数+1, 锚框个数)
            l_p: (锚框个数*4, )
            anc: (锚框个数, 4)
            nms_threshold: 非极大抑制中的阈值
        Return:
            output: (锚框个数, 6)
        """
        pred_bb_num = c_p.shape[1]
        anc = (anc + l_p.view(pred_bb_num, 4)).detach().cpu().numpy()   # 加上偏移量

        confidence, class_id = torch.max(c_p, 0)
        confidence = confidence.detach().cpu().numpy()
        class_id = class_id.detach().cpu().numpy()

        pred_bb_info = [Pred_BB_Info(
                            index = i,
                            class_id = class_id[i] - 1, # 正类label从0开始
                            confidence = confidence[i],
                            xyxy=[*anc[i]]) # xyxy是个列表
                        for i in range(pred_bb_num)]

        # 正类的index
        obj_bb_idx = [bb.index for bb in non_max_suppression(pred_bb_info, nms_threshold)]

        output = []
        for bb in pred_bb_info:
            output.append([
                (bb.class_id if bb.index in obj_bb_idx else -1.0),
                bb.confidence,
                *bb.xyxy
            ])

        return torch.tensor(output) # shape: (锚框个数, 6)

    batch_output = []
    for b in range(bn):
        batch_output.append(MultiBoxDetection_one(cls_prob[b], loc_pred[b], anchor[0], nms_threshold))

    return torch.stack(batch_output)

anchors = torch.tensor([[0.1, 0.08, 0.52, 0.92], [0.08, 0.2, 0.56, 0.95],
                        [0.15, 0.3, 0.62, 0.91], [0.55, 0.2, 0.9, 0.88]])
offset_preds = torch.tensor([0.0] * (4 * len(anchors)))
cls_probs = torch.tensor([[0., 0., 0., 0.,],  # 背景的预测概率
                          [0.9, 0.8, 0.7, 0.1],  # 狗的预测概率
                          [0.1, 0.2, 0.3, 0.9]])  # 猫的预测概率

fig = d2l.plt.imshow(img)
show_bboxes(fig.axes, anchors * bbox_scale,
            ['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])
plt.show()


output = MultiBoxDetection(
    cls_probs.unsqueeze(dim=0), offset_preds.unsqueeze(dim=0),
    anchors.unsqueeze(dim=0), nms_threshold=0.5)
print(output)

fig = d2l.plt.imshow(img)
for i in output[0].detach().cpu().numpy():
    if i[0] == -1:
        continue
    label = ('dog=', 'cat=')[int(i[0])] + str(i[1])
    show_bboxes(fig.axes, [torch.tensor(i[2:]) * bbox_scale], label)
plt.show()

print("*"*50)