/
test_AFW.py
157 lines (126 loc) · 5.81 KB
/
test_AFW.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
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)
parser.add_argument('--iter_ref', dest='iter_ref', default=1, type=int)
parser.add_argument('--margin', dest='margin', help='Accuracy margin.', default=22.5,
type=float)
args = parser.parse_args()
return args
if __name__ == '__main__':
args = parse_args()
cudnn.enabled = True
gpu = args.gpu_id
snapshot_path = args.snapshot
# ResNet101 with 3 outputs.
# model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 23, 3], 66)
# ResNet50
model = hopenet.Hopenet(torchvision.models.resnet.Bottleneck, [3, 4, 6, 3], 66, args.iter_ref)
# 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.AFW(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)
yaw_correct = .0
yaw_margin = args.margin
for i, (images, labels, name) in enumerate(test_loader):
images = Variable(images).cuda(gpu)
total += labels.size(0)
label_yaw = labels[:,0].float() * 3 - 99
label_pitch = labels[:,1].float() * 3 - 99
label_roll = labels[:,2].float() * 3 - 99
pre_yaw, pre_pitch, pre_roll, angles = model(images)
yaw = angles[0][:,0].cpu().data
pitch = angles[0][:,1].cpu().data
roll = angles[0][:,2].cpu().data
for idx in xrange(1,args.iter_ref+1):
yaw += angles[idx][:,0].cpu().data
pitch += angles[idx][:,1].cpu().data
roll += angles[idx][:,2].cpu().data
yaw = yaw * 3 - 99
pitch = pitch * 3 - 99
roll = roll * 3 - 99
# Mean absolute error
yaw_error += torch.sum(torch.abs(yaw - label_yaw))
pitch_error += torch.sum(torch.abs(pitch - label_pitch))
roll_error += torch.sum(torch.abs(roll - label_roll))
# Yaw accuracy
yaw_tensor_error = torch.abs(yaw - label_yaw).numpy()
yaw_correct += np.where(yaw_tensor_error <= yaw_margin)[0].shape[0]
if yaw_tensor_error[0] > yaw_margin:
print name[0] + ' ' + str(yaw[0]) + ' ' + str(label_yaw[0]) + ' ' + str(yaw_tensor_error[0])
# 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[0], pitch[0], roll[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))
print ('Yaw accuracy (<= ' + str(yaw_margin) + ' degrees) is %.4f' % (yaw_correct / total))
# Binned accuracy
# for idx in xrange(len(yaw_correct)):
# print yaw_correct[idx] / total, pitch_correct[idx] / total, roll_correct[idx] / total