From bf2f0bcfd1a7fbed462f65d44dd8589ab19ba715 Mon Sep 17 00:00:00 2001
From: natanielruiz <nataniel777@hotmail.com>
Date: 星期四, 26 十月 2017 03:19:35 +0800
Subject: [PATCH] Starting opensource
---
/dev/null | 192 --------------------------------
code/hopenet.py | 116 -------------------
2 files changed, 0 insertions(+), 308 deletions(-)
diff --git a/code/hopenet.py b/code/hopenet.py
index 80160d9..cd810e3 100644
--- a/code/hopenet.py
+++ b/code/hopenet.py
@@ -4,16 +4,6 @@
import math
import torch.nn.functional as F
-def ycbcr_to_rgb(input):
- # input is mini-batch N x 3 x H x W of an YCbCr image
- output = Variable(input.data.new(*input.size()))
- output[:, 0, :, :] = input[:, 0, :, :] + (input[:, 2, :, :] - 0.502) * 1.4
- output[:, 1, :, :] = input[:, 0, :, :] - (input[:, 1, :, :] - 0.502) * 0.343 - (input[:, 2, :, :] - 0.502) * 0.711
- output[:, 2, :, :] = input[:, 0, :, :] + (input[:, 1, :, :] - 0.502) * 1.765
- # output[output <= 0] = 0.
- # output[output > 1] = 1.
- return output
-
# CNN Model (2 conv layer)
class Simple_CNN(nn.Module):
def __init__(self):
@@ -234,112 +224,6 @@
pitch = self.fc_pitch(x)
roll = self.fc_roll(x)
return yaw, pitch, roll
-
-class Hopenet_SR(nn.Module):
- # This is just Hopenet with 3 output layers for yaw, pitch and roll.
- def __init__(self, block, layers, num_bins, upscale_factor):
- self.inplanes = 64
- super(Hopenet, self).__init__()
- # Super resolution sub-network
- self.sr_relu = nn.ReLU()
- self.sr_conv1 = nn.Conv2d(1, 64, (5, 5), (1, 1), (2, 2))
- self.sr_conv2 = nn.Conv2d(64, 64, (3, 3), (1, 1), (1, 1))
- self.sr_conv3 = nn.Conv2d(64, 32, (3, 3), (1, 1), (1, 1))
- self.sr_conv4 = nn.Conv2d(32, upscale_factor ** 2, (3, 3), (1, 1), (1, 1))
- self.sr_pixel_shuffle = nn.PixelShuffle(upscale_factor)
-
- # Pose estimation sub-network
- self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3,
- bias=False)
- self.bn1 = nn.BatchNorm2d(64)
- self.relu = nn.ReLU(inplace=True)
- self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
- self.layer1 = self._make_layer(block, 64, layers[0])
- self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
- self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
- self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
- self.avgpool = nn.AvgPool2d(7)
- self.fc_yaw = nn.Linear(512 * block.expansion, num_bins)
- self.fc_pitch = nn.Linear(512 * block.expansion, num_bins)
- self.fc_roll = nn.Linear(512 * block.expansion, num_bins)
-
- self.softmax = nn.Softmax()
- self.idx_tensor = Variable(torch.FloatTensor(range(66))).cuda()
-
- self.upscale_factor = upscale_factor
-
- for m in self.modules():
- if isinstance(m, nn.Conv2d):
- n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
- m.weight.data.normal_(0, math.sqrt(2. / n))
- elif isinstance(m, nn.BatchNorm2d):
- m.weight.data.fill_(1)
- m.bias.data.zero_()
-
- def _make_layer(self, block, planes, blocks, stride=1):
- downsample = None
- if stride != 1 or self.inplanes != planes * block.expansion:
- downsample = nn.Sequential(
- nn.Conv2d(self.inplanes, planes * block.expansion,
- kernel_size=1, stride=stride, bias=False),
- nn.BatchNorm2d(planes * block.expansion),
- )
-
- layers = []
- layers.append(block(self.inplanes, planes, stride, downsample))
- self.inplanes = planes * block.expansion
- for i in range(1, blocks):
- layers.append(block(self.inplanes, planes))
-
- return nn.Sequential(*layers)
-
- def forward(self, x):
- # Super-resolution sub-network
- y_channel = x[:,0,:,:]
-
- sr_y = self.sr_relu(self.sr_conv1(y_channel))
- sr_y = self.sr_relu(self.sr_conv2(sr_y))
- sr_y = self.sr_relu(self.sr_conv3(sr_y))
- sr_y = self.sr_pixel_shuffle(self.sr_conv4(sr_y))
-
- x[:,0,:,:] = sr_y
- x_rgb = ycbcr_to_rgb(x)
-
- out_img_cb = cb.resize(out_img_y.size, Image.BICUBIC)
- out_img_cr = cr.resize(out_img_y.size, Image.BICUBIC)
- out_img = Image.merge('YCbCr', [out_img_y, out_img_cb, out_img_cr]).convert('RGB')
-
- # Pose estimation sub-network
- x = self.conv1(sr_output)
- x = self.bn1(x)
- x = self.relu(x)
- x = self.maxpool(x)
-
- x = self.layer1(x)
- x = self.layer2(x)
- x = self.layer3(x)
- x = self.layer4(x)
-
- x = self.avgpool(x)
- x = x.view(x.size(0), -1)
- pre_yaw = self.fc_yaw(x)
- pre_pitch = self.fc_pitch(x)
- pre_roll = self.fc_roll(x)
-
- yaw = self.softmax(pre_yaw)
- yaw = Variable(torch.sum(yaw.data * self.idx_tensor.data, 1), requires_grad=True)
- pitch = self.softmax(pre_pitch)
- pitch = Variable(torch.sum(pitch.data * self.idx_tensor.data, 1), requires_grad=True)
- roll = self.softmax(pre_roll)
- roll = Variable(torch.sum(roll.data * self.idx_tensor.data, 1), requires_grad=True)
- yaw = yaw.view(yaw.size(0), 1)
- pitch = pitch.view(pitch.size(0), 1)
- roll = roll.view(roll.size(0), 1)
- angles = []
- preangles = torch.cat([yaw, pitch, roll], 1)
- angles.append(preangles)
-
- return pre_yaw, pre_pitch, pre_roll, angles, sr_y
class Hopenet_new(nn.Module):
# This is just Hopenet with 3 output layers for yaw, pitch and roll.
diff --git a/code/loss.py b/code/loss.py
deleted file mode 100644
index 805731b..0000000
--- a/code/loss.py
+++ /dev/null
@@ -1,37 +0,0 @@
-import torch
-import torch.nn as nn
-import torch.nn.functional as F
-from torch.autograd import Variable
-
-
-def one_hot(index, classes):
- size = index.size() + (classes,)
- view = index.size() + (1,)
-
- mask = torch.Tensor(*size).fill_(0)
- index = index.view(*view)
- ones = 1.
-
- if isinstance(index, Variable):
- ones = Variable(torch.Tensor(index.size()).fill_(1))
- mask = Variable(mask, volatile=index.volatile)
-
- return mask.scatter_(1, index, ones)
-
-
-class FocalLoss(nn.Module):
-
- def __init__(self, gamma=0, eps=1e-7):
- super(FocalLoss, self).__init__()
- self.gamma = gamma
- self.eps = eps
-
- def forward(self, input, target):
- y = one_hot(target, input.size(-1))
- logit = F.softmax(input)
- logit = logit.clamp(self.eps, 1. - self.eps)
-
- loss = -1 * y * torch.log(logit) # cross entropy
- loss = loss * (1 - logit) ** self.gamma # focal loss
-
- return loss.sum()
diff --git a/code/old/test_old.py b/code/old/test_old.py
deleted file mode 100644
index e831e22..0000000
--- a/code/old/test_old.py
+++ /dev/null
@@ -1,149 +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
- 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()])
-
- 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.AFLW2000(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 = 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 + '.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[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/old/test_shape.py b/code/old/test_shape.py
deleted file mode 100644
index a89e5ec..0000000
--- a/code/old/test_shape.py
+++ /dev/null
@@ -1,145 +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
- 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_shape(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, 60)
- # 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.CenterCrop(224), transforms.ToTensor()])
-
- pose_dataset = datasets.AFLW2000(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, shape = 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 + '.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[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/old/train_preangles_ft.py b/code/old/train_preangles_ft.py
deleted file mode 100644
index 1a31e7a..0000000
--- a/code/old/train_preangles_ft.py
+++ /dev/null
@@ -1,219 +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)
- 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('--dataset', dest='dataset', help='Dataset type.', default='Pose_300W_LP', type=str)
- parser.add_argument('--snapshot', dest='snapshot', help='Snapshot to start finetuning', 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.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
- 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, 0)
- # ResNet18
- # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
- if args.snapshot != '':
- load_filtered_state_dict(model, torch.load(args.snapshot))
- else:
- load_filtered_state_dict(model, model_zoo.load_url(model_urls['resnet50']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(240),
- transforms.RandomCrop(224), transforms.ToTensor(),
- transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
-
-
- if args.dataset == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list, transformations)
- elif 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 == 'AFLW_aug':
- pose_dataset = datasets.AFLW_aug(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()
- 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()
- reg_criterion = nn.MSELoss().cuda()
- # 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')
diff --git a/code/old/train_preangles_ft_sgd.py b/code/old/train_preangles_ft_sgd.py
deleted file mode 100644
index 8b0c4d1..0000000
--- a/code/old/train_preangles_ft_sgd.py
+++ /dev/null
@@ -1,219 +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)
- 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('--dataset', dest='dataset', help='Dataset type.', default='Pose_300W_LP', type=str)
- parser.add_argument('--snapshot', dest='snapshot', help='Snapshot to start finetuning', 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.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
- 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, 0)
- # ResNet18
- # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
- if args.snapshot != '':
- load_filtered_state_dict(model, torch.load(args.snapshot))
- else:
- load_filtered_state_dict(model, model_zoo.load_url(model_urls['resnet50']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(240),
- transforms.RandomCrop(224), transforms.ToTensor(),
- transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
-
-
- if args.dataset == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list, transformations)
- elif 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 == 'AFLW_aug':
- pose_dataset = datasets.AFLW_aug(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()
- 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()
- reg_criterion = nn.MSELoss().cuda()
- # 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.SGD([{'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, momentum=0.9)
-
- 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')
diff --git a/code/old/train_preangles_rmsprop.py b/code/old/train_preangles_rmsprop.py
deleted file mode 100644
index c866a5f..0000000
--- a/code/old/train_preangles_rmsprop.py
+++ /dev/null
@@ -1,281 +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('--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=0.001, type=float)
- parser.add_argument('--dataset', dest='dataset', help='Dataset type.', default='Pose_300W_LP', 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.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, 0)
- # 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(240),
- transforms.RandomCrop(224), transforms.ToTensor(),
- transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
-
-
- if args.dataset == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list, transformations)
- elif 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 == 'AFLW_aug':
- pose_dataset = datasets.AFLW_aug(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()
- 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()
- reg_criterion = nn.MSELoss().cuda()
- # 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.RMSprop([{'params': get_ignored_params(model), 'lr': 0},
- {'params': get_non_ignored_params(model), 'lr': args.lr},
- {'params': get_fc_params(model), 'lr': args.lr * 10}],
- 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/old/train_shape.py b/code/old/train_shape.py
deleted file mode 100644
index fcebadb..0000000
--- a/code/old/train_shape.py
+++ /dev/null
@@ -1,204 +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=1e-5, 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)
- 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():
- 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_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']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(224),transforms.RandomCrop(224),
- transforms.ToTensor()])
-
- 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,
- shuffle=True,
- num_workers=2)
-
- model.cuda(gpu)
- criterion = nn.CrossEntropyLoss().cuda(gpu)
- reg_criterion = nn.MSELoss().cuda(gpu)
- # Regression loss coefficient
- alpha = 0.1
-
- 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)
-
- 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 = Variable(labels[:,3:].cuda(gpu))
-
- optimizer.zero_grad()
- model.zero_grad()
-
- yaw, pitch, roll, shape = model(images)
-
- # Cross entropy loss
- loss_yaw = criterion(yaw, label_yaw)
- loss_pitch = criterion(pitch, label_pitch)
- loss_roll = criterion(roll, label_roll)
-
- # 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())
-
- # 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]
-
- # 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))]
- 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, 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_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_shape_epoch_'+ str(epoch+1) + '.pkl')
-
- # Save the final Trained Model
- torch.save(model.state_dict(), 'output/snapshots/resnet50_shape_epoch_' + str(epoch+1) + '.pkl')
diff --git a/code/test_preangles_superres.py b/code/test_preangles_superres.py
deleted file mode 100644
index 13f2451..0000000
--- a/code/test_preangles_superres.py
+++ /dev/null
@@ -1,181 +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
-
-from PIL import Image
-
-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)
- 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
- snapshot_path = args.snapshot
-
- model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, 0)
-
- 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.CenterCrop(224), transforms.ToTensor()])
-
- if args.dataset == 'AFLW2000':
- pose_dataset = datasets.AFLW2000(args.data_dir, args.filename_list,
- transformations)
- elif args.dataset == 'AFLW2000_ds':
- pose_dataset = datasets.AFLW2000_ds(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 == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(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.'
-
- # Super-resolution model
- sr_model = torch.load('data/sr_model/model_epoch_50.pth')["model"]
- sr_model = sr_model.cuda(gpu)
-
- # Test the Model
- model.eval() # Change model to 'eval' mode (BN uses moving mean/var).
- total = 0
-
- 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, cont_labels, name) in enumerate(test_loader):
-
- ### START Super-resolution ###
- # To new color space
- img = transforms.ToPILImage()(images[0])
- # print img
- img = img.convert('YCbCr')
- img_y, img_cb, img_cr = img.split()
-
- # Super-resolution
- img_y_var = Variable(transforms.ToTensor()(img_y)).view(1, -1, img_y.size[0], img_y.size[1]).cuda(gpu)
- out_sr = sr_model(img_y_var)
-
- img_h_y = out_sr.data[0].cpu().numpy().astype(np.float32)
-
- img_h_y = img_h_y * 255
- img_h_y[img_h_y<0] = 0
- img_h_y[img_h_y>255.] = 255.
- img_h_y = img_h_y[0]
-
- img_new = np.zeros((img_h_y.shape[0], img_h_y.shape[1], 3), np.uint8)
- img_new[:,:,0] = img_h_y
- img_new[:,:,1] = np.asarray(img_cb)
- img_new[:,:,2] = np.asarray(img_cr)
- img_new = Image.fromarray(img_new, "YCbCr").convert("RGB")
-
- # To tensor and normalize
- img_new.save('output/test_superres/' + name[0] + '.jpg', "JPEG")
- img = transforms.ToTensor()(img_new)
- img = transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])(img)
- images = Variable(img.view(1,-1,img.shape[1],img.shape[2])).cuda(gpu)
-
- ### END Super-resolution ###
-
- total += cont_labels.size(0)
- label_yaw = cont_labels[:,0].float()
- label_pitch = cont_labels[:,1].float()
- label_roll = cont_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() * 3 - 99
- pitch_predicted = torch.sum(pitch_predicted * idx_tensor, 1).cpu() * 3 - 99
- roll_predicted = torch.sum(roll_predicted * idx_tensor, 1).cpu() * 3 - 99
-
- # Mean absolute error
- yaw_error += torch.sum(torch.abs(yaw_predicted - label_yaw))
- pitch_error += torch.sum(torch.abs(pitch_predicted - label_pitch))
- roll_error += torch.sum(torch.abs(roll_predicted - label_roll))
-
- # Save images with pose cube.
- # TODO: fix for larger batch size
- if args.save_viz:
- name = name[0]
- if args.dataset == 'BIWI':
- cv2_img = cv2.imread(os.path.join(args.data_dir, name + '_rgb.png'))
- else:
- cv2_img = cv2.imread(os.path.join(args.data_dir, name + '.jpg'))
- if args.batch_size == 1:
- error_string = 'y %.2f, p %.2f, r %.2f' % (torch.sum(torch.abs(yaw_predicted - label_yaw)), torch.sum(torch.abs(pitch_predicted - label_pitch)), torch.sum(torch.abs(roll_predicted - label_roll)))
- cv2.putText(cv2_img, error_string, (30, cv2_img.shape[0]- 30), fontFace=1, fontScale=1, color=(0,0,255), thickness=1)
- utils.plot_pose_cube(cv2_img, yaw_predicted[0], pitch_predicted[0], roll_predicted[0])
- 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))
diff --git a/code/train_finetune.py b/code/train_finetune.py
deleted file mode 100644
index 10eb6ad..0000000
--- a/code/train_finetune.py
+++ /dev/null
@@ -1,203 +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_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=0.001, type=float)
- 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='Pose_300W_LP', type=str)
- parser.add_argument('--snapshot', dest='snapshot', help='Snapshot to start finetuning', 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)
- 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():
- 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 = []
- 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_finetune)
- 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_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, args.iter_ref)
- # ResNet18
- # model = hopenet.Hopenet(torchvision.models.resnet.BasicBlock, [2, 2, 2, 2], 66)
- if args.snapshot != '':
- load_filtered_state_dict(model, torch.load(args.snapshot))
- else:
- load_filtered_state_dict(model, model_zoo.load_url(model_urls['resnet50']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(240),
- transforms.RandomCrop(224), transforms.ToTensor(),
- transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
-
- if args.dataset == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list, transformations)
- elif 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 == 'AFLW_aug':
- pose_dataset = datasets.AFLW_aug(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()
- 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()
- reg_criterion = nn.MSELoss().cuda()
- smooth_l1_loss = nn.SmoothL1Loss().cuda()
- # 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': 0},
- {'params': get_fc_params(model), 'lr': args.lr}],
- lr = args.lr)
-
- print 'Ready to train network.'
-
- print 'Second phase of training (finetuning layer).'
- for epoch in range(num_epochs_ft):
- for i, (images, labels, cont_labels, name) in enumerate(train_loader):
- images = Variable(images.cuda(gpu))
-
- label_angles = Variable(cont_labels[:,:3].cuda(gpu))
-
- optimizer.zero_grad()
- model.zero_grad()
-
- pre_yaw, pre_pitch, pre_roll, angles = model(images)
-
- # Finetuning loss
- loss_seq = []
- for idx in xrange(1,len(angles)):
- label_angles_residuals = label_angles - (angles[0] * 3 - 99)
- # for idy in xrange(1,idx):
- # label_angles_residuals += angles[idy] * 3 - 99
- label_angles_residuals = label_angles_residuals.detach()
- # Reconvert to other unit
- label_angles_residuals = label_angles_residuals / 3.0 + 33
- loss_angles = smooth_l1_loss(angles[idx], label_angles_residuals)
- loss_seq.append(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: finetuning %.4f'
- %(epoch+1, num_epochs_ft, i+1, len(pose_dataset)//batch_size, loss_angles.data[0]))
-
- # Save models at numbered epochs.
- if epoch % 1 == 0 and epoch < num_epochs_ft:
- print 'Taking snapshot...'
- torch.save(model.state_dict(),
- 'output/snapshots/' + args.output_string + '_epoch_'+ str(epoch+1) + '.pkl')
diff --git a/code/train_finetune_new.py b/code/train_finetune_new.py
deleted file mode 100644
index 1f77d54..0000000
--- a/code/train_finetune_new.py
+++ /dev/null
@@ -1,192 +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_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=0.001, type=float)
- 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='Pose_300W_LP', type=str)
- parser.add_argument('--snapshot', dest='snapshot', help='Snapshot to start finetuning', 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)
- 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():
- 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.conv1x1)
- 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_finetune_new)
- 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_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')
-
-
- model = hopenet.Hopenet_new(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66)
-
- if args.snapshot != '':
- load_filtered_state_dict(model, torch.load(args.snapshot))
- else:
- load_filtered_state_dict(model, model_zoo.load_url(model_urls['resnet50']))
-
- print 'Loading data.'
-
- transformations = transforms.Compose([transforms.Scale(240),
- transforms.RandomCrop(224), transforms.ToTensor(),
- transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])
-
- if args.dataset == 'Pose_300W_LP':
- pose_dataset = datasets.Pose_300W_LP(args.data_dir, args.filename_list, transformations)
- elif 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 == 'AFLW_aug':
- pose_dataset = datasets.AFLW_aug(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()
- 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()
- reg_criterion = nn.MSELoss().cuda()
- smooth_l1_loss = nn.SmoothL1Loss().cuda()
- # Regression loss coefficient
- alpha = args.alpha
-
- 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}],
- lr = args.lr)
-
- print 'Ready to train network.'
-
- print 'Second phase of training (finetuning layer).'
- for epoch in range(num_epochs_ft):
- for i, (images, labels, cont_labels, name) in enumerate(train_loader):
- images = Variable(images.cuda(gpu))
-
- label_angles = Variable(cont_labels[:,:3].cuda(gpu))
-
- optimizer.zero_grad()
- model.zero_grad()
-
- pre_yaw, pre_pitch, pre_roll, preangles, final_angles = model(images)
-
- # Finetuning loss
- loss_seq = []
-
- loss_angles = smooth_l1_loss(final_angles, label_angles)
- loss_seq.append(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: finetuning %.4f'
- %(epoch+1, num_epochs_ft, i+1, len(pose_dataset)//batch_size, loss_angles.data[0]))
-
- # Save models at numbered epochs.
- if epoch % 1 == 0 and epoch < num_epochs_ft:
- print 'Taking snapshot...'
- torch.save(model.state_dict(),
- 'output/snapshots/' + args.output_string + '_epoch_'+ str(epoch+1) + '.pkl')
--
Gitblit v1.8.0