From abe876183052e9da9c3d633e41386c5c1f4fc1e6 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期五, 08 九月 2017 05:51:42 +0800
Subject: [PATCH] Before adding refinement layer
---
code/train.py | 25 +++++++++++++++++--------
1 files changed, 17 insertions(+), 8 deletions(-)
diff --git a/code/train.py b/code/train.py
index ec9e63f..5d7fc7d 100644
--- a/code/train.py
+++ b/code/train.py
@@ -102,10 +102,15 @@
print 'Loading data.'
- transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224),
- transforms.ToTensor()])
+ # transformations = transforms.Compose([transforms.Scale(224),
+ # transforms.RandomCrop(224),
+ # transforms.ToTensor()])
- pose_dataset = datasets.Pose_300W_LP_binned(args.data_dir, args.filename_list,
+ transformations = transforms.Compose([transforms.Scale(250),
+ transforms.RandomCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list,
transformations)
train_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
batch_size=batch_size,
@@ -124,6 +129,10 @@
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=0.01)
print 'Ready to train network.'
@@ -173,15 +182,15 @@
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]))
- if epoch == 0:
- torch.save(model.state_dict(),
- 'output/snapshots/resnet50_iter_'+ str(i+1) + '.pkl')
+ # if epoch == 0:
+ # torch.save(model.state_dict(),
+ # 'output/snapshots/resnet50_lbatch_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_norm_30rot_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_norm_30rot_epoch_' + str(epoch+1) + '.pkl')
--
Gitblit v1.8.0