forked from ashawkey/torch-ngp
-
Notifications
You must be signed in to change notification settings - Fork 0
/
network_tcnn.py
173 lines (137 loc) · 4.94 KB
/
network_tcnn.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
163
164
165
166
167
168
169
170
171
172
173
import torch
import torch.nn as nn
import torch.nn.functional as F
import numpy as np
import tinycudann as tcnn
from activation import trunc_exp
from .renderer import NeRFRenderer
class NeRFNetwork(NeRFRenderer):
def __init__(self,
encoding="HashGrid",
encoding_dir="SphericalHarmonics",
num_layers=2,
hidden_dim=64,
geo_feat_dim=15,
num_layers_color=3,
hidden_dim_color=64,
bound=1,
**kwargs
):
super().__init__(bound, **kwargs)
# sigma network
self.num_layers = num_layers
self.hidden_dim = hidden_dim
self.geo_feat_dim = geo_feat_dim
per_level_scale = np.exp2(np.log2(2048 * bound / 16) / (16 - 1))
self.encoder = tcnn.Encoding(
n_input_dims=3,
encoding_config={
"otype": "HashGrid",
"n_levels": 16,
"n_features_per_level": 2,
"log2_hashmap_size": 19,
"base_resolution": 16,
"per_level_scale": per_level_scale,
},
)
self.sigma_net = tcnn.Network(
n_input_dims=32,
n_output_dims=1 + self.geo_feat_dim,
network_config={
"otype": "FullyFusedMLP",
"activation": "ReLU",
"output_activation": "None",
"n_neurons": hidden_dim,
"n_hidden_layers": num_layers - 1,
},
)
# color network
self.num_layers_color = num_layers_color
self.hidden_dim_color = hidden_dim_color
self.encoder_dir = tcnn.Encoding(
n_input_dims=3,
encoding_config={
"otype": "SphericalHarmonics",
"degree": 4,
},
)
self.in_dim_color = self.encoder_dir.n_output_dims + self.geo_feat_dim
self.color_net = tcnn.Network(
n_input_dims=self.in_dim_color,
n_output_dims=3,
network_config={
"otype": "FullyFusedMLP",
"activation": "ReLU",
"output_activation": "None",
"n_neurons": hidden_dim_color,
"n_hidden_layers": num_layers_color - 1,
},
)
def forward(self, x, d):
# x: [N, 3], in [-bound, bound]
# d: [N, 3], nomalized in [-1, 1]
# sigma
x = (x + self.bound) / (2 * self.bound) # to [0, 1]
x = self.encoder(x)
h = self.sigma_net(x)
#sigma = F.relu(h[..., 0])
sigma = trunc_exp(h[..., 0])
geo_feat = h[..., 1:]
# color
d = (d + 1) / 2 # tcnn SH encoding requires inputs to be in [0, 1]
d = self.encoder_dir(d)
#p = torch.zeros_like(geo_feat[..., :1]) # manual input padding
h = torch.cat([d, geo_feat], dim=-1)
h = self.color_net(h)
# sigmoid activation for rgb
color = torch.sigmoid(h)
return sigma, color
def density(self, x):
# x: [N, 3], in [-bound, bound]
x = (x + self.bound) / (2 * self.bound) # to [0, 1]
x = self.encoder(x)
h = self.sigma_net(x)
#sigma = F.relu(h[..., 0])
sigma = trunc_exp(h[..., 0])
geo_feat = h[..., 1:]
return {
'sigma': sigma,
'geo_feat': geo_feat,
}
# allow masked inference
def color(self, x, d, mask=None, geo_feat=None, **kwargs):
# x: [N, 3] in [-bound, bound]
# mask: [N,], bool, indicates where we actually needs to compute rgb.
x = (x + self.bound) / (2 * self.bound) # to [0, 1]
if mask is not None:
rgbs = torch.zeros(mask.shape[0], 3, dtype=x.dtype, device=x.device) # [N, 3]
# in case of empty mask
if not mask.any():
return rgbs
x = x[mask]
d = d[mask]
geo_feat = geo_feat[mask]
# color
d = (d + 1) / 2 # tcnn SH encoding requires inputs to be in [0, 1]
d = self.encoder_dir(d)
h = torch.cat([d, geo_feat], dim=-1)
h = self.color_net(h)
# sigmoid activation for rgb
h = torch.sigmoid(h)
if mask is not None:
rgbs[mask] = h.to(rgbs.dtype) # fp16 --> fp32
else:
rgbs = h
return rgbs
# optimizer utils
def get_params(self, lr):
params = [
{'params': self.encoder.parameters(), 'lr': lr},
{'params': self.sigma_net.parameters(), 'lr': lr},
{'params': self.encoder_dir.parameters(), 'lr': lr},
{'params': self.color_net.parameters(), 'lr': lr},
]
if self.bg_radius > 0:
params.append({'params': self.encoder_bg.parameters(), 'lr': lr})
params.append({'params': self.bg_net.parameters(), 'lr': lr})
return params