说明

本文改编转载自：https://zh.d2l.ai/chapter_computer-vision/ssd.html
仅做个人学习记录，如侵删

相关数据集
http://d2l-data.s3-accelerate.amazonaws.com/banana-detection.zip

数据文件结构

• banana-detection
  • bananas_train
    • images
    • label.csv
  • bananas_val
    • images
    • label.csv

目标检测和边界框

%matplotlib inline
 
import sys
import math 
import torch
import torchvision
import numpy as np
from PIL import Image
from torch import nn
from torch.nn import functional as F
from d2l import torch as d2l

d2l.set_figsize()
file_path = '/Users/xx/Pictures/cat4.jpg' 
img = Image.open(file_path)
d2l.plt.imshow(img);  # 加分号只显示图

​

​

边界框

# bbox 是 bounding box的缩写
dog_bbox, cat_bbox = [60, 45, 378, 516], [400, 112, 655, 493]

def bbox_to_rect(bbox, color):  # 本函数已保存在d2lzh_pytorch中方便以后使用
    # 将边界框(左上x, 左上y, 右下x, 右下y)格式转换成matplotlib格式：
    # ((左上x, 左上y), 宽, 高)
    return d2l.plt.Rectangle(
        xy=(bbox[0], bbox[1]), width=bbox[2]-bbox[0], height=bbox[3]-bbox[1],
        fill=False, edgecolor=color, linewidth=2)

fig = d2l.plt.imshow(img)
fig.axes.add_patch(bbox_to_rect(dog_bbox, 'blue'))
fig.axes.add_patch(bbox_to_rect(cat_bbox, 'red'));

​

锚框

生成多个锚框

d2l.set_figsize()
img = Image.open(file_path)  
w, h = img.size
print("w = %d, h = %d" % (w, h))
#     w = 3374, h = 4498

# d2l.plt.imshow(img);  # 加分号只显示图

def MultiBoxPrior(feature_map, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5]):
    """
    # 按照「生成多个锚框」所讲的实现, anchor表示成(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    Args:
        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
    
    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)
    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])
Y.shape
#    torch.Size([1, 75881260, 4])

boxes = Y.reshape((h, w, 5, 4))
boxes[250, 250, 0, :]# * torch.tensor([w, h, w, h], dtype=torch.float32)
# 第一个size和ratio分别为0.75和1, 则宽高均为0.75 = 0.7184 + 0.0316 = 0.8206 - 0.0706
#v    tensor([-0.3009, -0.3194,  0.4491,  0.4306])

# 本函数已保存在 d2l pytorch包中 
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)]
        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'])

​

交并比

代码来自：https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Object-Detection/blob/master/utils.py#L356

# 以下函数已保存在d2l pytorch包中 
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)
    intersection_dims = torch.clamp(upper_bounds - lower_bounds, min=0)  # (n1, n2, 2)
    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)

标注训练集的锚框

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']);

compute_jaccard(anchors, ground_truth[:, 1:]) # 验证一下写的compute_jaccard函数

tensor([[0.0536, 0.0000],
        [0.1417, 0.0000],
        [0.0000, 0.5657],
        [0.0000, 0.2059],
        [0.0000, 0.7459]])

# 以下函数已保存在 d2l pytorch包中方便以后使用
def assign_anchor(bb, anchor, jaccard_threshold=0.5):
    """
    # 按照「9.4.1. 生成多个锚框」图9.3所讲为每个anchor分配真实的bb, anchor表示成归一化(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    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):
    """
    将(x_min, y_min, x_max, y_max)形式的anchor转换成(center_x, center_y, w, h)形式的.
    https://github.com/sgrvinod/a-PyTorch-Tutorial-to-Object-Detection/blob/master/utils.py
    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):
    """
    # 按照「9.4.1. 生成多个锚框」所讲的实现, anchor表示成归一化(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    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, )
        bbox_mask = ((assigned_idx >= 0).float().unsqueeze(-1)).repeat(1, 4) # (锚框总数, 4)

        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]

labels = MultiBoxTarget(anchors.unsqueeze(dim=0),
                        ground_truth.unsqueeze(dim=0))

labels[2]
# tensor([[0, 1, 2, 0, 2]])

 
labels[1]
# tensor([[0., 0., 0., 0., 1., 1., 1., 1., 1., 1., 1., 1., 0., 0., 0., 0., 1., 1., 1., 1.]])

 
labels[0]

tensor([[-0.0000e+00, -0.0000e+00, -0.0000e+00, -0.0000e+00,  1.4000e+00,
          1.0000e+01,  2.5940e+00,  7.1754e+00, -1.2000e+00,  2.6882e-01,
          1.6824e+00, -1.5655e+00, -0.0000e+00, -0.0000e+00, -0.0000e+00,
         -0.0000e+00, -5.7143e-01, -1.0000e+00,  4.1723e-06,  6.2582e-01]])

输出预测边界框

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'])

​

# 以下函数已保存在 d2l pytorch包中 
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):
    """
    # 按照「9.4.1. 生成多个锚框」所讲的实现, anchor表示成归一化(xmin, ymin, xmax, ymax).
    https://zh.d2l.ai/chapter_computer-vision/anchor.html
    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)

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

tensor([[[ 0.0000,  0.9000,  0.1000,  0.0800,  0.5200,  0.9200],
         [-1.0000,  0.8000,  0.0800,  0.2000,  0.5600,  0.9500],
         [-1.0000,  0.7000,  0.1500,  0.3000,  0.6200,  0.9100],
         [ 1.0000,  0.9000,  0.5500,  0.2000,  0.9000,  0.8800]]])

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)

​

多尺度目标检测

img = Image.open(file_path)
w, h = img.size
w, h   # (3374, 4498)

d2l.set_figsize()

def display_anchors(fmap_w, fmap_h, s):
    # 前两维的取值不影响输出结果(原书这里是(1, 10, fmap_w, fmap_h), 我认为错了)
    fmap = torch.zeros((1, 10, fmap_h, fmap_w), dtype=torch.float32)
    
    # 平移所有锚框使均匀分布在图片上
    offset_x, offset_y = 1.0/fmap_w, 1.0/fmap_h
    anchors = MultiBoxPrior(fmap, sizes=s, ratios=[1, 2, 0.5]) + \
        torch.tensor([offset_x/2, offset_y/2, offset_x/2, offset_y/2])
    
    bbox_scale = torch.tensor([[w, h, w, h]], dtype=torch.float32)
    d2l.show_bboxes(d2l.plt.imshow(img).axes,
                    anchors[0] * bbox_scale)

display_anchors(fmap_w=4, fmap_h=2, s=[0.15])

​

display_anchors(fmap_w=2, fmap_h=1, s=[0.4])

​

display_anchors(fmap_w=1, fmap_h=1, s=[0.8])

​

# 类别预测层
def cls_predictor(num_inputs, num_anchors, num_classes):
    return nn.Conv2d(num_inputs, num_anchors * (num_classes + 1),
                     kernel_size=3, padding=1)

# 边界框预测层
def bbox_predictor(num_inputs, num_anchors):
    return nn.Conv2d(num_inputs, num_anchors * 4, kernel_size=3, padding=1)

# 连结多尺度的预测
def forward(x, block):
    return block(x)

Y1 = forward(torch.zeros((2, 8, 20, 20)), cls_predictor(8, 5, 10))
Y2 = forward(torch.zeros((2, 16, 10, 10)), cls_predictor(16, 3, 10))
Y1.shape, Y2.shape
# (torch.Size([2, 55, 20, 20]), torch.Size([2, 33, 10, 10]))

def flatten_pred(pred):
    return torch.flatten(pred.permute(0, 2, 3, 1), start_dim=1)

def concat_preds(preds):
    return torch.cat([flatten_pred(p) for p in preds], dim=1)

concat_preds([Y1, Y2]).shape
#    torch.Size([2, 25300])

# 高和宽减半块
def down_sample_blk(in_channels, out_channels):
    blk = []
    for _ in range(2):
        blk.append(nn.Conv2d(in_channels, out_channels,
                             kernel_size=3, padding=1))
        blk.append(nn.BatchNorm2d(out_channels))
        blk.append(nn.ReLU())
        in_channels = out_channels
    blk.append(nn.MaxPool2d(2))
    return nn.Sequential(*blk)

forward(torch.zeros((2, 3, 20, 20)), down_sample_blk(3, 10)).shape
#    torch.Size([2, 10, 10, 10])

# 基本网络块
def base_net():
    blk = []
    num_filters = [3, 16, 32, 64]
    for i in range(len(num_filters) - 1):
        blk.append(down_sample_blk(num_filters[i], num_filters[i+1]))
    return nn.Sequential(*blk)

forward(torch.zeros((2, 3, 256, 256)), base_net()).shape
#    torch.Size([2, 64, 32, 32])

# 完整的模型
def get_blk(i):
    if i == 0:
        blk = base_net()
    elif i == 1:
        blk = down_sample_blk(64, 128)
    elif i == 4:
        blk = nn.AdaptiveMaxPool2d((1,1))
    else:
        blk = down_sample_blk(128, 128)
    return blk

def blk_forward(X, blk, size, ratio, cls_predictor, bbox_predictor):
    Y = blk(X)
    anchors = d2l.multibox_prior(Y, sizes=size, ratios=ratio)
    cls_preds = cls_predictor(Y)
    bbox_preds = bbox_predictor(Y)
    return (Y, anchors, cls_preds, bbox_preds)

sizes = [[0.2, 0.272], [0.37, 0.447], [0.54, 0.619], [0.71, 0.79],
         [0.88, 0.961]]
ratios = [[1, 2, 0.5]] * 5
num_anchors = len(sizes[0]) + len(ratios[0]) - 1

完整的模型 TinySSD

# 定义完整的模型 TinySSD
class TinySSD(nn.Module):
    def __init__(self, num_classes, **kwargs):
        super(TinySSD, self).__init__(**kwargs)
        self.num_classes = num_classes
        idx_to_in_channels = [64, 128, 128, 128, 128]
        
        for i in range(5):
            # 即赋值语句self.blk_i=get_blk(i)
            setattr(self, f'blk_{
      
      i}', get_blk(i))
            setattr(self, f'cls_{
      
      i}', cls_predictor(idx_to_in_channels[i],
                                                    num_anchors, num_classes))
            setattr(self, f'bbox_{
      
      i}', bbox_predictor(idx_to_in_channels[i],
                                                      num_anchors))

    def forward(self, X):
        anchors, cls_preds, bbox_preds = [None] * 5, [None] * 5, [None] * 5
        
        for i in range(5):
            # getattr(self,'blk_%d'%i)即访问self.blk_i
            X, anchors[i], cls_preds[i], bbox_preds[i] = blk_forward(
                X, getattr(self, f'blk_{
      
      i}'), sizes[i], ratios[i],
                getattr(self, f'cls_{
      
      i}'), getattr(self, f'bbox_{
      
      i}'))
            
        anchors = torch.cat(anchors, dim=1)
        cls_preds = concat_preds(cls_preds)
        cls_preds = cls_preds.reshape(
            cls_preds.shape[0], -1, self.num_classes + 1)
        bbox_preds = concat_preds(bbox_preds)
        
        return anchors, cls_preds, bbox_preds

net = TinySSD(num_classes=1)
X = torch.zeros((32, 3, 256, 256))
anchors, cls_preds, bbox_preds = net(X)

print('output anchors:', anchors.shape)
print('output class preds:', cls_preds.shape)
print('output bbox preds:', bbox_preds.shape)

output anchors: torch.Size([1, 5444, 4])
output class preds: torch.Size([32, 5444, 2])
output bbox preds: torch.Size([32, 21776])

# 训练模型
batch_size = 32
train_iter, _ = d2l.load_data_bananas(batch_size)

Downloading ../data/banana-detection.zip from http://d2l-data.s3-accelerate.amazonaws.com/banana-detection.zip...
read 1000 training examples
read 100 validation examples

device, net = d2l.try_gpu(), TinySSD(num_classes=1)
trainer = torch.optim.SGD(net.parameters(), lr=0.2, weight_decay=5e-4)

# 定义损失函数和评价函数
cls_loss = nn.CrossEntropyLoss(reduction='none')
bbox_loss = nn.L1Loss(reduction='none')

def calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels, bbox_masks):
    batch_size, num_classes = cls_preds.shape[0], cls_preds.shape[2]
    cls = cls_loss(cls_preds.reshape(-1, num_classes),
                   cls_labels.reshape(-1)).reshape(batch_size, -1).mean(dim=1)
    bbox = bbox_loss(bbox_preds * bbox_masks,
                     bbox_labels * bbox_masks).mean(dim=1)
    return cls + bbox

def cls_eval(cls_preds, cls_labels):
    # 由于类别预测结果放在最后一维，argmax需要指定最后一维。
    return float((cls_preds.argmax(dim=-1).type(
        cls_labels.dtype) == cls_labels).sum() )

def bbox_eval(bbox_preds, bbox_labels, bbox_masks):
    return float((torch.abs((bbox_labels - bbox_preds) * bbox_masks)).sum())

# 训练模型
num_epochs, timer = 20, d2l.Timer()
animator = d2l.Animator(xlabel='epoch', xlim=[1, num_epochs],
                        legend=['class error', 'bbox mae'])
net = net.to(device)

for epoch in range(num_epochs):
    # 训练精确度的和，训练精确度的和中的示例数
    # 绝对误差的和，绝对误差的和中的示例数
    metric = d2l.Accumulator(4)
    net.train()
    for features, target in train_iter:
        timer.start()
        trainer.zero_grad()
        X, Y = features.to(device), target.to(device)
        
        # 生成多尺度的锚框，为每个锚框预测类别和偏移量
        anchors, cls_preds, bbox_preds = net(X)
        
        # 为每个锚框标注类别和偏移量
        bbox_labels, bbox_masks, cls_labels = d2l.multibox_target(anchors, Y)
        
        # 根据类别和偏移量的预测和标注值计算损失函数
        l = calc_loss(cls_preds, cls_labels, bbox_preds, bbox_labels,
                      bbox_masks)
        l.mean().backward()
        trainer.step()
        metric.add(cls_eval(cls_preds, cls_labels), cls_labels.numel(),
                   bbox_eval(bbox_preds, bbox_labels, bbox_masks),
                   bbox_labels.numel())
                   
    cls_err, bbox_mae = 1 - metric[0] / metric[1], metric[2] / metric[3]
    animator.add(epoch + 1, (cls_err, bbox_mae))
    
print(f'class err {
      
      cls_err:.2e}, bbox mae {
      
      bbox_mae:.2e}')
print(f'{
      
      len(train_iter.dataset) / timer.stop():.1f} examples/sec on '
      f'{
      
      str(device)}')

class err 3.39e-03, bbox mae 3.32e-03
729.9 examples/sec on cpu

# 预测目标

def predict(X):
    net.eval()
    anchors, cls_preds, bbox_preds = net(X.to(device))
    cls_probs = F.softmax(cls_preds, dim=2).permute(0, 2, 1)
    output = d2l.multibox_detection(cls_probs, bbox_preds, anchors)
    idx = [i for i, row in enumerate(output[0]) if row[0] != -1]
    return output[0, idx]

def display(img, output, threshold):
    d2l.set_figsize((5, 5))
    fig = d2l.plt.imshow(img)
    for row in output:
        score = float(row[1])
        if score < threshold:
            continue
        h, w = img.shape[0:2]
        bbox = [row[2:6] * torch.tensor((w, h, w, h), device=row.device)]
        d2l.show_bboxes(fig.axes, bbox, '%.2f' % score, 'w')

file_path = '/Users/xx/Downloads/dog2.jpeg' 
file_path = '/Users/xx/Documents/nlp_data/banana-detection/bananas_val/images/11.png'
X = torchvision.io.read_image(file_path).unsqueeze(0).float()
img = X.squeeze(0).permute(1, 2, 0).long()

output = predict(X)

display(img, output.cpu(), threshold=0.9)

2023-03-31(五)