文章目录
模型介绍
SSD是单阶段的目标检测算法,通过卷积神经网络进行特征提取,取不同的特征层进行检测输出,所以SSD是一种多尺度的检测方法。在需要检测的特征层,直接使用一个3 ×3卷积,进行通道的变换。SSD采用了anchor的策略,预设不同长宽比例的anchor,每一个输出特征层基于anchor预测多个检测框(4或者6)。采用了多尺度检测方法,浅层用于检测小目标,深层用于检测大目标。
模型的特点
-
多尺度检测
在SSD的网络结构图中我们可以看到,SSD使用了多个特征层,一共6种不同的特征图尺寸。大尺度特征图(较靠前的特征图)可以用来检测小物体,而小尺度特征图(较靠后的特征图)用来检测大物体。多尺度检测的方式,可以使得检测更加充分(SSD属于密集检测),更能检测出小目标。
-
采用卷积进行检测
与YOLO最后采用全连接层不同,SSD直接采用卷积对不同的特征图来进行提取检测结果。对于形状为m×n×p的特征图,只需要采用3×3×p这样比较小的卷积核得到检测值。
-
预设anchor
在YOLOv1中,直接由网络预测目标的尺寸,这种方式使得预测框的长宽比和尺寸没有限制,难以训练。在SSD中,采用预设边界框,我们习惯称它为anchor(在SSD论文中叫default bounding boxes),预测框的尺寸在anchor的指导下进行微调。
数据采样
部分实现
import cv2
import numpy as np
def _rand(a=0., b=1.):
return np.random.rand() * (b - a) + a
def intersect(box_a, box_b):
"""Compute the intersect of two sets of boxes."""
max_yx = np.minimum(box_a[:, 2:4], box_b[2:4])
min_yx = np.maximum(box_a[:, :2], box_b[:2])
inter = np.clip((max_yx - min_yx), a_min=0, a_max=np.inf)
return inter[:, 0] * inter[:, 1]
def jaccard_numpy(box_a, box_b):
"""Compute the jaccard overlap of two sets of boxes."""
inter = intersect(box_a, box_b)
area_a = ((box_a[:, 2] - box_a[:, 0]) *
(box_a[:, 3] - box_a[:, 1]))
area_b = ((box_b[2] - box_b[0]) *
(box_b[3] - box_b[1]))
union = area_a + area_b - inter
return inter / union
def random_sample_crop(image, boxes):
"""Crop images and boxes randomly."""
height, width, _ = image.shape
min_iou = np.random.choice([None, 0.1, 0.3, 0.5, 0.7, 0.9])
if min_iou is None:
return image, boxes
for _ in range(50):
image_t = image
w = _rand(0.3, 1.0) * width
h = _rand(0.3, 1.0) * height
# aspect ratio constraint b/t .5 & 2
if h / w < 0.5 or h / w > 2:
continue
left = _rand() * (width - w)
top = _rand() * (height - h)
rect = np.array([int(top), int(left), int(top + h), int(left + w)])
overlap = jaccard_numpy(boxes, rect)
# dropout some boxes
drop_mask = overlap > 0
if not drop_mask.any():
continue
if overlap[drop_mask].min() < min_iou and overlap[drop_mask].max() > (min_iou + 0.2):
continue
image_t = image_t[rect[0]:rect[2], rect[1]:rect[3], :]
centers = (boxes[:, :2] + boxes[:, 2:4]) / 2.0
m1 = (rect[0] < centers[:, 0]) * (rect[1] < centers[:, 1])
m2 = (rect[2] > centers[:, 0]) * (rect[3] > centers[:, 1])
# mask in that both m1 and m2 are true
mask = m1 * m2 * drop_mask
# have any valid boxes? try again if not
if not mask.any():
continue
# take only matching gt boxes
boxes_t = boxes[mask, :].copy()
boxes_t[:, :2] = np.maximum(boxes_t[:, :2], rect[:2])
boxes_t[:, :2] -= rect[:2]
boxes_t[:, 2:4] = np.minimum(boxes_t[:, 2:4], rect[2:4])
boxes_t[:, 2:4] -= rect[:2]
return image_t, boxes_t
return image, boxes
def ssd_bboxes_encode(boxes):
"""Labels anchors with ground truth inputs."""
def jaccard_with_anchors(bbox):
"""Compute jaccard score a box and the anchors."""
# Intersection bbox and volume.
ymin = np.maximum(y1, bbox[0])
xmin = np.maximum(x1, bbox[1])
ymax = np.minimum(y2, bbox[2])
xmax = np.minimum(x2, bbox[3])
w = np.maximum(xmax - xmin, 0.)
h = np.maximum(ymax - ymin, 0.)
# Volumes.
inter_vol = h * w
union_vol = vol_anchors + (bbox[2] - bbox[0]) * (bbox[3] - bbox[1]) - inter_vol
jaccard = inter_vol / union_vol
return np.squeeze(jaccard)
pre_scores = np.zeros((8732), dtype=np.float32)
t_boxes = np.zeros((8732, 4), dtype=np.float32)
t_label = np.zeros((8732), dtype=np.int64)
for bbox in boxes:
label = int(bbox[4])
scores = jaccard_with_anchors(bbox)
idx = np.argmax(scores)
scores[idx] = 2.0
mask = (scores > matching_threshold)
mask = mask & (scores > pre_scores)
pre_scores = np.maximum(pre_scores, scores * mask)
t_label = mask * label + (1 - mask) * t_label
for i in range(4):
t_boxes[:, i] = mask * bbox[i] + (1 - mask) * t_boxes[:, i]
index = np.nonzero(t_label)
# Transform to tlbr.
bboxes = np.zeros((8732, 4), dtype=np.float32)
bboxes[:, [0, 1]] = (t_boxes[:, [0, 1]] + t_boxes[:, [2, 3]]) / 2
bboxes[:, [2, 3]] = t_boxes[:, [2, 3]] - t_boxes[:, [0, 1]]
# Encode features.
bboxes_t = bboxes[index]
default_boxes_t = default_boxes[index]
bboxes_t[:, :2] = (bboxes_t[:, :2] - default_boxes_t[:, :2]) / (default_boxes_t[:, 2:] * 0.1)
tmp = np.maximum(bboxes_t[:, 2:4] / default_boxes_t[:, 2:4], 0.000001)
bboxes_t[:, 2:4] = np.log(tmp) / 0.2
bboxes[index] = bboxes_t
num_match = np.array([len(np.nonzero(t_label)[0])], dtype=np.int32)
return bboxes, t_label.astype(np.int32), num_match
def preprocess_fn(img_id, image, box, is_training):
"""Preprocess function for dataset."""
cv2.setNumThreads(2)
def _infer_data(image, input_shape):
img_h, img_w, _ = image.shape
input_h, input_w = input_shape
image = cv2.resize(image, (input_w, input_h))
# When the channels of image is 1
if len(image.shape) == 2:
image = np.expand_dims(image, axis=-1)
image = np.concatenate([image, image, image], axis=-1)
return img_id, image, np.array((img_h, img_w), np.float32)
def _data_aug(image, box, is_training, image_size=(300, 300)):
ih, iw, _ = image.shape
h, w = image_size
if not is_training:
return _infer_data(image, image_size)
# Random crop
box = box.astype(np.float32)
image, box = random_sample_crop(image, box)
ih, iw, _ = image.shape
# Resize image
image = cv2.resize(image, (w, h))
# Flip image or not
flip = _rand() < .5
if flip:
image = cv2.flip(image, 1, dst=None)
# When the channels of image is 1
if len(image.shape) == 2:
image = np.expand_dims(image, axis=-1)
image = np.concatenate([image, image, image], axis=-1)
box[:, [0, 2]] = box[:, [0, 2]] / ih
box[:, [1, 3]] = box[:, [1, 3]] / iw
if flip:
box[:, [1, 3]] = 1 - box[:, [3, 1]]
box, label, num_match = ssd_bboxes_encode(box)
return image, box, label, num_match
return _data_aug(image, box, is_training, image_size=[300, 300])
网络结构
SSD网络由VGG16 Base Layer、Extra Feature Layer、Detection Layer、NMS、Anchor几部分构成
anchor会对应c个类别和4个回归偏移量是如何来的?下面重点理解一下Anchor
- 概念:Anchor,也称为锚框,是一组预设的边界框,用于在训练时构建真实的边框位置相对于预设边框的偏移。这些预设的边界框具有不同的尺寸和长宽比,旨在覆盖图像中可能出现的各种目标大小和形状。
- 作用:Anchor的主要作用是作为目标检测的起点,通过在这些预设的边界框上进行精细化的调整,使得模型能够更准确地预测出目标的实际位置和类别。
损失函数
公式
使用2个损失函数,位置损失函数和置信度损失函数
其中:
- N 是先验框的正样本数量;
- c 为类别置信度预测值;
- l 为先验框的所对应边界框的位置预测值;
- g 为ground truth的位置参数
- α 用以调整confidence loss和location loss之间的比例,默认为1。
位置损失函数使用smooth l1损失,位置信息为解码后的位置信息
置信度损失函数是多类置信度上的softmax损失
实现
def class_loss(logits, label):
"""Calculate category losses."""
label = ops.one_hot(label, ops.shape(logits)[-1], Tensor(1.0, ms.float32), Tensor(0.0, ms.float32))
weight = ops.ones_like(logits)
pos_weight = ops.ones_like(logits)
sigmiod_cross_entropy = ops.binary_cross_entropy_with_logits(logits, label, weight.astype(ms.float32), pos_weight.astype(ms.float32))
sigmoid = ops.sigmoid(logits)
label = label.astype(ms.float32)
p_t = label * sigmoid + (1 - label) * (1 - sigmoid)
modulating_factor = ops.pow(1 - p_t, 2.0)
alpha_weight_factor = label * 0.75 + (1 - label) * (1 - 0.75)
focal_loss = modulating_factor * alpha_weight_factor * sigmiod_cross_entropy
return focal_loss
NMS
训练过程是不需要用到非极大值抑制(NMS),
推理时,例如输入一张图片要求输出框的时候,需要用到NMS过滤掉那些重叠度较大的预测框。
非极大值抑制的流程如下:
-
根据置信度得分进行排序
-
选择置信度最高的比边界框添加到最终输出列表中,将其从边界框列表中删除
-
计算所有边界框的面积
-
计算置信度最高的边界框与其它候选框的IoU
-
删除IoU大于阈值的边界框
-
重复上述过程,直至边界框列表为空
训练过程
先验框匹配
在训练过程中,首先要确定训练图片中的ground truth(真实目标)与哪个先验框来进行匹配,与之匹配的先验框所对应的边界框将负责预测它。
此章节学习到此结束,感谢昇思平台。
标签:11,box,image,mask,label,boxes,np,SSD,打卡 From: https://blog.csdn.net/weixin_42630613/article/details/107795559