From c495a0f6b13b794bab9f6e3423d5038ce645d816 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期三, 13 九月 2017 21:12:59 +0800
Subject: [PATCH] Batch testing and hopenet training complete
---
code/train.py | 24
code/hopenet.py | 6
code/test_on_video.py | 2
code/batch_testing/batch_testing_AFLW_preangles.py | 147 +++++++++
code/train_AFLW_preangles.py | 265 ++++++++++++++++
code/batch_testing_preangles.py | 158 +++++++++
code/batch_testing.py | 147 +++++++++
code/train_preangles.py | 2
code/test.py | 9
code/test_biwi_preangles.py | 149 +++++++++
10 files changed, 888 insertions(+), 21 deletions(-)
diff --git a/code/batch_testing.py b/code/batch_testing.py
new file mode 100644
index 0000000..74ad58b
--- /dev/null
+++ b/code/batch_testing.py
@@ -0,0 +1,147 @@
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+from torch.utils.data import DataLoader
+from torchvision import transforms
+import torch.backends.cudnn as cudnn
+import torchvision
+import torch.nn.functional as F
+
+import cv2
+import matplotlib.pyplot as plt
+import sys
+import os
+import argparse
+
+import datasets
+import hopenet
+import utils
+
+import glob
+
+def parse_args():
+ """Parse input arguments."""
+ parser = argparse.ArgumentParser(description='Head pose estimation using the Hopenet network.')
+ parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
+ default=0, type=int)
+ parser.add_argument('--data_dir', dest='data_dir', help='Directory path for data.',
+ default='', type=str)
+ parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
+ default='', type=str)
+ parser.add_argument('--snapshot_folder', dest='snapshot_folder', help='Name of model snapshot folder.',
+ default='', type=str)
+ parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
+ default=1, type=int)
+ parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
+ default=False, type=bool)
+ parser.add_argument('--iter_ref', dest='iter_ref', help='Number of iterative refinement passes.',
+ default=1, type=int)
+ parser.add_argument('--dataset', dest='dataset', help='Dataset type.', default='AFLW2000', type=str)
+ args = parser.parse_args()
+
+ return args
+
+if __name__ == '__main__':
+ args = parse_args()
+
+ cudnn.enabled = True
+ gpu = args.gpu_id
+
+ # 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, args.iter_ref)
+ # ResNet18
+ # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
+
+ print 'Loading snapshot list.'
+ # Load snapshot
+ snapshot_list = sorted(glob.glob(os.path.join(args.snapshot_folder, '*.pkl')))
+
+ print 'Loading data.'
+
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.RandomCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ if args.dataset == 'AFLW2000':
+ pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
+ transformations)
+ elif args.dataset == 'BIWI':
+ pose_dataset = datasets.BIWI(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFLW':
+ pose_dataset = datasets.AFLW(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFW':
+ pose_dataset = datasets.AFW(args.data_dir, args.filename_list, transformations)
+ else:
+ print 'Error: not a valid dataset name'
+ sys.exit()
+ test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
+ batch_size=args.batch_size,
+ num_workers=2)
+
+ model.cuda(gpu)
+
+ print 'Ready to test network.'
+
+ prefix = args.snapshot_folder.split('/')[-1]
+ if prefix == '':
+ prefix = args.snapshot_folder.split('/')[-2]
+ output_file_name = prefix + '_' + args.dataset + '_angles.txt'
+ txt_output = open(os.path.join('output/batch_snapshots', output_file_name), 'w')
+
+ for snapshot_path in snapshot_list:
+ snapshot_name = snapshot_path.split('/')[-1].split('.')[0]
+ print 'Loading snapshot ' + snapshot_name
+
+ saved_state_dict = torch.load(snapshot_path)
+ model.load_state_dict(saved_state_dict)
+
+ # Test the Model
+ model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
+ total = 0
+ n_margins = 20
+ yaw_correct = np.zeros(n_margins)
+ pitch_correct = np.zeros(n_margins)
+ roll_correct = np.zeros(n_margins)
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
+
+ yaw_error = .0
+ pitch_error = .0
+ roll_error = .0
+
+ l1loss = torch.nn.L1Loss(size_average=False)
+
+ for i, (images, labels, name) in enumerate(test_loader):
+ images = Variable(images).cuda(gpu)
+ total += labels.size(0)
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+
+ pre_yaw, pre_pitch, pre_roll, angles = model(images)
+ yaw = angles[args.iter_ref-1][:,0].cpu().data
+ pitch = angles[args.iter_ref-1][:,1].cpu().data
+ roll = angles[args.iter_ref-1][:,2].cpu().data
+
+ # Mean absolute error
+ yaw_error += torch.sum(torch.abs(yaw - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll - label_roll) * 3)
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
+ utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99)
+ cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)
+
+ print('Test error in degrees of the model on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+ txt_output.write('Test error in degrees of model ' + snapshot_name + ' on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f \n' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+
+ txt_output.close()
diff --git a/code/batch_testing/batch_testing_AFLW_preangles.py b/code/batch_testing/batch_testing_AFLW_preangles.py
new file mode 100644
index 0000000..e0c170e
--- /dev/null
+++ b/code/batch_testing/batch_testing_AFLW_preangles.py
@@ -0,0 +1,147 @@
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+from torch.utils.data import DataLoader
+from torchvision import transforms
+import torch.backends.cudnn as cudnn
+import torchvision
+import torch.nn.functional as F
+
+import cv2
+import matplotlib.pyplot as plt
+import sys
+import os
+import argparse
+
+import datasets
+import hopenet
+import utils
+
+import glob
+
+def parse_args():
+ """Parse input arguments."""
+ parser = argparse.ArgumentParser(description='Head pose estimation using the Hopenet network.')
+ parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
+ default=0, type=int)
+ parser.add_argument('--data_dir', dest='data_dir', help='Directory path for data.',
+ default='', type=str)
+ parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
+ default='', type=str)
+ parser.add_argument('--snapshot_folder', dest='snapshot_folder', help='Name of model snapshot folder.',
+ default='', type=str)
+ parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
+ default=1, type=int)
+ parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
+ default=False, type=bool)
+
+ args = parser.parse_args()
+
+ return args
+
+if __name__ == '__main__':
+ args = parse_args()
+
+ cudnn.enabled = True
+ gpu = args.gpu_id
+
+ # 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)
+ # ResNet18
+ # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
+
+ print 'Loading snapshot list.'
+ # Load snapshot
+ snapshot_list = sorted(glob.glob(os.path.join(args.snapshot_folder, '*.pkl')))
+
+ 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(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ pose_dataset = datasets.AFLW(args.data_dir, args.filename_list,
+ transformations)
+ test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
+ batch_size=args.batch_size,
+ num_workers=2)
+
+ model.cuda(gpu)
+
+ print 'Ready to test network.'
+
+ output_file_name = args.snapshot_folder.split('/')[-1] + '_AFLW_preangles.txt'
+ txt_output = open(os.join('output/batch_snapshots', output_file_name), 'w')
+
+ for snapshot_path in snapshot_list:
+ snapshot_name = snapshot_path.split('/')[-1].split('.')[0]
+ print 'Loading snapshot ' + snapshot_name
+
+ saved_state_dict = torch.load(snapshot_path)
+ model.load_state_dict(saved_state_dict)
+
+ # Test the Model
+ model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
+ total = 0
+ n_margins = 20
+ yaw_correct = np.zeros(n_margins)
+ pitch_correct = np.zeros(n_margins)
+ roll_correct = np.zeros(n_margins)
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
+
+ yaw_error = .0
+ pitch_error = .0
+ roll_error = .0
+
+ l1loss = torch.nn.L1Loss(size_average=False)
+
+ for i, (images, labels, name) in enumerate(test_loader):
+ images = Variable(images).cuda(gpu)
+ total += labels.size(0)
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+
+ yaw, pitch, roll, angles = model(images)
+
+ # Binned predictions
+ _, yaw_bpred = torch.max(yaw.data, 1)
+ _, pitch_bpred = torch.max(pitch.data, 1)
+ _, roll_bpred = torch.max(roll.data, 1)
+
+ # Continuous predictions
+ yaw_predicted = utils.softmax_temperature(yaw.data, 1)
+ pitch_predicted = utils.softmax_temperature(pitch.data, 1)
+ roll_predicted = utils.softmax_temperature(roll.data, 1)
+
+ yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1).cpu()
+ pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1).cpu()
+ roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu()
+
+ # Mean absolute error
+ yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll_predicted - label_roll) * 3)
+
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
+ utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99)
+ cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)
+
+ print('Test error in degrees of the model on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+ txt_output.write('Test error in degrees of model ' + snapshot_name + ' on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f \n' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+
+ txt_output.close()
diff --git a/code/batch_testing_preangles.py b/code/batch_testing_preangles.py
new file mode 100644
index 0000000..11390b0
--- /dev/null
+++ b/code/batch_testing_preangles.py
@@ -0,0 +1,158 @@
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+from torch.utils.data import DataLoader
+from torchvision import transforms
+import torch.backends.cudnn as cudnn
+import torchvision
+import torch.nn.functional as F
+
+import cv2
+import matplotlib.pyplot as plt
+import sys
+import os
+import argparse
+
+import datasets
+import hopenet
+import utils
+
+import glob
+
+def parse_args():
+ """Parse input arguments."""
+ parser = argparse.ArgumentParser(description='Head pose estimation using the Hopenet network.')
+ parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
+ default=0, type=int)
+ parser.add_argument('--data_dir', dest='data_dir', help='Directory path for data.',
+ default='', type=str)
+ parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
+ default='', type=str)
+ parser.add_argument('--snapshot_folder', dest='snapshot_folder', help='Name of model snapshot folder.',
+ default='', type=str)
+ parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
+ default=1, type=int)
+ parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
+ default=False, type=bool)
+ parser.add_argument('--dataset', dest='dataset', help='Dataset type.', default='AFLW2000', type=str)
+
+ args = parser.parse_args()
+
+ return args
+
+if __name__ == '__main__':
+ args = parse_args()
+
+ cudnn.enabled = True
+ gpu = args.gpu_id
+
+ # 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)
+ # ResNet18
+ # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
+
+ print 'Loading snapshot list.'
+ # Load snapshot
+ snapshot_list = sorted(glob.glob(os.path.join(args.snapshot_folder, '*.pkl')))
+
+ print 'Loading data.'
+
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.RandomCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ if args.dataset == 'AFLW2000':
+ pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
+ transformations)
+ elif args.dataset == 'BIWI':
+ pose_dataset = datasets.BIWI(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFLW':
+ pose_dataset = datasets.AFLW(args.data_dir, args.filename_list, transformations)
+ elif args.dataset == 'AFW':
+ pose_dataset = datasets.AFW(args.data_dir, args.filename_list, transformations)
+ else:
+ print 'Error: not a valid dataset name'
+ sys.exit()
+ test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
+ batch_size=args.batch_size,
+ num_workers=2)
+
+ model.cuda(gpu)
+
+ print 'Ready to test network.'
+
+ prefix = args.snapshot_folder.split('/')[-1]
+ if prefix == '':
+ prefix = args.snapshot_folder.split('/')[-2]
+ output_file_name = prefix + '_' + args.dataset + '_preangles.txt'
+ txt_output = open(os.path.join('output/batch_snapshots', output_file_name), 'w')
+
+ for snapshot_path in snapshot_list:
+ snapshot_name = snapshot_path.split('/')[-1].split('.')[0]
+ print 'Loading snapshot ' + snapshot_name
+
+ saved_state_dict = torch.load(snapshot_path)
+ model.load_state_dict(saved_state_dict)
+
+ # Test the Model
+ model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
+ total = 0
+ n_margins = 20
+ yaw_correct = np.zeros(n_margins)
+ pitch_correct = np.zeros(n_margins)
+ roll_correct = np.zeros(n_margins)
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
+
+ yaw_error = .0
+ pitch_error = .0
+ roll_error = .0
+
+ l1loss = torch.nn.L1Loss(size_average=False)
+
+ for i, (images, labels, name) in enumerate(test_loader):
+ images = Variable(images).cuda(gpu)
+ total += labels.size(0)
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+
+ yaw, pitch, roll, angles = model(images)
+
+ # Binned predictions
+ _, yaw_bpred = torch.max(yaw.data, 1)
+ _, pitch_bpred = torch.max(pitch.data, 1)
+ _, roll_bpred = torch.max(roll.data, 1)
+
+ # Continuous predictions
+ yaw_predicted = utils.softmax_temperature(yaw.data, 1)
+ pitch_predicted = utils.softmax_temperature(pitch.data, 1)
+ roll_predicted = utils.softmax_temperature(roll.data, 1)
+
+ yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1).cpu()
+ pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1).cpu()
+ roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu()
+
+ # Mean absolute error
+ yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll_predicted - label_roll) * 3)
+
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
+ utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99)
+ cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)
+
+ print('Test error in degrees of the model on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+ txt_output.write('Test error in degrees of model ' + snapshot_name + ' on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f \n' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+
+ txt_output.close()
diff --git a/code/hopenet.py b/code/hopenet.py
index 5bac804..81e645c 100644
--- a/code/hopenet.py
+++ b/code/hopenet.py
@@ -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,
@@ -62,6 +62,8 @@
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):
@@ -117,7 +119,7 @@
angles = []
angles.append(torch.cat([yaw, pitch, roll], 1))
- for idx in xrange(1):
+ for idx in xrange(self.iter_ref):
angles.append(self.fc_finetune(torch.cat((angles[-1], x), 1)))
return pre_yaw, pre_pitch, pre_roll, angles
diff --git a/code/test.py b/code/test.py
index b01d07e..ca7a820 100644
--- a/code/test.py
+++ b/code/test.py
@@ -33,6 +33,7 @@
default=1, type=int)
parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
default=False, type=bool)
+ parser.add_argument('--iter_ref', dest='iter_ref', default=1, type=int)
args = parser.parse_args()
@@ -48,7 +49,7 @@
# 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(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, args.iter_ref)
# ResNet18
# model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
@@ -98,9 +99,9 @@
label_roll = labels[:,2].float()
pre_yaw, pre_pitch, pre_roll, angles = model(images)
- yaw = angles[0][:,0].cpu().data
- pitch = angles[0][:,1].cpu().data
- roll = angles[0][:,2].cpu().data
+ yaw = angles[args.iter_ref-1][:,0].cpu().data
+ pitch = angles[args.iter_ref-1][:,1].cpu().data
+ roll = angles[args.iter_ref-1][:,2].cpu().data
# Mean absolute error
yaw_error += torch.sum(torch.abs(yaw - label_yaw) * 3)
diff --git a/code/test_biwi_preangles.py b/code/test_biwi_preangles.py
new file mode 100644
index 0000000..a64dab9
--- /dev/null
+++ b/code/test_biwi_preangles.py
@@ -0,0 +1,149 @@
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+from torch.utils.data import DataLoader
+from torchvision import transforms
+import torch.backends.cudnn as cudnn
+import torchvision
+import torch.nn.functional as F
+
+import cv2
+import matplotlib.pyplot as plt
+import sys
+import os
+import argparse
+
+import datasets
+import hopenet
+import utils
+
+def parse_args():
+ """Parse input arguments."""
+ parser = argparse.ArgumentParser(description='Head pose estimation using the Hopenet network.')
+ parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
+ default=0, type=int)
+ parser.add_argument('--data_dir', dest='data_dir', help='Directory path for data.',
+ default='', type=str)
+ parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
+ default='', type=str)
+ parser.add_argument('--snapshot', dest='snapshot', help='Name of model snapshot.',
+ default='', type=str)
+ parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
+ default=1, type=int)
+ parser.add_argument('--save_viz', dest='save_viz', help='Save images with pose cube.',
+ default=False, type=bool)
+
+ args = parser.parse_args()
+
+ return args
+
+if __name__ == '__main__':
+ args = parse_args()
+
+ cudnn.enabled = True
+ gpu = args.gpu_id
+ snapshot_path = args.snapshot
+
+ # 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)
+ # ResNet18
+ # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
+
+ print 'Loading snapshot.'
+ # Load snapshot
+ saved_state_dict = torch.load(snapshot_path)
+ model.load_state_dict(saved_state_dict)
+
+ print 'Loading data.'
+
+ # transformations = transforms.Compose([transforms.Scale(224),
+ # transforms.RandomCrop(224), transforms.ToTensor()])
+
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.CenterCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ pose_dataset = datasets.BIWI(args.data_dir, args.filename_list,
+ transformations)
+ test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
+ batch_size=args.batch_size,
+ num_workers=2)
+
+ model.cuda(gpu)
+
+ print 'Ready to test network.'
+
+ # Test the Model
+ model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
+ total = 0
+ n_margins = 20
+ yaw_correct = np.zeros(n_margins)
+ pitch_correct = np.zeros(n_margins)
+ roll_correct = np.zeros(n_margins)
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = torch.FloatTensor(idx_tensor).cuda(gpu)
+
+ yaw_error = .0
+ pitch_error = .0
+ roll_error = .0
+
+ l1loss = torch.nn.L1Loss(size_average=False)
+
+ for i, (images, labels, name) in enumerate(test_loader):
+ images = Variable(images).cuda(gpu)
+ total += labels.size(0)
+ label_yaw = labels[:,0].float()
+ label_pitch = labels[:,1].float()
+ label_roll = labels[:,2].float()
+
+ yaw, pitch, roll, angles = model(images)
+
+ # Binned predictions
+ _, yaw_bpred = torch.max(yaw.data, 1)
+ _, pitch_bpred = torch.max(pitch.data, 1)
+ _, roll_bpred = torch.max(roll.data, 1)
+
+ # Continuous predictions
+ yaw_predicted = utils.softmax_temperature(yaw.data, 1)
+ pitch_predicted = utils.softmax_temperature(pitch.data, 1)
+ roll_predicted = utils.softmax_temperature(roll.data, 1)
+
+ yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1).cpu()
+ pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1).cpu()
+ roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu()
+
+ # Mean absolute error
+ yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw) * 3)
+ pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch) * 3)
+ roll_error += torch.sum(torch.abs(roll_predicted - label_roll) * 3)
+
+ # Binned Accuracy
+ # for er in xrange(n_margins):
+ # yaw_bpred[er] += (label_yaw[0] in range(yaw_bpred[0,0] - er, yaw_bpred[0,0] + er + 1))
+ # pitch_bpred[er] += (label_pitch[0] in range(pitch_bpred[0,0] - er, pitch_bpred[0,0] + er + 1))
+ # roll_bpred[er] += (label_roll[0] in range(roll_bpred[0,0] - er, roll_bpred[0,0] + er + 1))
+
+ # print label_yaw[0], yaw_bpred[0,0]
+
+ # Save images with pose cube.
+ # TODO: fix for larger batch size
+ if args.save_viz:
+ name = name[0]
+ cv2_img = cv2.imread(os.path.join(args.data_dir, name + '_rgb.png'))
+ #print os.path.join('output/images', name + '.jpg')
+ #print label_yaw[0] * 3 - 99, label_pitch[0] * 3 - 99, label_roll[0] * 3 - 99
+ #print yaw_predicted * 3 - 99, pitch_predicted * 3 - 99, roll_predicted * 3 - 99
+ utils.plot_pose_cube(cv2_img, yaw_predicted[0] * 3 - 99, pitch_predicted[0] * 3 - 99, roll_predicted[0] * 3 - 99)
+ cv2.imwrite(os.path.join('output/images', name + '.jpg'), cv2_img)
+
+ print('Test error in degrees of the model on the ' + str(total) +
+ ' test images. Yaw: %.4f, Pitch: %.4f, Roll: %.4f' % (yaw_error / total,
+ pitch_error / total, roll_error / total))
+
+ # Binned accuracy
+ # for idx in xrange(len(yaw_correct)):
+ # print yaw_correct[idx] / total, pitch_correct[idx] / total, roll_correct[idx] / total
diff --git a/code/test_on_video.py b/code/test_on_video.py
index b410ea7..8d6c5fd 100644
--- a/code/test_on_video.py
+++ b/code/test_on_video.py
@@ -141,7 +141,7 @@
img_shape = img.size()
img = img.view(1, img_shape[0], img_shape[1], img_shape[2])
img = Variable(img).cuda(gpu)
- yaw, pitch, roll = model(img)
+ yaw, pitch, roll, angles = model(img)
yaw_predicted = F.softmax(yaw)
pitch_predicted = F.softmax(pitch)
diff --git a/code/train.py b/code/train.py
index ff060af..50eeb82 100644
--- a/code/train.py
+++ b/code/train.py
@@ -46,6 +46,8 @@
parser.add_argument('--output_string', dest='output_string', help='String appended to output snapshots.', default = '', type=str)
parser.add_argument('--alpha', dest='alpha', help='Regression loss coefficient.',
default=0.001, type=float)
+ parser.add_argument('--iter_ref', dest='iter_ref', help='Number of iterative refinement passes.',
+ default=1, type=int)
args = parser.parse_args()
return args
@@ -111,7 +113,7 @@
# 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(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, args.iter_ref)
# 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']))
@@ -177,14 +179,12 @@
loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())
- # print yaw_predicted, label_yaw.float(), loss_reg_yaw
# 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_seq = [loss_reg_yaw, loss_reg_pitch, loss_reg_roll]
grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
torch.autograd.backward(loss_seq, grad_seq)
optimizer.step()
@@ -226,9 +226,9 @@
pitch_predicted = softmax(pre_pitch)
roll_predicted = softmax(pre_roll)
- yaw_predicted = torch.sum(yaw_predicted.data * idx_tensor, 1)
- pitch_predicted = torch.sum(pitch_predicted.data * idx_tensor, 1)
- roll_predicted = torch.sum(roll_predicted.data * idx_tensor, 1)
+ yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1)
+ pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1)
+ roll_predicted = torch.sum(roll_predicted * idx_tensor, 1)
loss_reg_yaw = reg_criterion(yaw_predicted, label_yaw.float())
loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
@@ -240,9 +240,11 @@
loss_roll += alpha * loss_reg_roll
# Finetuning loss
- loss_angles = reg_criterion(angles[0], label_angles.float())
+ loss_seq = [loss_yaw, loss_pitch, loss_roll]
+ for idx in xrange(args.iter_ref):
+ loss_angles = reg_criterion(angles[idx], label_angles.float())
+ loss_seq.append(loss_angles)
- loss_seq = [loss_yaw, loss_pitch, loss_roll, loss_angles]
grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
torch.autograd.backward(loss_seq, grad_seq)
optimizer.step()
@@ -255,11 +257,7 @@
# 'output/snapshots/' + args.output_string + '_iter_'+ str(i+1) + '.pkl')
# Save models at numbered epochs.
- if epoch % 1 == 0 and epoch < num_epochs_ft - 1:
+ if epoch % 1 == 0 and epoch < num_epochs_ft:
print 'Taking snapshot...'
torch.save(model.state_dict(),
'output/snapshots/' + args.output_string + '_epoch_'+ str(num_epochs+epoch+1) + '.pkl')
-
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/' + args.output_string + '_epoch_' + str(num_epochs+epoch+1) + '.pkl')
diff --git a/code/train_AFLW_preangles.py b/code/train_AFLW_preangles.py
new file mode 100644
index 0000000..ede3439
--- /dev/null
+++ b/code/train_AFLW_preangles.py
@@ -0,0 +1,265 @@
+import numpy as np
+import torch
+import torch.nn as nn
+from torch.autograd import Variable
+from torch.utils.data import DataLoader
+from torchvision import transforms
+import torchvision
+import torch.backends.cudnn as cudnn
+import torch.nn.functional as F
+
+import cv2
+import matplotlib.pyplot as plt
+import sys
+import os
+import argparse
+
+import datasets
+import hopenet
+import torch.utils.model_zoo as model_zoo
+
+model_urls = {
+ 'resnet18': 'https://download.pytorch.org/models/resnet18-5c106cde.pth',
+ 'resnet34': 'https://download.pytorch.org/models/resnet34-333f7ec4.pth',
+ 'resnet50': 'https://download.pytorch.org/models/resnet50-19c8e357.pth',
+ 'resnet101': 'https://download.pytorch.org/models/resnet101-5d3b4d8f.pth',
+ 'resnet152': 'https://download.pytorch.org/models/resnet152-b121ed2d.pth',
+}
+
+def parse_args():
+ """Parse input arguments."""
+ parser = argparse.ArgumentParser(description='Head pose estimation using the Hopenet network.')
+ parser.add_argument('--gpu', dest='gpu_id', help='GPU device id to use [0]',
+ default=0, type=int)
+ parser.add_argument('--num_epochs', dest='num_epochs', help='Maximum number of training epochs.',
+ default=5, type=int)
+ parser.add_argument('--num_epochs_ft', dest='num_epochs_ft', help='Maximum number of finetuning epochs.',
+ default=5, type=int)
+ parser.add_argument('--batch_size', dest='batch_size', help='Batch size.',
+ default=16, type=int)
+ parser.add_argument('--lr', dest='lr', help='Base learning rate.',
+ default=0.001, type=float)
+ parser.add_argument('--data_dir', dest='data_dir', help='Directory path for data.',
+ default='', type=str)
+ parser.add_argument('--filename_list', dest='filename_list', help='Path to text file containing relative paths for every example.',
+ default='', type=str)
+ parser.add_argument('--output_string', dest='output_string', help='String appended to output snapshots.', default = '', type=str)
+ parser.add_argument('--alpha', dest='alpha', help='Regression loss coefficient.',
+ default=0.00, type=float)
+ args = parser.parse_args()
+ return args
+
+def get_ignored_params(model):
+ # Generator function that yields ignored params.
+ b = []
+ b.append(model.conv1)
+ b.append(model.bn1)
+ b.append(model.fc_finetune)
+ for i in range(len(b)):
+ for module_name, module in b[i].named_modules():
+ if 'bn' in module_name:
+ module.eval()
+ for name, param in module.named_parameters():
+ yield param
+
+def get_non_ignored_params(model):
+ # Generator function that yields params that will be optimized.
+ b = []
+ b.append(model.layer1)
+ b.append(model.layer2)
+ b.append(model.layer3)
+ b.append(model.layer4)
+ for i in range(len(b)):
+ for module_name, module in b[i].named_modules():
+ if 'bn' in module_name:
+ module.eval()
+ for name, param in module.named_parameters():
+ yield param
+
+def get_fc_params(model):
+ b = []
+ b.append(model.fc_yaw)
+ b.append(model.fc_pitch)
+ b.append(model.fc_roll)
+ for i in range(len(b)):
+ for module_name, module in b[i].named_modules():
+ for name, param in module.named_parameters():
+ yield param
+
+def load_filtered_state_dict(model, snapshot):
+ # By user apaszke from discuss.pytorch.org
+ model_dict = model.state_dict()
+ # 1. filter out unnecessary keys
+ snapshot = {k: v for k, v in snapshot.items() if k in model_dict}
+ # 2. overwrite entries in the existing state dict
+ model_dict.update(snapshot)
+ # 3. load the new state dict
+ model.load_state_dict(model_dict)
+
+if __name__ == '__main__':
+ args = parse_args()
+
+ cudnn.enabled = True
+ num_epochs = args.num_epochs
+ num_epochs_ft = args.num_epochs_ft
+ batch_size = args.batch_size
+ gpu = args.gpu_id
+
+ if not os.path.exists('output/snapshots'):
+ os.makedirs('output/snapshots')
+
+ # 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)
+ # 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']))
+
+ print 'Loading data.'
+
+ transformations = transforms.Compose([transforms.Scale(224),
+ transforms.RandomCrop(224), transforms.ToTensor(),
+ transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
+
+ pose_dataset = datasets.AFLW(args.data_dir, args.filename_list,
+ transformations)
+ train_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
+ batch_size=batch_size,
+ shuffle=True,
+ num_workers=2)
+
+ model.cuda(gpu)
+ softmax = nn.Softmax()
+ criterion = nn.CrossEntropyLoss().cuda(gpu)
+ reg_criterion = nn.MSELoss().cuda(gpu)
+ # Regression loss coefficient
+ alpha = args.alpha
+
+ idx_tensor = [idx for idx in xrange(66)]
+ idx_tensor = Variable(torch.FloatTensor(idx_tensor)).cuda(gpu)
+
+ optimizer = torch.optim.Adam([{'params': get_ignored_params(model), 'lr': 0},
+ {'params': get_non_ignored_params(model), 'lr': args.lr},
+ {'params': get_fc_params(model), 'lr': args.lr * 2}],
+ lr = args.lr)
+
+ print 'Ready to train network.'
+
+ print 'First phase of training.'
+ 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))
+
+ optimizer.zero_grad()
+ model.zero_grad()
+
+ pre_yaw, pre_pitch, pre_roll, angles = model(images)
+
+ # Cross entropy loss
+ loss_yaw = criterion(pre_yaw, label_yaw)
+ loss_pitch = criterion(pre_pitch, label_pitch)
+ loss_roll = criterion(pre_roll, label_roll)
+
+ # MSE loss
+ yaw_predicted = softmax(pre_yaw)
+ pitch_predicted = softmax(pre_pitch)
+ roll_predicted = softmax(pre_roll)
+
+ yaw_predicted = torch.sum(yaw_predicted * idx_tensor, 1)
+ pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1)
+ roll_predicted = torch.sum(roll_predicted * idx_tensor, 1)
+
+ loss_reg_yaw = reg_criterion(yaw_predicted, label_yaw.float())
+ loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
+ loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())
+
+ # print yaw_predicted, label_yaw.float(), loss_reg_yaw
+ # 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_seq = [loss_reg_yaw, loss_reg_pitch, loss_reg_roll]
+ grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
+ torch.autograd.backward(loss_seq, grad_seq)
+ optimizer.step()
+
+ 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/' + args.output_string + '_iter_'+ str(i+1) + '.pkl')
+
+ # Save models at numbered epochs.
+ if epoch % 1 == 0 and epoch < num_epochs:
+ print 'Taking snapshot...'
+ torch.save(model.state_dict(),
+ 'output/snapshots/' + args.output_string + '_epoch_'+ str(epoch+1) + '.pkl')
+
+ print 'Second phase of training (finetuning layer).'
+ for epoch in range(num_epochs_ft):
+ 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_angles = Variable(labels[:,:3].cuda(gpu))
+
+ optimizer.zero_grad()
+ model.zero_grad()
+
+ pre_yaw, pre_pitch, pre_roll, angles = model(images)
+
+ # Cross entropy loss
+ loss_yaw = criterion(pre_yaw, label_yaw)
+ loss_pitch = criterion(pre_pitch, label_pitch)
+ loss_roll = criterion(pre_roll, label_roll)
+
+ # MSE loss
+ yaw_predicted = softmax(pre_yaw)
+ pitch_predicted = softmax(pre_pitch)
+ roll_predicted = softmax(pre_roll)
+
+ yaw_predicted = torch.sum(yaw_predicted.data * idx_tensor, 1)
+ pitch_predicted = torch.sum(pitch_predicted.data * idx_tensor, 1)
+ roll_predicted = torch.sum(roll_predicted.data * idx_tensor, 1)
+
+ loss_reg_yaw = reg_criterion(yaw_predicted, label_yaw.float())
+ loss_reg_pitch = reg_criterion(pitch_predicted, label_pitch.float())
+ loss_reg_roll = reg_criterion(roll_predicted, label_roll.float())
+
+ # Total loss
+ loss_yaw += alpha * loss_reg_yaw
+ loss_pitch += alpha * loss_reg_pitch
+ loss_roll += alpha * loss_reg_roll
+
+ # Finetuning loss
+ loss_angles = reg_criterion(angles[0], label_angles.float())
+
+ loss_seq = [loss_yaw, loss_pitch, loss_roll, loss_angles]
+ grad_seq = [torch.Tensor(1).cuda(gpu) for _ in range(len(loss_seq))]
+ torch.autograd.backward(loss_seq, grad_seq)
+ optimizer.step()
+
+ if (i+1) % 100 == 0:
+ print ('Epoch [%d/%d], Iter [%d/%d] Losses: pre-yaw %.4f, pre-pitch %.4f, pre-roll %.4f, finetuning %.4f'
+ %(epoch+1, num_epochs_ft, i+1, len(pose_dataset)//batch_size, loss_yaw.data[0], loss_pitch.data[0], loss_roll.data[0], loss_angles.data[0]))
+ # if epoch == 0:
+ # torch.save(model.state_dict(),
+ # 'output/snapshots/' + args.output_string + '_iter_'+ str(i+1) + '.pkl')
+
+ # Save models at numbered epochs.
+ if epoch % 1 == 0 and epoch < num_epochs_ft - 1:
+ print 'Taking snapshot...'
+ torch.save(model.state_dict(),
+ 'output/snapshots/' + args.output_string + '_epoch_'+ str(num_epochs+epoch+1) + '.pkl')
+
+
+ # Save the final Trained Model
+ torch.save(model.state_dict(), 'output/snapshots/' + args.output_string + '_epoch_' + str(num_epochs+epoch+1) + '.pkl')
diff --git a/code/train_preangles.py b/code/train_preangles.py
index 65a2017..3179c24 100644
--- a/code/train_preangles.py
+++ b/code/train_preangles.py
@@ -134,7 +134,7 @@
criterion = nn.CrossEntropyLoss().cuda()
reg_criterion = nn.MSELoss().cuda()
# Regression loss coefficient
- alpha = 0.00
+ alpha = args.alpha
idx_tensor = [idx for idx in xrange(66)]
idx_tensor = Variable(torch.FloatTensor(idx_tensor)).cuda(gpu)
--
Gitblit v1.8.0