import torch import torch.nn as nn import torch.nn.functional as F from torch.autograd import Variable class Bottleneck(nn.Module): def init(self, last_planes, in_planes, out_planes, dense_depth, stride, first_layer): super(Bottleneck, self).init() self.out_planes = out_planes self.dense_depth = dense_depth self.conv1 = nn.Conv2d(last_planes, in_planes, kernel_size=1, bias=False) self.bn1 = nn.BatchNorm2d(in_planes) self.conv2 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=32, bias=False) self.bn2 = nn.BatchNorm2d(in_planes) self.conv3 = nn.Conv2d(in_planes, out_planes+dense_depth, kernel_size=1, bias=False) self.bn3 = nn.BatchNorm2d(out_planes+dense_depth) self.shortcut = nn.Sequential() if first_layer: self.shortcut = nn.Sequential( nn.Conv2d(last_planes, out_planes+dense_depth, kernel_size=1, stride=stride, bias=False), nn.BatchNorm2d(out_planes+dense_depth) ) def forward(self, x): out = F.relu(self.bn1(self.conv1(x))) out = F.relu(self.bn2(self.conv2(out))) out = self.bn3(self.conv3(out)) x = self.shortcut(x) d = self.out_planes out = torch.cat([x[:,:d,:,:]+out[:,:d,:,:], x[:,d:,:,:], out[:,d:,:,:]], 1) out = F.relu(out) return out class DPN(nn.Module): def init(self, cfg): super(DPN, self).init() in_planes, out_planes = cfg['in_planes'], cfg['out_planes'] num_blocks, dense_depth = cfg['num_blocks'], cfg['dense_depth'] self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False) self.bn1 = nn.BatchNorm2d(64) self.last_planes = 64 self.layer1 = self._make_layer(in_planes[0], out_planes[0], num_blocks[0], dense_depth[0], stride=1) self.layer2 = self._make_layer(in_planes[1], out_planes[1], num_blocks[1], dense_depth[1], stride=2) self.layer3 = self._make_layer(in_planes[2], out_planes[2], num_blocks[2], dense_depth[2], stride=2) self.layer4 = self._make_layer(in_planes[3], out_planes[3], num_blocks[3], dense_depth[3], stride=2) self.linear = nn.Linear(out_planes[3]+(num_blocks[3]+1)dense_depth[3], 10) def _make_layer(self, in_planes, out_planes, num_blocks, dense_depth, stride): strides = [stride] + 1 layers = [] for i,stride in (strides): layers.append(Bottleneck(self.last_planes, in_planes, out_planes, dense_depth, stride, i==0)) self.last_planes = out_planes + (i+2) * dense_depth return nn.Sequential(*layers) def forward(self, x): out = F.relu(self.bn1(self.conv1(x))) out = self.layer1(out) out = self.layer2(out) out = self.layer3(out) out = self.layer4(out) out = F.avg_pool2d(out, 4) out = out.view(out.size(0), -1) out = self.linear(out) return out def DPN92(): cfg = { 'in_planes': (96,192,384,768), 'out_planes': (256,512,1024,2048), 'num_blocks': (3,4,20,3), 'dense_depth': (16,32,24,128) } return DPN(cfg)基于这个程序改成对摄像头采集的图像检测与分类输出坐标、大小和种类
时间: 2023-06-10 08:06:07 浏览: 180
pytorch_API_docs.zip
这个程序是一个深度残差网络(DPN)用于图像分类,需要进行较大的修改才能用于目标检测和分类。需要添加目标检测和分类的头部网络,以输出目标的坐标、大小和种类。同时需要将输入改为摄像头采集的图像。
以下是基于这个程序的修改建议:
```python
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
class Bottleneck(nn.Module):
def __init__(self, last_planes, in_planes, out_planes, dense_depth, stride, first_layer):
super(Bottleneck, self).__init__()
self.out_planes = out_planes
self.dense_depth = dense_depth
self.conv1 = nn.Conv2d(last_planes, in_planes, kernel_size=1, bias=False)
self.bn1 = nn.BatchNorm2d(in_planes)
self.conv2 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=32, bias=False)
self.bn2 = nn.BatchNorm2d(in_planes)
self.conv3 = nn.Conv2d(in_planes, out_planes * dense_depth, kernel_size=1, bias=False)
self.bn3 = nn.BatchNorm2d(out_planes * dense_depth)
self.shortcut = nn.Sequential()
if first_layer:
self.shortcut = nn.Sequential(
nn.Conv2d(last_planes, out_planes * dense_depth, kernel_size=1, stride=stride, bias=False),
nn.BatchNorm2d(out_planes * dense_depth)
)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = F.relu(self.bn2(self.conv2(out)))
out = self.bn3(self.conv3(out))
x = self.shortcut(x)
d = self.out_planes
out = torch.cat([x[:, :d, :, :], out[:, :d, :, :], x[:, d:, :, :], out[:, d:, :, :]], 1)
out = F.relu(out)
return out
class DPN(nn.Module):
def __init__(self, cfg, num_classes):
super(DPN, self).__init__()
in_planes, out_planes = cfg['in_planes'], cfg['out_planes']
num_blocks, dense_depth = cfg['num_blocks'], cfg['dense_depth']
self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
self.bn1 = nn.BatchNorm2d(64)
self.last_planes = 64
self.layer1 = self._make_layer(in_planes[0], out_planes[0], num_blocks[0], dense_depth[0], stride=1)
self.layer2 = self._make_layer(in_planes[1], out_planes[1], num_blocks[1], dense_depth[1], stride=2)
self.layer3 = self._make_layer(in_planes[2], out_planes[2], num_blocks[2], dense_depth[2], stride=2)
self.layer4 = self._make_layer(in_planes[3], out_planes[3], num_blocks[3], dense_depth[3], stride=2)
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.fc = nn.Linear(out_planes[3] * dense_depth[3], num_classes * 5) # 输出目标的坐标、大小和种类
def _make_layer(self, in_planes, out_planes, num_blocks, dense_depth, stride):
strides = [stride] + [1] * (num_blocks - 1)
layers = []
for i, stride in enumerate(strides):
layers.append(Bottleneck(self.last_planes, in_planes, out_planes, dense_depth, stride, i==0))
self.last_planes = out_planes * dense_depth
return nn.Sequential(*layers)
def forward(self, x):
out = F.relu(self.bn1(self.conv1(x)))
out = self.layer1(out)
out = self.layer2(out)
out = self.layer3(out)
out = self.layer4(out)
out = self.avgpool(out)
out = out.view(out.size(0), -1)
out = self.fc(out)
return out
def DPN92(num_classes=80):
cfg = {
'in_planes': (96, 192, 384, 768),
'out_planes': (256, 512, 1024, 2048),
'num_blocks': (3, 4, 20, 3),
'dense_depth': (16, 32, 24, 128)
}
return DPN(cfg, num_classes)
```
在上述修改中,我们添加了一个新的类别数参数 `num_classes`,用于控制输出的目标种类数。同时将最后的全连接层 `linear` 替换为了一个新的全连接层 `fc`,输出目标的坐标、大小和种类。在 `forward` 函数中,我们添加了一个自适应平均池化层 `avgpool`,用于将最后一层特征图的大小缩小为 `1x1`。最后将特征图展平后送入全连接层 `fc` 进行分类和回归。
阅读全文