From e306e86e925e4211c1c2d2f68de45d5e55f3e215 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期日, 13 八月 2017 01:22:31 +0800
Subject: [PATCH] Some cleanup and AFLW working
---
code/train.py | 37 +++++++++++++------------------------
1 files changed, 13 insertions(+), 24 deletions(-)
diff --git a/code/train_resnet_bins_comb.py b/code/train.py
similarity index 84%
rename from code/train_resnet_bins_comb.py
rename to code/train.py
index eb23590..bef7aca 100644
--- a/code/train_resnet_bins_comb.py
+++ b/code/train.py
@@ -105,7 +105,7 @@
transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224),
transforms.ToTensor()])
- pose_dataset = datasets.Pose_300W_LP_binned(args.data_dir, args.filename_list,
+ pose_dataset = datasets.300W_LP(args.data_dir, args.filename_list,
transformations)
train_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
batch_size=batch_size,
@@ -113,11 +113,10 @@
num_workers=2)
model.cuda(gpu)
- criterion = nn.CrossEntropyLoss()
- reg_criterion = nn.MSELoss()
+ criterion = nn.CrossEntropyLoss().cuda()
+ reg_criterion = nn.MSELoss().cuda()
# Regression loss coefficient
- alpha = 0.1
- lsm = nn.Softmax()
+ alpha = 0.01
idx_tensor = [idx for idx in xrange(66)]
idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
@@ -125,33 +124,25 @@
optimizer = torch.optim.Adam([{'params': get_ignored_params(model), 'lr': args.lr},
{'params': get_non_ignored_params(model), 'lr': args.lr * 10}],
lr = args.lr)
- # optimizer = torch.optim.SGD([{'params': get_ignored_params(model), 'lr': args.lr},
- # {'params': get_non_ignored_params(model), 'lr': args.lr}],
- # lr = args.lr, momentum=0.9, weight_decay=5e-4)
- # optimizer = torch.optim.RMSprop([{'params': get_ignored_params(model), 'lr': args.lr},
- # {'params': get_non_ignored_params(model), 'lr': args.lr * 10}],
- # 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)
+ 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))
optimizer.zero_grad()
+ model.zero_grad()
+
yaw, pitch, roll = model(images)
+ # Cross entropy loss
loss_yaw = criterion(yaw, label_yaw)
loss_pitch = criterion(pitch, label_pitch)
loss_roll = criterion(roll, label_roll)
-
- # loss_seq = [loss_yaw, loss_pitch, loss_roll]
- # grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
- # torch.autograd.backward(loss_seq, grad_seq)
- # optimizer.step()
# MSE loss
yaw_predicted = F.softmax(yaw)
@@ -166,15 +157,13 @@
loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())
- # print yaw_predicted[0], label_yaw.data[0]
-
+ # 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]
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()
@@ -195,4 +184,4 @@
'output/snapshots/resnet50_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_epoch' + str(epoch+1) + '.pkl')
--
Gitblit v1.8.0