File size: 9,308 Bytes
8d34f50 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 |
import numpy as np
import torch
import torch.nn as nn
import torch.nn.functional as F
from update import BasicUpdateBlock, SmallUpdateBlock
from extractor import BasicEncoder, SmallEncoder
from corr import CorrBlock, AlternateCorrBlock
from utils_core.utils import bilinear_sampler, coords_grid, upflow8
try:
autocast = torch.cuda.amp.autocast
except:
# dummy autocast for PyTorch < 1.6
class autocast:
def __init__(self, enabled):
pass
def __enter__(self):
pass
def __exit__(self, *args):
pass
class RAFT(nn.Module):
def __init__(self, args):
super(RAFT, self).__init__()
self.args = args
if args.small:
self.hidden_dim = hdim = 96
self.context_dim = cdim = 64
args.corr_levels = 4
args.corr_radius = 3
else:
self.hidden_dim = hdim = 128
self.context_dim = cdim = 128
args.corr_levels = 4
args.corr_radius = 4
if 'dropout' not in self.args:
self.args.dropout = 0
if 'alternate_corr' not in self.args:
self.args.alternate_corr = False
# feature network, context network, and update block
if args.small:
self.fnet = SmallEncoder(output_dim=128, norm_fn='instance', dropout=args.dropout)
self.cnet = SmallEncoder(output_dim=hdim+cdim, norm_fn='none', dropout=args.dropout)
self.update_block = SmallUpdateBlock(self.args, hidden_dim=hdim)
else:
self.fnet = BasicEncoder(output_dim=256, norm_fn='instance', dropout=args.dropout)
self.cnet = BasicEncoder(output_dim=hdim+cdim, norm_fn='batch', dropout=args.dropout)
self.update_block = BasicUpdateBlock(self.args, hidden_dim=hdim)
def freeze_bn(self):
for m in self.modules():
if isinstance(m, nn.BatchNorm2d):
m.eval()
def initialize_flow(self, img):
""" Flow is represented as difference between two coordinate grids flow = coords1 - coords0"""
N, C, H, W = img.shape
coords0 = coords_grid(N, H//8, W//8).to(img.device)
coords1 = coords_grid(N, H//8, W//8).to(img.device)
# optical flow computed as difference: flow = coords1 - coords0
return coords0, coords1
def upsample_flow(self, flow, mask):
""" Upsample flow field [H/8, W/8, 2] -> [H, W, 2] using convex combination """
N, _, H, W = flow.shape
mask = mask.view(N, 1, 9, 8, 8, H, W)
mask = torch.softmax(mask, dim=2)
up_flow = F.unfold(8 * flow, [3,3], padding=1)
up_flow = up_flow.view(N, 2, 9, 1, 1, H, W)
up_flow = torch.sum(mask * up_flow, dim=2)
up_flow = up_flow.permute(0, 1, 4, 2, 5, 3)
return up_flow.reshape(N, 2, 8*H, 8*W)
def forward(self, image1, image2, iters=12, flow_init=None, upsample=True, test_mode=False):
""" Estimate optical flow between pair of frames """
image1 = 2 * (image1 / 255.0) - 1.0
image2 = 2 * (image2 / 255.0) - 1.0
image1 = image1.contiguous()
image2 = image2.contiguous()
hdim = self.hidden_dim
cdim = self.context_dim
# run the feature network
with autocast(enabled=self.args.mixed_precision):
fmap1, fmap2 = self.fnet([image1, image2])
fmap1 = fmap1.float()
fmap2 = fmap2.float()
# print("fmap mean: ", fmap1.mean(), fmap2.mean())
if self.args.alternate_corr:
corr_fn = AlternateCorrBlock(fmap1, fmap2, radius=self.args.corr_radius)
else:
corr_fn = CorrBlock(fmap1, fmap2, radius=self.args.corr_radius)
# run the context network
with autocast(enabled=self.args.mixed_precision):
cnet = self.cnet(image1)
net, inp = torch.split(cnet, [hdim, cdim], dim=1)
net = torch.tanh(net)
inp = torch.relu(inp)
coords0, coords1 = self.initialize_flow(image1)
if flow_init is not None:
coords1 = coords1 + flow_init
flow_predictions = []
for itr in range(iters):
coords1 = coords1.detach()
corr = corr_fn(coords1) # index correlation volume
flow = coords1 - coords0
with autocast(enabled=self.args.mixed_precision):
net, up_mask, delta_flow, feature = self.update_block(net, inp, corr, flow)
# print("delta flow mean: ", delta_flow.mean())
# F(t+1) = F(t) + \Delta(t)
coords1 = coords1 + delta_flow
# upsample predictions
if up_mask is None:
flow_up = upflow8(coords1 - coords0)
else:
flow_up = self.upsample_flow(coords1 - coords0, up_mask)
return flow_up, feature
class RAFT_ALL(nn.Module):
def __init__(self, args):
super(RAFT_ALL, self).__init__()
self.args = args
if args.small:
self.hidden_dim = hdim = 96
self.context_dim = cdim = 64
args.corr_levels = 4
args.corr_radius = 3
else:
self.hidden_dim = hdim = 128
self.context_dim = cdim = 128
args.corr_levels = 4
args.corr_radius = 4
if 'dropout' not in self.args:
self.args.dropout = 0
if 'alternate_corr' not in self.args:
self.args.alternate_corr = False
# feature network, context network, and update block
if args.small:
self.fnet = SmallEncoder(output_dim=128, norm_fn='instance', dropout=args.dropout)
self.cnet = SmallEncoder(output_dim=hdim+cdim, norm_fn='none', dropout=args.dropout)
self.update_block = SmallUpdateBlock(self.args, hidden_dim=hdim)
else:
self.fnet = BasicEncoder(output_dim=256, norm_fn='instance', dropout=args.dropout)
self.cnet = BasicEncoder(output_dim=hdim+cdim, norm_fn='batch', dropout=args.dropout)
self.update_block = BasicUpdateBlock(self.args, hidden_dim=hdim)
def freeze_bn(self):
for m in self.modules():
if isinstance(m, nn.BatchNorm2d):
m.eval()
def initialize_flow(self, img):
""" Flow is represented as difference between two coordinate grids flow = coords1 - coords0"""
N, C, H, W = img.shape
coords0 = coords_grid(N, H//8, W//8).to(img.device)
coords1 = coords_grid(N, H//8, W//8).to(img.device)
# optical flow computed as difference: flow = coords1 - coords0
return coords0, coords1
def upsample_flow(self, flow, mask):
""" Upsample flow field [H/8, W/8, 2] -> [H, W, 2] using convex combination """
N, _, H, W = flow.shape
mask = mask.view(N, 1, 9, 8, 8, H, W)
mask = torch.softmax(mask, dim=2)
up_flow = F.unfold(8 * flow, [3,3], padding=1)
up_flow = up_flow.view(N, 2, 9, 1, 1, H, W)
up_flow = torch.sum(mask * up_flow, dim=2)
up_flow = up_flow.permute(0, 1, 4, 2, 5, 3)
return up_flow.reshape(N, 2, 8*H, 8*W)
def forward(self, image1, image2, iters=12, flow_init=None, upsample=True, test_mode=False):
""" Estimate optical flow between pair of frames """
image1 = 2 * (image1 / 255.0) - 1.0
image2 = 2 * (image2 / 255.0) - 1.0
image1 = image1.contiguous()
image2 = image2.contiguous()
hdim = self.hidden_dim
cdim = self.context_dim
# run the feature network
with autocast(enabled=self.args.mixed_precision):
fmap1, fmap2 = self.fnet([image1, image2])
fmap1 = fmap1.float()
fmap2 = fmap2.float()
# print("fmap mean: ", fmap1.mean(), fmap2.mean())
if self.args.alternate_corr:
corr_fn = AlternateCorrBlock(fmap1, fmap2, radius=self.args.corr_radius)
else:
corr_fn = CorrBlock(fmap1, fmap2, radius=self.args.corr_radius)
# run the context network
with autocast(enabled=self.args.mixed_precision):
cnet = self.cnet(image1)
net, inp = torch.split(cnet, [hdim, cdim], dim=1)
net = torch.tanh(net)
inp = torch.relu(inp)
coords0, coords1 = self.initialize_flow(image1)
if flow_init is not None:
coords1 = coords1 + flow_init
flow_predictions = []
for itr in range(iters):
coords1 = coords1.detach()
corr = corr_fn(coords1) # index correlation volume
flow = coords1 - coords0
with autocast(enabled=self.args.mixed_precision):
net, up_mask, delta_flow, feature = self.update_block(net, inp, corr, flow)
# print("delta flow mean: ", delta_flow.mean())
# F(t+1) = F(t) + \Delta(t)
coords1 = coords1 + delta_flow
# upsample predictions
if up_mask is None:
flow_up = upflow8(coords1 - coords0)
else:
flow_up = self.upsample_flow(coords1 - coords0, up_mask)
flow_predictions.append(flow_up)
return flow_predictions, feature
|