python与pytorch中的冒号“：”的用法_Norstc的博客-CSDN博客_pytorch 冒号冒号的作用是按一定标号取list的部分元素给定列表a，那么a[st:ed]表示取标号从st到ed-1的所有元素，即[st,ed)如果没有给定st或者ed就表示没有给的st默认为0，ed默认为len(a)即a[st:]表示取从st开始的所有元素；a[:ed]表示从0取到第ed-1个元素...https://blog.csdn.net/a493823882/article/details/120126949

d2l.set_figsize()  

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)

 坐上的xy  高宽 

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'));

 

---

---

---

---

---

 

 

 

 

 

4. Q&A

Q：有哪些标注软件/平台推荐？
A：弹幕上说的：Labeling，Makesense，Vott 等。也可以自己标注，使用半监督学习，迁移学习等。

更多QA

哇咔咔负负得正的博客_CSDN博客-CV,Pytorch,数据库领域博主哇咔咔负负得正擅长CV,Pytorch,数据库,等方面的知识https://blog.csdn.net/qq_39906884?type=blog数据集 书上 没有

Pytorch 目标检测和数据集_哇咔咔负负得正的博客-CSDN博客_pytorch 目标识别Pytorch 目标检测和数据集0. 环境介绍环境使用 Kaggle 里免费建立的 Notebook教程使用李沐老师的 动手学深度学习 网站和 视频讲解小技巧：当遇到函数看不懂的时候可以按 Shift+Tab 查看函数详解。1. 目标检测1.1 概述在图像分类任务中，我们假设图像中只有一个主要物体对象，我们只关注如何识别其类别。然而，很多时候图像里有多个我们感兴趣的目标，我们不仅想知道它们的类别，还想得到它们在图像中的具体位置。 在计算机视觉里，我们将这类任务称为目标检测（object dehttps://blog.csdn.net/qq_39906884/article/details/124619593?spm=1001.2014.3001.5502

---

---

---

---

---

42 锚框【动手学深度学习v2】_哔哩哔哩_bilibili动手学深度学习 v2 - 从零开始介绍深度学习算法和代码实现课程主页：https://courses.d2l.ai/zh-v2/教材：https://zh-v2.d2l.ai/, 视频播放量 48054、弹幕量 518、点赞数 844、投硬币枚数 643、收藏人数 307、转发人数 31, 视频作者 跟李沐学AI, 作者简介 ，相关视频：44 物体检测算法：R-CNN，SSD，YOLO【动手学深度学习v2】，43 树叶分类竞赛技术总结【动手学深度学习v2】，PyTorch深度学习快速入门教程（绝对通俗易懂！）【小土堆】，程序员才能理解的动图，哈哈哈哈，(强推)李宏毅2021/2022春机器学习课程，日本人工智能又一次刷新了我的认知。。。，1.1Faster RCNN理论合集，人工智能研究生现状，“神经网络”是什么？如何直观理解它的能力极限？它是如何无限逼近真理的？，从“卷积”、到“图像卷积操作”、再到“卷积神经网络”，“卷积”意义的3次改变https://www.bilibili.com/video/BV1aB4y1K7za?p=2&vd_source=eba877d881f216d635d2dfec9dc10379

---

 

 

 

 

 

 

 

 

 

 

---

---

---

---

---

---

---

图片错啦 不是Python

np.set_printoptions(2)  # 精简输出精度

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。
    # 因为一个像素的的高为1且宽为1，我们选择偏移我们的中心0.5
    offset_h, offset_w = 0.5, 0.5
    steps_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_h
    center_w = (torch.arange(in_width, device=device) + offset_w) * steps_w
    shift_y, shift_x = torch.meshgrid(center_h, center_w)
    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_manipulations
    return output.unsqueeze(0)

 

img = d2l.plt.imread('../img/catdog.jpg')
h, w = img.shape[:2]

print(h, w)
X = torch.rand(size=(1, 3, h, w))   批量大小1  rgb无所谓
Y = multibox_prior(X, sizes=[0.75, 0.5, 0.25], ratios=[1, 2, 0.5])
                          磨框是百分之75 50 25        1：1 2：1 1：2 
Y.shape

561 728图片 十几万像素

批量1 204两百万个磨框  4是每个磨框的位置

boxes = Y.reshape(h, w, 5, 4) 生产五个这样子的磨框 3+3-1
boxes[250, 250, 0, :]   ：是坐标

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_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().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=9, color=text_color,
                      bbox=dict(facecolor=color, lw=0))

 250250像素为中心的所有磨框画出来 

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)
    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_areas
    return inter_areas / union_areas

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IoU
    jaccard = 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 >= 0.5).reshape(-1)
    box_j = indices[max_ious >= 0.5]
    anchors_bbox_map[anc_i] = box_j
    col_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_idx
        jaccard[:, box_idx] = col_discard
        jaccard[anc_idx, :] = row_discard
    return anchors_bbox_map

#@save
def offset_boxes(anchors, assigned_bb, eps=1e-6):
    """对锚框偏移量的转换"""
    c_anc = d2l.box_corner_to_center(anchors)
    c_assigned_bb = d2l.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

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']);

multibox_target(anchors, labels):

 

labels[2] 表示labels

tensor([[0, 1, 2, 0, 2]])每个磨框的类别

labels[1] 表示mask

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

磨框个数撑4

labels[0]  表示偏移

tensor([[-0.00e+00, -0.00e+00, -0.00e+00, -0.00e+00,  1.40e+00,  1.00e+01,
          2.59e+00,  7.18e+00, -1.20e+00,  2.69e-01,  1.68e+00, -1.57e+00,
         -0.00e+00, -0.00e+00, -0.00e+00, -0.00e+00, -5.71e-01, -1.00e+00,
          4.17e-06,  6.26e-01]])

---

---

 

 

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: break
        iou = 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] = -1
        class_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] = -1
        conf[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 = d2l.plt.imshow(img)
show_bboxes(fig.axes, anchors * bbox_scale,
            ['dog=0.9', 'dog=0.8', 'dog=0.7', 'cat=0.9'])

fig = d2l.plt.imshow(img)
for i in output[0].detach().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)