python与pytorch中的冒号“:”的用法_Norstc的博客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...

csv python 冒号 python冒号用法_ios

csv python 冒号 python冒号用法_python_02


d2l.set_figsize()


csv python 冒号 python冒号用法_csv python 冒号_03


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'));

 

csv python 冒号 python冒号用法_目标检测_04






 

csv python 冒号 python冒号用法_python_05

 

csv python 冒号 python冒号用法_csv python 冒号_06

 

csv python 冒号 python冒号用法_目标检测_07

 

csv python 冒号 python冒号用法_目标检测_08

 

csv python 冒号 python冒号用法_深度学习_09

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-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 de








csv python 冒号 python冒号用法_目标检测_10

 

csv python 冒号 python冒号用法_目标检测_11

csv python 冒号 python冒号用法_ios_12

 

csv python 冒号 python冒号用法_ios_13

 

csv python 冒号 python冒号用法_深度学习_14

 

csv python 冒号 python冒号用法_ios_15

 

csv python 冒号 python冒号用法_ios_16

 

csv python 冒号 python冒号用法_ios_17

 

csv python 冒号 python冒号用法_csv python 冒号_18

 

csv python 冒号 python冒号用法_深度学习_19

 

csv python 冒号 python冒号用法_ios_20

 

csv python 冒号 python冒号用法_目标检测_21








csv python 冒号 python冒号用法_ios_22


图片错啦 不是Python np.set_printoptions(2) # 精简输出精度


csv python 冒号 python冒号用法_深度学习_23

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)

 

csv python 冒号 python冒号用法_深度学习_24

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


csv python 冒号 python冒号用法_csv python 冒号_25

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))


csv python 冒号 python冒号用法_csv python 冒号_26

 250250像素为中心的所有磨框画出来 

csv python 冒号 python冒号用法_python_27

csv python 冒号 python冒号用法_python_28

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

csv python 冒号 python冒号用法_目标检测_29

csv python 冒号 python冒号用法_目标检测_30

csv python 冒号 python冒号用法_csv python 冒号_31

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

csv python 冒号 python冒号用法_csv python 冒号_32

#@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


csv python 冒号 python冒号用法_ios_33

csv python 冒号 python冒号用法_深度学习_34

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):


csv python 冒号 python冒号用法_目标检测_35

csv python 冒号 python冒号用法_目标检测_36

csv python 冒号 python冒号用法_python_37

 

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]])



csv python 冒号 python冒号用法_目标检测_38

 

csv python 冒号 python冒号用法_ios_39

 

csv python 冒号 python冒号用法_目标检测_40

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)

 

csv python 冒号 python冒号用法_目标检测_41

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)

csv python 冒号 python冒号用法_深度学习_42

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'])

csv python 冒号 python冒号用法_深度学习_43

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)

csv python 冒号 python冒号用法_目标检测_44