From b736ea13637991ba816318f3bdb37a2482bf703c Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期六, 12 八月 2017 10:38:50 +0800
Subject: [PATCH] Cleanup of old experiments
---
/dev/null | 147 -------------------------------------------------
1 files changed, 0 insertions(+), 147 deletions(-)
diff --git a/code/test.py b/code/test.py
deleted file mode 100644
index 401e02b..0000000
--- a/code/test.py
+++ /dev/null
@@ -1,82 +0,0 @@
-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 cv2
-import matplotlib.pyplot as plt
-import sys
-import os
-import argparse
-
-from datasets import AFLW2000
-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)
-
- args = parser.parse_args()
-
- return args
-
-if __name__ == '__main__':
- args = parse_args()
-
- cudnn.enabled = True
- batch_size = 1
- gpu = args.gpu_id
- snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
-
- model = hopenet.Simple_CNN()
-
- 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(302),transforms.CenterCrop(302),transforms.ToTensor()])
-
- pose_dataset = AFLW2000(args.data_dir, args.filename_list,
- transformations)
- test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=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).
- error = .0
- total = 0
- for i, (images, labels, path) in enumerate(test_loader):
- images = Variable(images).cuda(gpu)
- labels = Variable(labels).cuda(gpu)
- outputs = model(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- # TODO: There are more efficient ways.
- for idx in xrange(len(outputs)):
- error += utils.mse_loss(outputs[idx], labels[idx])
-
-
- print('Test MSE error of the model on the ' + str(total) +
- ' test images: %.4f' % (error / total))
diff --git a/code/test_resnet.py b/code/test_resnet.py
deleted file mode 100644
index 6e674c9..0000000
--- a/code/test_resnet.py
+++ /dev/null
@@ -1,94 +0,0 @@
-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 cv2
-import matplotlib.pyplot as plt
-import sys
-import os
-import argparse
-
-from datasets import AFLW2000
-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)
-
- args = parser.parse_args()
-
- return args
-
-if __name__ == '__main__':
- args = parse_args()
-
- cudnn.enabled = True
- batch_size = 1
- gpu = args.gpu_id
- snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
-
- model = torchvision.models.resnet18()
- # Parameters of newly constructed modules have requires_grad=True by default
- num_ftrs = model.fc.in_features
- model.fc = nn.Linear(num_ftrs, 3)
-
- 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()])
-
- pose_dataset = AFLW2000(args.data_dir, args.filename_list,
- transformations)
- test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=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).
- error = .0
- total = 0
- count = 0
- for i, (images, labels, name) in enumerate(test_loader):
- images = Variable(images).cuda(gpu)
- labels = Variable(labels).cuda(gpu)
- outputs = model(images)
- _, predicted = torch.max(outputs.data, 1)
- total += labels.size(0)
- # TODO: There are more efficient ways.
- for idx in xrange(len(outputs)):
- if abs(labels[idx].data[2]) * 180 / np.pi > 100:
- print name
- count += 1
- # print abs(outputs[idx].data[0] - labels[idx].data[0]) * 180 / np.pi, 180 * outputs[idx].data[0] / np.pi, labels[idx].data[0] * 180 / np.pi
- print labels[idx].data * 180 / np.pi
-
- # error += utils.mse_loss(outputs[idx], labels[idx])
- error += abs(outputs[idx].data[0] - labels[idx].data[0]) * 180 / np.pi
-
- print 'count ', count
- print('Test MSE error of the model on the ' + str(total) +
- ' test images: %.4f' % (error / total))
diff --git a/code/test_resnet_bins_grayscale.py b/code/test_resnet_bins_grayscale.py
deleted file mode 100644
index 4502346..0000000
--- a/code/test_resnet_bins_grayscale.py
+++ /dev/null
@@ -1,144 +0,0 @@
-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
- batch_size = 1
- gpu = args.gpu_id
- snapshot_path = os.path.join('output/snapshots', args.snapshot + '.pkl')
-
- # 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(),
- transforms.Lambda(lambda x: datasets.stack_grayscale_tensor(x))])
-
- pose_dataset = datasets.AFLW2000_binned(args.data_dir, args.filename_list,
- transformations, image_mode = 'L')
- test_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=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
-
- for i, (images, labels, name) in enumerate(test_loader):
- images = Variable(images).cuda(gpu)
- total += labels.size(0)
- label_yaw = labels[:,0]
- label_pitch = labels[:,1]
- label_roll = labels[:,2]
-
- yaw, pitch, roll = 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)
-
- yaw_predicted = F.softmax(yaw)
- pitch_predicted = F.softmax(pitch)
- roll_predicted = F.softmax(roll)
-
- # Continuous predictions
- yaw_predicted = torch.sum(yaw_predicted.data[0] * idx_tensor)
- pitch_predicted = torch.sum(pitch_predicted.data[0] * idx_tensor)
- roll_predicted = torch.sum(roll_predicted.data[0] * idx_tensor)
-
- # Mean absolute error
- yaw_error += abs(yaw_predicted - label_yaw[0]) * 3
- pitch_error += abs(pitch_predicted - label_pitch[0]) * 3
- roll_error += abs(roll_predicted - label_roll[0]) * 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.
- if args.save_viz:
- name = name[0]
- cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
- #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 * 3 - 99, pitch_predicted * 3 - 99, roll_predicted * 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/train.py b/code/train.py
deleted file mode 100644
index 949b1b7..0000000
--- a/code/train.py
+++ /dev/null
@@ -1,103 +0,0 @@
-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 cv2
-import matplotlib.pyplot as plt
-import sys
-import os
-import argparse
-
-from datasets import Pose_300W_LP
-import hopenet
-
-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('--batch_size', dest='batch_size', help='Batch size.',
- default=16, type=int)
- parser.add_argument('--lr', dest='lr', help='Base learning rate.',
- default=0.01, 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)
-
- args = parser.parse_args()
-
- return args
-
-if __name__ == '__main__':
- args = parse_args()
-
- cudnn.enabled = True
- num_epochs = args.num_epochs
- batch_size = args.batch_size
- gpu = args.gpu_id
-
- if not os.path.exists('output/snapshots'):
- os.makedirs('output/snapshots')
-
- # model = hopenet.Hopenet()
- model = hopenet.Simple_CNN()
-
- # Load ResNet pretrained on ImageNet.
- # saved_state_dict = torch.load('data/##pretrained-resnet##.pkl')
-
- # Replace ResNet's last layer by a regression layer.
- # for i in saved_state_dict:
- # i_parts = i.split('.')
- # if i_parts[1]=='##LASTLAYER##':
- # saved_state_dict[i] = model.state_dict()[i]
-
- # Load rest of pretrained resnet.
- #model.load_state_dict(saved_state_dict)
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(330),transforms.RandomCrop(302),transforms.ToTensor()])
-
- pose_dataset = Pose_300W_LP(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)
- criterion = nn.MSELoss(size_average = True)
- optimizer = torch.optim.Adam(model.parameters(), lr = args.lr)
-
- print 'Ready to train network.'
-
- for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images).cuda(gpu)
- labels = Variable(labels).cuda(gpu)
-
- optimizer.zero_grad()
- outputs = model(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss.data[0]))
-
- # Save models at even numbered epochs.
- if epoch % 5 == 0 and epoch < num_epochs - 1:
- print 'Taking snapshot...'
- torch.save(model.state_dict(),
- 'output/snapshots/Hopenet' + str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/Hopenet' + str(epoch+1) + '.pkl')
diff --git a/code/train_resnet.py b/code/train_resnet.py
deleted file mode 100644
index ffb9b6f..0000000
--- a/code/train_resnet.py
+++ /dev/null
@@ -1,97 +0,0 @@
-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 cv2
-import matplotlib.pyplot as plt
-import sys
-import os
-import argparse
-
-from datasets import Pose_300W_LP
-import hopenet
-
-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('--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)
-
- args = parser.parse_args()
-
- return args
-
-if __name__ == '__main__':
- args = parse_args()
-
- cudnn.enabled = True
- num_epochs = args.num_epochs
- batch_size = args.batch_size
- gpu = args.gpu_id
-
- if not os.path.exists('output/snapshots'):
- os.makedirs('output/snapshots')
-
- model = torchvision.models.resnet18(pretrained=True)
- # for param in model.parameters():
- # param.requires_grad = False
- # Parameters of newly constructed modules have requires_grad=True by default
- num_ftrs = model.fc.in_features
- model.fc = nn.Linear(num_ftrs, 3)
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(230),transforms.RandomCrop(224),
- transforms.ToTensor()])
-
- pose_dataset = Pose_300W_LP(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)
- criterion = nn.MSELoss(size_average = True)
- optimizer = torch.optim.Adam(model.parameters(), lr = args.lr)
-
- print 'Ready to train network.'
-
- for epoch in range(num_epochs):
- for i, (images, labels) in enumerate(train_loader):
- images = Variable(images).cuda(gpu)
- labels = Variable(labels).cuda(gpu)
-
- optimizer.zero_grad()
- outputs = model(images)
- loss = criterion(outputs, labels)
- loss.backward()
- optimizer.step()
-
- if (i+1) % 100 == 0:
- print ('Epoch [%d/%d], Iter [%d/%d] Loss: %.4f'
- %(epoch+1, num_epochs, i+1, len(pose_dataset)//batch_size, loss.data[0]))
-
- # Save models at even numbered epochs.
- if epoch % 1 == 0 and epoch < num_epochs - 1:
- print 'Taking snapshot...'
- torch.save(model.state_dict(),
- 'output/snapshots/resnet18_epoch_' + str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet18_epoch_' + str(epoch+1) + '.pkl')
diff --git a/code/train_resnet_bins_comb_dup.py b/code/train_resnet_bins_comb_dup.py
deleted file mode 100644
index b435b89..0000000
--- a/code/train_resnet_bins_comb_dup.py
+++ /dev/null
@@ -1,198 +0,0 @@
-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('--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)
-
- 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.layer1)
- b.append(model.layer2)
- b.append(model.layer3)
- b.append(model.layer4)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-def get_non_ignored_params(model):
- # Generator function that yields params that will be optimized.
- b = []
- b.append(model.fc_yaw)
- b.append(model.fc_pitch)
- b.append(model.fc_roll)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-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
- 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()])
-
- pose_dataset = datasets.Pose_300W_LP_binned(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)
- criterion = nn.CrossEntropyLoss()
- reg_criterion = nn.MSELoss()
- # Regression loss coefficient
- alpha = 0.1
- lsm = nn.Softmax()
-
- idx_tensor = [idx for idx in xrange(66)]
- 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}],
- 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)
-
- optimizer.zero_grad()
- yaw, pitch, roll = model(images)
-
- 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)
- pitch_predicted = F.softmax(pitch)
- roll_predicted = F.softmax(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())
-
- # print yaw_predicted[0], label_yaw.data[0]
-
- 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()
-
- # 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 (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_lowlr_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_lowlr_epoch_'+ str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet50_lowlr_epoch_' + str(epoch+1) + '.pkl')
diff --git a/code/train_resnet_bins_grayscale.py b/code/train_resnet_bins_grayscale.py
deleted file mode 100644
index 83941d0..0000000
--- a/code/train_resnet_bins_grayscale.py
+++ /dev/null
@@ -1,159 +0,0 @@
-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 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('--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)
-
- 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.layer1)
- b.append(model.layer2)
- b.append(model.layer3)
- b.append(model.layer4)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-def get_non_ignored_params(model):
- # Generator function that yields params that will be optimized.
- b = []
- b.append(model.fc_yaw)
- b.append(model.fc_pitch)
- b.append(model.fc_roll)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-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
- 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['resnet18']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224),
- transforms.ToTensor(), transforms.Lambda(lambda x: datasets.stack_grayscale_tensor(x))])
-
- pose_dataset = datasets.Pose_300W_LP_binned(args.data_dir, args.filename_list,
- transformations, image_mode='L')
- train_loader = torch.utils.data.DataLoader(dataset=pose_dataset,
- batch_size=batch_size,
- shuffle=True,
- num_workers=2)
-
- model.cuda(gpu)
- criterion = nn.CrossEntropyLoss()
- 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)
- # optimizer = torch.optim.RMSprop([{'params': get_ignored_params(model), 'lr': args.lr},
- # {'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)
-
- optimizer.zero_grad()
- yaw, pitch, roll = model(images)
- 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()
-
- 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 (i+1) % 10000 and epoch == 0:
- # torch.save(model.state_dict(), 'output/snapshots/resnet18_cr_gray_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/resnet18_cr_gray_epoch_'+ str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet18_cr_gray_epoch_' + str(epoch+1) + '.pkl')
diff --git a/code/train_resnet_bins_yaw.py b/code/train_resnet_bins_yaw.py
deleted file mode 100644
index 063f3c8..0000000
--- a/code/train_resnet_bins_yaw.py
+++ /dev/null
@@ -1,147 +0,0 @@
-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 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('--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)
-
- 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.layer1)
- b.append(model.layer2)
- b.append(model.layer3)
- b.append(model.layer4)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-def get_non_ignored_params(model):
- # Generator function that yields params that will be optimized.
- b = []
- b.append(model.fc_yaw)
- b.append(model.fc_pitch)
- b.append(model.fc_roll)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-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
- batch_size = args.batch_size
- gpu = args.gpu_id
-
- if not os.path.exists('output/snapshots'):
- os.makedirs('output/snapshots')
-
- # ResNet50 with 3 outputs.
- model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 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()])
-
- pose_dataset = datasets.Pose_300W_LP_binned(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)
- criterion = nn.CrossEntropyLoss()
- 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)
-
- 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)
-
- optimizer.zero_grad()
- yaw, pitch, roll = model(images)
- 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))]
- loss_yaw.backward()
- 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]))
-
- # 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_binned_yaw_epoch_' + str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet50_binned_yaw_epoch_' + str(epoch+1) + '.pkl')
diff --git a/code/train_resnet_bins_yaw.py~ b/code/train_resnet_bins_yaw.py~
deleted file mode 100644
index f33ffd6..0000000
--- a/code/train_resnet_bins_yaw.py~
+++ /dev/null
@@ -1,147 +0,0 @@
-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 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('--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)
-
- 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.layer1)
- b.append(model.layer2)
- b.append(model.layer3)
- b.append(model.layer4)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-def get_non_ignored_params(model):
- # Generator function that yields params that will be optimized.
- b = []
- b.append(model.fc_yaw)
- b.append(model.fc_pitch)
- b.append(model.fc_roll)
- for i in range(len(b)):
- for j in b[i].modules():
- for k in j.parameters():
- yield k
-
-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
- batch_size = args.batch_size
- gpu = args.gpu_id
-
- if not os.path.exists('output/snapshots'):
- os.makedirs('output/snapshots')
-
- # ResNet50 with 3 outputs.
- model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 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()])
-
- pose_dataset = datasets.Pose_300W_LP_binned(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)
- criterion = nn.CrossEntropyLoss()
- 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)
-
- 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)
-
- optimizer.zero_grad()
- yaw, pitch, roll = model(images)
- 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()
-
- 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]))
-
- # 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_binned_epoch_' + str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet50_binned_epoch_' + str(epoch+1) + '.pkl')
--
Gitblit v1.8.0