From 2eb13d63b15a8ac908d6fa324c7f3d19141ca570 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期六, 12 八月 2017 08:57:15 +0800
Subject: [PATCH] Temperature softmax and 10 shape PCA regression.
---
code/train_resnet_shape.py | 53 +++++++++++++++++++++++++++++++++--------------------
1 files changed, 33 insertions(+), 20 deletions(-)
diff --git a/code/train_resnet_shape.py b/code/train_resnet_shape.py
index c874fae..f6baddf 100644
--- a/code/train_resnet_shape.py
+++ b/code/train_resnet_shape.py
@@ -66,7 +66,17 @@
b.append(model.fc_yaw)
b.append(model.fc_pitch)
b.append(model.fc_roll)
+ b.append(model.fc_shape_0)
b.append(model.fc_shape_1)
+ b.append(model.fc_shape_2)
+ b.append(model.fc_shape_3)
+ b.append(model.fc_shape_4)
+ b.append(model.fc_shape_5)
+ b.append(model.fc_shape_6)
+ b.append(model.fc_shape_7)
+ b.append(model.fc_shape_8)
+ b.append(model.fc_shape_9)
+
for i in range(len(b)):
for j in b[i].modules():
for k in j.parameters():
@@ -96,7 +106,7 @@
# ResNet101 with 3 outputs
# model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 23, 3], 66)
# ResNet50
- model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66)
+ model = hopenet.Hopenet_shape(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, 60)
# ResNet18
# model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
load_filtered_state_dict(model, model_zoo.load_url(model_urls['resnet50']))
@@ -114,8 +124,8 @@
num_workers=2)
model.cuda(gpu)
- criterion = nn.CrossEntropyLoss()
- reg_criterion = nn.MSELoss()
+ criterion = nn.CrossEntropyLoss().cuda(gpu)
+ reg_criterion = nn.MSELoss().cuda(gpu)
# Regression loss coefficient
alpha = 0.1
lsm = nn.Softmax()
@@ -124,21 +134,23 @@
idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
optimizer = torch.optim.Adam([{'params': get_ignored_params(model), 'lr': args.lr},
- {'params': get_non_ignored_params(model), 'lr': args.lr * 10}],
+ {'params': get_non_ignored_params(model), 'lr': args.lr}],
lr = args.lr)
print 'Ready to train network.'
for epoch in range(num_epochs):
for i, (images, labels, name) in enumerate(train_loader):
- images = Variable(images).cuda(gpu)
- label_yaw = Variable(labels[:,0]).cuda(gpu)
- label_pitch = Variable(labels[:,1]).cuda(gpu)
- label_roll = Variable(labels[:,2]).cuda(gpu)
- label_shape_1 = Variable(labels[:,3]).cuda(gpu)
+ images = Variable(images.cuda(gpu))
+ label_yaw = Variable(labels[:,0].cuda(gpu))
+ label_pitch = Variable(labels[:,1].cuda(gpu))
+ label_roll = Variable(labels[:,2].cuda(gpu))
+ label_shape = Variable(labels[:,3:].cuda(gpu))
optimizer.zero_grad()
- yaw, pitch, roll, shape_1 = model(images)
+ model.zero_grad()
+
+ yaw, pitch, roll, shape = model(images)
# Cross entropy loss
loss_yaw = criterion(yaw, label_yaw)
@@ -158,17 +170,18 @@
loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())
- # Shape space loss
- loss_shape_1 = criterion(shape_1, label_shape_1)
-
# Total loss
loss_yaw += alpha * loss_reg_yaw
loss_pitch += alpha * loss_reg_pitch
loss_roll += alpha * loss_reg_roll
- loss_seq = [loss_yaw, loss_pitch, loss_roll, loss_shape_1]
+ loss_seq = [loss_yaw, loss_pitch, loss_roll]
+
+ # Shape space loss
+ for idx in xrange(len(shape)):
+ loss_seq.append(criterion(shape[idx], label_shape[:,idx]))
+
grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
- model.zero_grad()
torch.autograd.backward(loss_seq, grad_seq)
optimizer.step()
@@ -176,17 +189,17 @@
# %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss_yaw.data[0], loss_pitch.data[0], loss_roll.data[0]))
if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Iter [%d/%d] Losses: Yaw %.4f, Pitch %.4f, Roll %.4f'
- %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss_yaw.data[0], loss_pitch.data[0], loss_roll.data[0]))
+ print ('Epoch [%d/%d], Iter [%d/%d] Losses: Yaw %.4f, Pitch %.4f, Roll %.4f, Shape %.4f'
+ %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss_yaw.data[0], loss_pitch.data[0], loss_roll.data[0], loss_seq[3].data[0]))
if epoch == 0:
torch.save(model.state_dict(),
- 'output/snapshots/resnet50_iter_'+ str(i+1) + '.pkl')
+ 'output/snapshots/resnet50_shape_iter_'+ str(i+1) + '.pkl')
# Save models at numbered epochs.
if epoch % 1 == 0 and epoch < num_epochs - 1:
print 'Taking snapshot...'
torch.save(model.state_dict(),
- 'output/snapshots/resnet50_epoch_'+ str(epoch+1) + '.pkl')
+ 'output/snapshots/resnet50_shape_epoch_'+ str(epoch+1) + '.pkl')
# Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet50_epoch_' + str(epoch+1) + '.pkl')
+ torch.save(model.state_dict(), 'output/snapshots/resnet50_shape_epoch_' + str(epoch+1) + '.pkl')
--
Gitblit v1.8.0