昇思25天学习打卡营第11天|SSD目标检测

SSD网络

目标检测问题可以分为以下两个问题：1）分类:所有类别的概率；2）定位: 4个值(中心位置x,y,宽w,高h)

Single Shot MultiBox Detector，SSD：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。
SSD的框架：

SSD模型结构

SSD采用VGG16作为基础模型，然后在VGG16的基础上新增了卷积层来获得更多的特征图,利用了多尺度的特征图做检测。SSD先通过卷积不断进行特征提取，在需要检测物体的网络，直接通过一个3 ×3卷积得到输出，卷积的通道数由anchor数量和类别数量决定，具体为(anchor数量*(类别数量+4))。
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，特征层的尺寸分别是38 × 38，19 ×19，10 ×10，5 ×5，3 ×3，1 ×1一共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。

SSD模型构建

VGG16 Base Layer, Extra Feature Layer, Detection Layer, NMS, Anchor

vgg16

from mindspore import nndef _make_layer(channels):in_channels = channels[0]layers = []for out_channels in channels[1:]:layers.append(nn.Conv2d(in_channels=in_channels, out_channels=out_channels, kernel_size=3))layers.append(nn.ReLU())in_channels = out_channelsreturn nn.SequentialCell(layers)class Vgg16(nn.Cell):"""VGG16 module."""def __init__(self):super(Vgg16, self).__init__()self.b1 = _make_layer([3, 64, 64])self.b2 = _make_layer([64, 128, 128])self.b3 = _make_layer([128, 256, 256, 256])self.b4 = _make_layer([256, 512, 512, 512])self.b5 = _make_layer([512, 512, 512, 512])self.m1 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')self.m2 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')self.m3 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')self.m4 = nn.MaxPool2d(kernel_size=2, stride=2, pad_mode='SAME')self.m5 = nn.MaxPool2d(kernel_size=3, stride=1, pad_mode='SAME')def construct(self, x):# block1x = self.b1(x)x = self.m1(x)# block2x = self.b2(x)x = self.m2(x)# block3x = self.b3(x)x = self.m3(x)# block4x = self.b4(x)block4 = xx = self.m4(x)# block5x = self.b5(x)x = self.m5(x)return block4, x

ssd300vgg16

import mindspore as ms
import mindspore.nn as nn
import mindspore.ops as opsdef _last_conv2d(in_channel, out_channel, kernel_size=3, stride=1, pad_mod='same', pad=0):in_channels = in_channelout_channels = in_channeldepthwise_conv = nn.Conv2d(in_channels, out_channels, kernel_size, stride, pad_mode='same',padding=pad, group=in_channels)conv = nn.Conv2d(in_channel, out_channel, kernel_size=1, stride=1, padding=0, pad_mode='same', has_bias=True)bn = nn.BatchNorm2d(in_channel, eps=1e-3, momentum=0.97,gamma_init=1, beta_init=0, moving_mean_init=0, moving_var_init=1)return nn.SequentialCell([depthwise_conv, bn, nn.ReLU6(), conv])class FlattenConcat(nn.Cell):"""FlattenConcat module."""def __init__(self):super(FlattenConcat, self).__init__()self.num_ssd_boxes = 8732def construct(self, inputs):output = ()batch_size = ops.shape(inputs[0])[0]for x in inputs:x = ops.transpose(x, (0, 2, 3, 1))output += (ops.reshape(x, (batch_size, -1)),)res = ops.concat(output, axis=1)return ops.reshape(res, (batch_size, self.num_ssd_boxes, -1))class MultiBox(nn.Cell):"""Multibox conv layers. Each multibox layer contains class conf scores and localization predictions."""def __init__(self):super(MultiBox, self).__init__()num_classes = 81out_channels = [512, 1024, 512, 256, 256, 256]num_default = [4, 6, 6, 6, 4, 4]loc_layers = []cls_layers = []for k, out_channel in enumerate(out_channels):loc_layers += [_last_conv2d(out_channel, 4 * num_default[k],kernel_size=3, stride=1, pad_mod='same', pad=0)]cls_layers += [_last_conv2d(out_channel, num_classes * num_default[k],kernel_size=3, stride=1, pad_mod='same', pad=0)]self.multi_loc_layers = nn.CellList(loc_layers)self.multi_cls_layers = nn.CellList(cls_layers)self.flatten_concat = FlattenConcat()def construct(self, inputs):loc_outputs = ()cls_outputs = ()for i in range(len(self.multi_loc_layers)):loc_outputs += (self.multi_loc_layers[i](inputs[i]),)cls_outputs += (self.multi_cls_layers[i](inputs[i]),)return self.flatten_concat(loc_outputs), self.flatten_concat(cls_outputs)class SSD300Vgg16(nn.Cell):"""SSD300Vgg16 module."""def __init__(self):super(SSD300Vgg16, self).__init__()# VGG16 backbone: block1~5self.backbone = Vgg16()# SSD blocks: block6~7self.b6_1 = nn.Conv2d(in_channels=512, out_channels=1024, kernel_size=3, padding=6, dilation=6, pad_mode='pad')self.b6_2 = nn.Dropout(p=0.5)self.b7_1 = nn.Conv2d(in_channels=1024, out_channels=1024, kernel_size=1)self.b7_2 = nn.Dropout(p=0.5)# Extra Feature Layers: block8~11self.b8_1 = nn.Conv2d(in_channels=1024, out_channels=256, kernel_size=1, padding=1, pad_mode='pad')self.b8_2 = nn.Conv2d(in_channels=256, out_channels=512, kernel_size=3, stride=2, pad_mode='valid')self.b9_1 = nn.Conv2d(in_channels=512, out_channels=128, kernel_size=1, padding=1, pad_mode='pad')self.b9_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, stride=2, pad_mode='valid')self.b10_1 = nn.Conv2d(in_channels=256, out_channels=128, kernel_size=1)self.b10_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, pad_mode='valid')self.b11_1 = nn.Conv2d(in_channels=256, out_channels=128, kernel_size=1)self.b11_2 = nn.Conv2d(in_channels=128, out_channels=256, kernel_size=3, pad_mode='valid')# boxesself.multi_box = MultiBox()def construct(self, x):# VGG16 backbone: block1~5block4, x = self.backbone(x)# SSD blocks: block6~7x = self.b6_1(x)  # 1024x = self.b6_2(x)x = self.b7_1(x)  # 1024x = self.b7_2(x)block7 = x# Extra Feature Layers: block8~11x = self.b8_1(x)  # 256x = self.b8_2(x)  # 512block8 = xx = self.b9_1(x)  # 128x = self.b9_2(x)  # 256block9 = xx = self.b10_1(x)  # 128x = self.b10_2(x)  # 256block10 = xx = self.b11_1(x)  # 128x = self.b11_2(x)  # 256block11 = x# boxesmulti_feature = (block4, block7, block8, block9, block10, block11)pred_loc, pred_label = self.multi_box(multi_feature)if not self.training:pred_label = ops.sigmoid(pred_label)pred_loc = pred_loc.astype(ms.float32)pred_label = pred_label.astype(ms.float32)return pred_loc, pred_label