23.目标检测基础

1.边缘框实现

import matplotlib.pyplot as plt
import torch
def box_corner_to_center(boxes):x1,y1,x2,y2=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]cx=(x1+x2)/2cy=(y1+y2)/2w=x2-x1h=y2-y1boxes=torch.stack((cx,cy,w,h),axis=-1)return boxes
def box_center_to_corner(boxes):cx,cy,w,h=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]x1=cx-0.5*wy1=cy-0.5*hx2=cx+0.5*wy2=cy+0.5*hboxes=torch.stack((x1,y1,x2,y2),axis=-1)return boxes
def bbox_to_rect(bbox, color):# 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 plt.Rectangle(xy=(bbox[0], bbox[1]), width=bbox[2]-bbox[0], height=bbox[3]-bbox[1],fill=False, edgecolor=color, linewidth=2)
dog_bbox, cat_bbox = [60.0, 45.0, 378.0, 516.0], [400.0, 112.0, 655.0, 493.0]
# boxes=torch.tensor((dog_bbox,cat_bbox))
# box_center_to_corner(box_corner_to_center(boxes))==boxes
img = plt.imread('../img/catdog.jpg')
fig = plt.imshow(img)
fig.axes.add_patch(bbox_to_rect(dog_bbox, 'blue'))
fig.axes.add_patch(bbox_to_rect(cat_bbox, 'red'))

2.目标检测数据集加载

import os
import pandas as pd
import torch
import torchvision
import matplotlib.pyplot as plt
from matplotlib import patches
def read_data_bananas(is_train=True):"""读取香蕉检测数据集中的图像和标签"""data_dir = r"/data/Public/Datasets/d2l-limu/banana-detection"csv_fname = os.path.join(data_dir, 'bananas_train' if is_train else 'bananas_val', 'label.csv')csv_data = pd.read_csv(csv_fname)csv_data = csv_data.set_index('img_name')images, targets = [], []for img_name, target in csv_data.iterrows():images.append(torchvision.io.read_image(os.path.join(data_dir, 'bananas_train' if is_train else'bananas_val', 'images', f'{img_name}')))# 这里的target包含（类别，左上角x，左上角y，右下角x，右下角y），# 其中所有图像都具有相同的香蕉类（索引为0）targets.append(list(target))return images, torch.tensor(targets).unsqueeze(1) / 256class BananasDataset(torch.utils.data.Dataset):"""一个用于加载香蕉检测数据集的自定义数据集"""def __init__(self, is_train):self.features, self.labels = read_data_bananas(is_train)print('read ' + str(len(self.features)) + (f' training examples' ifis_train else f' validation examples'))def __getitem__(self, idx):return (self.features[idx].float(), self.labels[idx])def __len__(self):return len(self.features)def load_data_bananas(batch_size):"""加载香蕉检测数据集"""train_iter = torch.utils.data.DataLoader(BananasDataset(is_train=True),batch_size, shuffle=True)val_iter = torch.utils.data.DataLoader(BananasDataset(is_train=False),batch_size)return train_iter, val_iterbatch_size, edge_size = 32, 256
train_iter, _ = load_data_bananas(batch_size)
batch = next(iter(train_iter))
imgs = (batch[0][0:10].permute(0, 2, 3, 1)) / 255
fig, axes = plt.subplots(2, 5, figsize=(14, 5))
for i, ax in enumerate(axes.flatten()):ax.imshow(imgs[i])  ax.axis('off')bbox = batch[1][i][0][1:5] * 256  rect = patches.Rectangle((bbox[0], bbox[1]),  bbox[2] - bbox[0],   bbox[3] - bbox[1],    linewidth=2,edgecolor='r',facecolor='none')ax.add_patch(rect) 
plt.tight_layout()
plt.show()

3.瞄框生成绘图

%matplotlib inline
import torch
import matplotlib.patches as patches
torch.set_printoptions(2)
##############################################################################################################
#生成大量的瞄框数量:
#首先是按照不同的像素为中心进行瞄框生成
def multibox_prior(data, sizes, ratios):"""生成以每个像素为中心具有不同形状的锚框"""in_height, in_width = data.shape[-2:]device, num_sizes, num_ratios = data.device, len(sizes), len(ratios)boxes_per_pixel = (num_sizes + num_ratios - 1)size_tensor = torch.tensor(sizes, device=device)ratio_tensor = torch.tensor(ratios, device=device)# 为了将锚点移动到像素的中心，需要设置偏移量。# 因为一个像素的高为1且宽为1，我们选择偏移我们的中心0.5offset_h, offset_w = 0.5, 0.5steps_h = 1.0 / in_height  # 在y轴上缩放步长steps_w = 1.0 / in_width  # 在x轴上缩放步长# 生成锚框的所有中心点center_h = (torch.arange(in_height, device=device) + offset_h) * steps_hcenter_w = (torch.arange(in_width, device=device) + offset_w) * steps_wshift_y, shift_x = torch.meshgrid(center_h, center_w, indexing='ij')shift_y, shift_x = shift_y.reshape(-1), shift_x.reshape(-1)# 生成“boxes_per_pixel”个高和宽，# 之后用于创建锚框的四角坐标(xmin,xmax,ymin,ymax)w = torch.cat((size_tensor * torch.sqrt(ratio_tensor[0]),sizes[0] * torch.sqrt(ratio_tensor[1:])))\* in_height / in_width  # 处理矩形输入h = torch.cat((size_tensor / torch.sqrt(ratio_tensor[0]),sizes[0] / torch.sqrt(ratio_tensor[1:])))# 除以2来获得半高和半宽anchor_manipulations = torch.stack((-w, -h, w, h)).T.repeat(in_height * in_width, 1) / 2# 每个中心点都将有“boxes_per_pixel”个锚框，# 所以生成含所有锚框中心的网格，重复了“boxes_per_pixel”次out_grid = torch.stack([shift_x, shift_y, shift_x, shift_y],dim=1).repeat_interleave(boxes_per_pixel, dim=0)output = out_grid + anchor_manipulationsreturn output.unsqueeze(0)
##############################################################################################################
#边界框绘图:
#一个像素点可以生成n+m-1个瞄框:
def show_bboxes(axes, bboxes, labels=None, colors=None):"""显示所有边界框"""def _make_list(obj, default_values=None):if obj is None:obj = default_valueselif not isinstance(obj, (list, tuple)):obj = [obj]return objlabels = _make_list(labels)colors = _make_list(colors, ['b', 'g', 'r', 'm', 'c'])for i, bbox in enumerate(bboxes):color = colors[i % len(colors)]x_min, y_min, x_max, y_max = bbox.detach().numpy()rect = patches.Rectangle((x_min, y_min),  x_max - x_min,   y_max - y_min,  linewidth=2,edgecolor=color,facecolor='none')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=9, color=text_color,bbox=dict(facecolor=color, lw=0))
##############################################################################################################
img = plt.imread('../img/catdog.jpg')
h, w = img.shape[:2]
print(h, w)
X = torch.rand(size=(1, 3, h, w))
Y = multibox_prior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])
boxes = Y.reshape(h, w, 5, 4)
boxes[250, 250, 0, :]
bbox_scale = torch.tensor((w, h, w, h))
fig = plt.imshow(img)
show_bboxes(fig.axes, boxes[250, 250, :, :] * bbox_scale,['s=0.75, r=1', 's=0.5, r=1', 's=0.25, r=1', 's=0.75, r=2','s=0.75, r=0.5'])
##############################################################################################################

3.真实标注框分配瞄框

import torch
import matplotlib.patches as patches
torch.set_printoptions(2)
##############################################################################################################
#计算对应的IoU:|A^B|/|AUB|
def box_iou(boxes1, boxes2):"""计算两个锚框或边界框列表中成对的交并比"""box_area = lambda boxes: ((boxes[:, 2] - boxes[:, 0]) *(boxes[:, 3] - boxes[:, 1]))# boxes1,boxes2,areas1,areas2的形状:# boxes1：(boxes1的数量,4),# boxes2：(boxes2的数量,4),# areas1：(boxes1的数量,),# areas2：(boxes2的数量,)areas1 = box_area(boxes1)areas2 = box_area(boxes2)# inter_upperlefts,inter_lowerrights,inters的形状:# (boxes1的数量,boxes2的数量,2)#对比交叉区域的高度和宽度:inter_upperlefts = torch.max(boxes1[:, None, :2], boxes2[:, :2])inter_lowerrights = torch.min(boxes1[:, None, 2:], boxes2[:, 2:])inters = (inter_lowerrights - inter_upperlefts).clamp(min=0)# inter_areasandunion_areas的形状:(boxes1的数量,boxes2的数量)inter_areas = inters[:, :, 0] * inters[:, :, 1]union_areas = areas1[:, None] + areas2 - inter_areasreturn inter_areas / union_areas
##############################################################################################################
#将真是边界框分给瞄框:
def assign_anchor_to_bbox(ground_truth, anchors, device, iou_threshold=0.5):"""将最接近的真实边界框分配给锚框"""num_anchors, num_gt_boxes = anchors.shape[0], ground_truth.shape[0]# 位于第i行和第j列的元素x_ij是锚框i和真实边界框j的IoUjaccard = box_iou(anchors, ground_truth)# 对于每个锚框，分配的真实边界框的张量anchors_bbox_map = torch.full((num_anchors,), -1, dtype=torch.long,device=device)# 根据阈值，决定是否分配真实边界框max_ious, indices = torch.max(jaccard, dim=1)anc_i = torch.nonzero(max_ious >= iou_threshold).reshape(-1)box_j = indices[max_ious >= iou_threshold]anchors_bbox_map[anc_i] = box_jcol_discard = torch.full((num_anchors,), -1)row_discard = torch.full((num_gt_boxes,), -1)for _ in range(num_gt_boxes):max_idx = torch.argmax(jaccard)box_idx = (max_idx % num_gt_boxes).long()anc_idx = (max_idx / num_gt_boxes).long()anchors_bbox_map[anc_idx] = box_idxjaccard[:, box_idx] = col_discardjaccard[anc_idx, :] = row_discardreturn anchors_bbox_map
def box_corner_to_center(boxes):x1,y1,x2,y2=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]cx=(x1+x2)/2cy=(y1+y2)/2w=x2-x1h=y2-y1boxes=torch.stack((cx,cy,w,h),axis=-1)return boxes
def box_center_to_corner(boxes):cx,cy,w,h=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]x1=cx-0.5*wy1=cy-0.5*hx2=cx+0.5*wy2=cy+0.5*hboxes=torch.stack((x1,y1,x2,y2),axis=-1)return boxes
def offset_boxes(anchors, assigned_bb, eps=1e-6):"""对锚框偏移量的转换"""c_anc = box_corner_to_center(anchors)c_assigned_bb = box_corner_to_center(assigned_bb)offset_xy = 10 * (c_assigned_bb[:, :2] - c_anc[:, :2]) / c_anc[:, 2:]offset_wh = 5 * torch.log(eps + c_assigned_bb[:, 2:] / c_anc[:, 2:])offset = torch.cat([offset_xy, offset_wh], axis=1)return offset
##############################################################################################################
def multibox_target(anchors, labels):"""使用真实边界框标记锚框"""batch_size, anchors = labels.shape[0], anchors.squeeze(0)batch_offset, batch_mask, batch_class_labels = [], [], []device, num_anchors = anchors.device, anchors.shape[0]for i in range(batch_size):label = labels[i, :, :]anchors_bbox_map = assign_anchor_to_bbox(label[:, 1:], anchors, device)bbox_mask = ((anchors_bbox_map >= 0).float().unsqueeze(-1)).repeat(1, 4)# 将类标签和分配的边界框坐标初始化为零class_labels = torch.zeros(num_anchors, dtype=torch.long,device=device)assigned_bb = torch.zeros((num_anchors, 4), dtype=torch.float32,device=device)# 使用真实边界框来标记锚框的类别。# 如果一个锚框没有被分配，标记其为背景（值为零）indices_true = torch.nonzero(anchors_bbox_map >= 0)bb_idx = anchors_bbox_map[indices_true]class_labels[indices_true] = label[bb_idx, 0].long() + 1assigned_bb[indices_true] = label[bb_idx, 1:]# 偏移量转换offset = offset_boxes(anchors, assigned_bb) * bbox_maskbatch_offset.append(offset.reshape(-1))batch_mask.append(bbox_mask.reshape(-1))batch_class_labels.append(class_labels)bbox_offset = torch.stack(batch_offset)bbox_mask = torch.stack(batch_mask)class_labels = torch.stack(batch_class_labels)return (bbox_offset, bbox_mask, class_labels)
##############################################################################################################
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 = 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'])
##############################################################################################################

4.非极大值抑制预测边界框

import torch
import matplotlib.patches as patches
torch.set_printoptions(2)
##############################################################################################################
def box_corner_to_center(boxes):x1,y1,x2,y2=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]cx=(x1+x2)/2cy=(y1+y2)/2w=x2-x1h=y2-y1boxes=torch.stack((cx,cy,w,h),axis=-1)return boxes
def box_center_to_corner(boxes):cx,cy,w,h=boxes[:,0],boxes[:,1],boxes[:,2],boxes[:,3]x1=cx-0.5*wy1=cy-0.5*hx2=cx+0.5*wy2=cy+0.5*hboxes=torch.stack((x1,y1,x2,y2),axis=-1)return boxes
def offset_inverse(anchors, offset_preds):"""根据带有预测偏移量的锚框来预测边界框"""anc = box_corner_to_center(anchors)pred_bbox_xy = (offset_preds[:, :2] * anc[:, 2:] / 10) + anc[:, :2]pred_bbox_wh = torch.exp(offset_preds[:, 2:] / 5) * anc[:, 2:]pred_bbox = torch.cat((pred_bbox_xy, pred_bbox_wh), axis=1)predicted_bbox = box_center_to_corner(pred_bbox)return predicted_bbox
##############################################################################################################
def nms(boxes, scores, iou_threshold):"""对预测边界框的置信度进行排序"""B = torch.argsort(scores, dim=-1, descending=True)keep = []  # 保留预测边界框的指标while B.numel() > 0:i = B[0]keep.append(i)if B.numel() == 1: breakiou = box_iou(boxes[i, :].reshape(-1, 4),boxes[B[1:], :].reshape(-1, 4)).reshape(-1)inds = torch.nonzero(iou <= iou_threshold).reshape(-1)B = B[inds + 1]return torch.tensor(keep, device=boxes.device)
##############################################################################################################
def multibox_detection(cls_probs, offset_preds, anchors, nms_threshold=0.5,pos_threshold=0.009999999):"""使用非极大值抑制来预测边界框"""device, batch_size = cls_probs.device, cls_probs.shape[0]anchors = anchors.squeeze(0)num_classes, num_anchors = cls_probs.shape[1], cls_probs.shape[2]out = []for i in range(batch_size):cls_prob, offset_pred = cls_probs[i], offset_preds[i].reshape(-1, 4)conf, class_id = torch.max(cls_prob[1:], 0)predicted_bb = offset_inverse(anchors, offset_pred)keep = nms(predicted_bb, conf, nms_threshold)# 找到所有的non_keep索引，并将类设置为背景all_idx = torch.arange(num_anchors, dtype=torch.long, device=device)combined = torch.cat((keep, all_idx))uniques, counts = combined.unique(return_counts=True)non_keep = uniques[counts == 1]all_id_sorted = torch.cat((keep, non_keep))class_id[non_keep] = -1class_id = class_id[all_id_sorted]conf, predicted_bb = conf[all_id_sorted], predicted_bb[all_id_sorted]# pos_threshold是一个用于非背景预测的阈值below_min_idx = (conf < pos_threshold)class_id[below_min_idx] = -1conf[below_min_idx] = 1 - conf[below_min_idx]pred_info = torch.cat((class_id.unsqueeze(1),conf.unsqueeze(1),predicted_bb), dim=1)out.append(pred_info)return torch.stack(out)
##############################################################################################################
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] * anchors.numel())
cls_probs = torch.tensor([[0] * 4,  # 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 = plt.figure(figsize=(10, 5))
ax1 = fig.add_subplot(1, 2, 1)
ax1.imshow(img)
ax1.set_title("Original Image")
# 绘制原始图像的边界框
show_bboxes(ax1, anchors * bbox_scale,['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])
#第二张子图:利用非极大值抑制筛选框:
ax2 = fig.add_subplot(1, 2, 2)
ax2.imshow(img)
ax2.set_title("With Bounding Boxes")
output = multibox_detection(cls_probs.unsqueeze(dim=0),offset_preds.unsqueeze(dim=0),anchors.unsqueeze(dim=0),nms_threshold=0.5)
for i in output[0].detach().numpy():if i[0] == -1:continuelabel = ('dog=', 'cat=')[int(i[0])] + str(i[1])show_bboxes(ax2, [torch.tensor(i[2:]) * bbox_scale], label)
plt.tight_layout()
plt.show()
##############################################################################################################