-
Notifications
You must be signed in to change notification settings - Fork 13
/
Copy pathutils.py
162 lines (134 loc) · 7.57 KB
/
utils.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
158
159
160
161
162
"""
This file is adapted from https://github.com/fangchangma/sparse-to-dense.pytorch
"""
import os
import torch
import shutil
import argparse
import numpy as np
import matplotlib.pyplot as plt
from PIL import Image
from model.models import Decoder
cmap = plt.cm.viridis
def parse_command():
# Define some constants
model_names = ['resnet18', 'resnet34', 'resnet50', 'resnet18_new', 'resnet18_latefusion', 'resnet18_multistage',
'resnet18_multistage_uncertainty', 'resnet18_multistage_uncertainty_fixs']
loss_names = ['l1', 'l2']
data_names = ['nuscenes']
sparsifier_names = ["uniform", "lidar_radar", "radar", "radar_filtered", "radar_filtered2"]
decoder_names = Decoder.names
modality_names = ['rgb', 'rgbd', 'd']
parser = argparse.ArgumentParser(description='Sparse-to-Dense')
parser.add_argument('--arch', '-a', metavar='ARCH', default='resnet18', choices=model_names,
help='model architecture: ' + ' | '.join(model_names) + ' (default: resnet18)')
parser.add_argument('--data', metavar='DATA', default='nyudepthv2',
choices=data_names,
help='dataset: ' + ' | '.join(data_names) + ' (default: nyudepthv2)')
parser.add_argument('--modality', '-m', metavar='MODALITY', default='rgb', choices=modality_names,
help='modality: ' + ' | '.join(modality_names) + ' (default: rgb)')
parser.add_argument('-s', '--num-samples', default=0, type=int, metavar='N',
help='number of sparse depth samples (default: 0)')
parser.add_argument('--max-depth', default=-1.0, type=float, metavar='D',
help='cut-off depth of sparsifier, negative values means infinity (default: inf [m])')
parser.add_argument('--sparsifier', metavar='SPARSIFIER', default=None, choices=sparsifier_names,
help='sparsifier: ' + ' | '.join(sparsifier_names) + ' (default: None)')
parser.add_argument('--decoder', '-d', metavar='DECODER', default='deconv2', choices=decoder_names,
help='decoder: ' + ' | '.join(decoder_names) + ' (default: deconv2)')
parser.add_argument('-j', '--workers', default=10, type=int, metavar='N',
help='number of data loading workers (default: 10)')
parser.add_argument('--epochs', default=15, type=int, metavar='N',
help='number of total epochs to run (default: 15)')
parser.add_argument('-c', '--criterion', metavar='LOSS', default='l1', choices=loss_names,
help='loss function: ' + ' | '.join(loss_names) + ' (default: l1)')
parser.add_argument('-b', '--batch-size', default=8, type=int, help='mini-batch size (default: 8)')
parser.add_argument('--lr', '--learning-rate', default=0.01, type=float,
metavar='LR', help='initial learning rate (default 0.01)')
parser.add_argument('--momentum', default=0.9, type=float, metavar='M',
help='momentum')
parser.add_argument('--weight-decay', '--wd', default=1e-4, type=float,
metavar='W', help='weight decay (default: 1e-4)')
parser.add_argument('--print-freq', '-p', default=50, type=int,
metavar='N', help='print frequency (default: 10)')
parser.add_argument('--resume', default='', type=str, metavar='PATH',
help='path to latest checkpoint (default: none)')
parser.add_argument('-e', '--evaluate', dest='evaluate', type=str, default='',
help='evaluate model on validation set')
parser.add_argument('--no-pretrain', dest='pretrained', action='store_false',
help='not to use ImageNet pre-trained weights')
parser.add_argument('--no-validation', dest="validation", action='store_false',
help="not do the evaluation during the training.")
parser.set_defaults(pretrained=True)
parser.set_defaults(validation=True)
args = parser.parse_args()
if args.modality == 'rgb' and args.num_samples != 0:
print("number of samples is forced to be 0 when input modality is rgb")
args.num_samples = 0
if args.modality == 'rgb' and args.max_depth != 0.0:
print("max depth is forced to be 0.0 when input modality is rgb/rgbd")
args.max_depth = 0.0
return args
def save_checkpoint(state, is_best, epoch, output_directory):
checkpoint_filename = os.path.join(output_directory, 'checkpoint-' + str(epoch) + '.pth.tar')
torch.save(state, checkpoint_filename)
if is_best:
best_filename = os.path.join(output_directory, 'model_best.pth.tar')
shutil.copyfile(checkpoint_filename, best_filename)
def adjust_learning_rate(optimizer, epoch, lr_init):
"""Sets the learning rate to the initial LR decayed by 10 every 5 epochs"""
lr = lr_init * (0.1 ** (epoch // 5))
for param_group in optimizer.param_groups:
param_group['lr'] = lr
# Explicitly define the learning rate schedule.
def adjust_learning_rate_new(optimizer, epoch, lr_init):
if epoch <= 6:
lr = lr_init
elif (epoch >6) and (epoch <= 15):
lr = 0.1 * lr_init
else:
lr = 0.01 * lr_init
for param_group in optimizer.param_groups:
param_group['lr'] = lr
def get_output_directory(args):
output_directory = os.path.join('results',
'{}.sparsifier={}.samples={}.modality={}.arch={}.decoder={}.criterion={}.lr={}.bs={}.pretrained={}'.
format(args.data, args.sparsifier, args.num_samples, args.modality, \
args.arch, args.decoder, args.criterion, args.lr, args.batch_size, \
args.pretrained))
return output_directory
def colored_depthmap(depth, d_min=None, d_max=None):
if d_min is None:
d_min = np.min(depth)
if d_max is None:
d_max = np.max(depth)
depth_relative = (depth - d_min) / (d_max - d_min)
return 255 * cmap(depth_relative)[:,:,:3] # H, W, C
def merge_into_row(input, depth_target, depth_pred):
# ipdb.set_trace()
rgb = 255 * np.transpose(np.squeeze(input.cpu().numpy()), (1,2,0)) # H, W, C
depth_target_cpu = np.squeeze(depth_target.cpu().numpy())
depth_pred_cpu = np.squeeze(depth_pred.data.cpu().numpy())
d_min = min(np.min(depth_target_cpu), np.min(depth_pred_cpu))
d_max = max(np.max(depth_target_cpu), np.max(depth_pred_cpu))
depth_target_col = colored_depthmap(depth_target_cpu, d_min, d_max)
depth_pred_col = colored_depthmap(depth_pred_cpu, d_min, d_max)
img_merge = np.hstack([rgb, depth_target_col, depth_pred_col])
return img_merge
def merge_into_row_with_gt(input, depth_input, depth_target, depth_pred):
# ipdb.set_trace()
rgb = 255 * np.transpose(np.squeeze(input.cpu().numpy()), (1,2,0)) # H, W, C
depth_input_cpu = np.squeeze(depth_input.cpu().numpy())
depth_target_cpu = np.squeeze(depth_target.cpu().numpy())
depth_pred_cpu = np.squeeze(depth_pred.data.cpu().numpy())
d_min = min(np.min(depth_input_cpu), np.min(depth_target_cpu), np.min(depth_pred_cpu))
d_max = max(np.max(depth_input_cpu), np.max(depth_target_cpu), np.max(depth_pred_cpu))
depth_input_col = colored_depthmap(depth_input_cpu, d_min, d_max)
depth_target_col = colored_depthmap(depth_target_cpu, d_min, d_max)
depth_pred_col = colored_depthmap(depth_pred_cpu, d_min, d_max)
img_merge = np.hstack([rgb, depth_input_col, depth_target_col, depth_pred_col])
return img_merge
def add_row(img_merge, row):
return np.vstack([img_merge, row])
def save_image(img_merge, filename):
img_merge = Image.fromarray(img_merge.astype('uint8'))
img_merge.save(filename)