From dd62d6fa4a85f18a29de009a972f5599b19ec946 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期四, 14 九月 2017 00:51:53 +0800
Subject: [PATCH] Fixing hopenet
---
code/hopenet.py | 34 ++++++++++++++++++++++++++++------
1 files changed, 28 insertions(+), 6 deletions(-)
diff --git a/code/hopenet.py b/code/hopenet.py
index 1b94fa1..d122243 100644
--- a/code/hopenet.py
+++ b/code/hopenet.py
@@ -1,8 +1,8 @@
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):
@@ -41,7 +41,7 @@
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,
@@ -57,6 +57,13 @@
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):
@@ -96,11 +103,26 @@
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 = []
+ angles.append(torch.cat([yaw, pitch, roll], 1))
+
+ for idx in xrange(self.iter_ref):
+ angles.append(self.fc_finetune(torch.cat((angles[idx], x), 1)))
+
+ return pre_yaw, pre_pitch, pre_roll, angles
class Hopenet_shape(nn.Module):
# This is just Hopenet with 3 output layers for yaw, pitch and roll.
--
Gitblit v1.8.0