| | |
|---|
| | | import torch |
|---|
| | | import torch.nn as nn |
|---|
| | | import torchvision.datasets as dsets |
|---|
| | | from torch.autograd import Variable |
|---|
| | | import math |
|---|
| | | import torch.nn.functional as F |
|---|
| | | |
|---|
| | | # CNN Model (2 conv layer) |
|---|
| | | class Simple_CNN(nn.Module): |
|---|
| | |
|---|
| | | |
|---|
| | | class Hopenet(nn.Module): |
|---|
| | | # This is just Hopenet with 3 output layers for yaw, pitch and roll. |
|---|
| | | def __init__(self, block, layers, num_bins): |
|---|
| | | def __init__(self, block, layers, num_bins, iter_ref): |
|---|
| | | self.inplanes = 64 |
|---|
| | | super(Hopenet, self).__init__() |
|---|
| | | self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3, |
|---|
| | |
|---|
| | | 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.softmax = nn.Softmax() |
|---|
| | | self.fc_finetune = nn.Linear(512 * block.expansion + 3, 3) |
|---|
| | | |
|---|
| | | self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda() |
|---|
| | | |
|---|
| | | self.iter_ref = iter_ref |
|---|
| | | |
|---|
| | | for m in self.modules(): |
|---|
| | | if isinstance(m, nn.Conv2d): |
|---|
| | |
|---|
| | | |
|---|
| | | x = self.avgpool(x) |
|---|
| | | x = x.view(x.size(0), -1) |
|---|
| | | yaw = self.fc_yaw(x) |
|---|
| | | pitch = self.fc_pitch(x) |
|---|
| | | roll = self.fc_roll(x) |
|---|
| | | pre_yaw = self.fc_yaw(x) |
|---|
| | | pre_pitch = self.fc_pitch(x) |
|---|
| | | pre_roll = self.fc_roll(x) |
|---|
| | | |
|---|
| | | return yaw, pitch, roll |
|---|
| | | yaw = self.softmax(pre_yaw) |
|---|
| | | yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True) |
|---|
| | | pitch = self.softmax(pre_pitch) |
|---|
| | | pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True) |
|---|
| | | roll = self.softmax(pre_roll) |
|---|
| | | roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True) |
|---|
| | | yaw = yaw.view(yaw.size(0), 1) |
|---|
| | | pitch = pitch.view(pitch.size(0), 1) |
|---|
| | | roll = roll.view(roll.size(0), 1) |
|---|
| | | angles = [] |
|---|
| | | preangles = torch.cat([yaw, pitch, roll], 1) |
|---|
| | | angles.append(preangles) |
|---|
| | | |
|---|
| | | # angles predicts the residual |
|---|
| | | for idx in xrange(self.iter_ref): |
|---|
| | | angles.append(self.fc_finetune(torch.cat((preangles, x), 1))) |
|---|
| | | |
|---|
| | | return pre_yaw, pre_pitch, pre_roll, angles |
|---|
