You cannot select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
73 lines
2.7 KiB
Python
73 lines
2.7 KiB
Python
import torch
|
|
import torch.nn as nn
|
|
import torchvision
|
|
|
|
|
|
class HopeNet(nn.Module):
|
|
# Hopenet with 3 output layers for yaw, pitch and roll
|
|
# Predicts Euler angles by binning and regression with the expected value
|
|
def __init__(self, block, layers, num_bins):
|
|
super(HopeNet, self).__init__()
|
|
if block == 'resnet':
|
|
block = torchvision.models.resnet.Bottleneck
|
|
self.inplanes = 64
|
|
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, bias=False)
|
|
self.bn1 = nn.BatchNorm2d(64)
|
|
self.relu = nn.ReLU(inplace=True)
|
|
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
|
|
self.layer1 = self._make_layer(block, 64, layers[0])
|
|
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
|
|
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
|
|
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
|
|
self.avgpool = nn.AvgPool2d(7)
|
|
self.fc_yaw = nn.Linear(512 * block.expansion, num_bins)
|
|
self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
|
|
self.fc_roll = nn.Linear(512 * block.expansion, num_bins)
|
|
|
|
self.idx_tensor = torch.arange(66).float()
|
|
|
|
def _make_layer(self, block, planes, blocks, stride=1):
|
|
downsample = None
|
|
if stride != 1 or self.inplanes != planes * block.expansion:
|
|
downsample = nn.Sequential(
|
|
nn.Conv2d(self.inplanes, planes * block.expansion, kernel_size=1, stride=stride, bias=False),
|
|
nn.BatchNorm2d(planes * block.expansion),
|
|
)
|
|
|
|
layers = []
|
|
layers.append(block(self.inplanes, planes, stride, downsample))
|
|
self.inplanes = planes * block.expansion
|
|
for i in range(1, blocks):
|
|
layers.append(block(self.inplanes, planes))
|
|
return nn.Sequential(*layers)
|
|
|
|
@staticmethod
|
|
def softmax_temperature(tensor, temperature):
|
|
result = torch.exp(tensor / temperature)
|
|
result = torch.div(result, torch.sum(result, 1).unsqueeze(1).expand_as(result))
|
|
return result
|
|
|
|
def bin2degree(self, predict):
|
|
predict = self.softmax_temperature(predict, 1)
|
|
return torch.sum(predict * self.idx_tensor.type_as(predict), 1) * 3 - 99
|
|
|
|
def forward(self, x):
|
|
x = self.relu(self.bn1(self.conv1(x)))
|
|
x = self.maxpool(x)
|
|
|
|
x = self.layer1(x)
|
|
x = self.layer2(x)
|
|
x = self.layer3(x)
|
|
x = self.layer4(x)
|
|
|
|
x = self.avgpool(x)
|
|
x = x.view(x.size(0), -1)
|
|
pre_yaw = self.fc_yaw(x)
|
|
pre_pitch = self.fc_pitch(x)
|
|
pre_roll = self.fc_roll(x)
|
|
|
|
yaw = self.bin2degree(pre_yaw)
|
|
pitch = self.bin2degree(pre_pitch)
|
|
roll = self.bin2degree(pre_roll)
|
|
return yaw, pitch, roll
|