import torch import torch.nn as nn import torch.nn.functional as F #Ref: https://github.com/princeton-vl/RAFT/blob/master/core/update.py class FlowHead(nn.Module): def __init__(self, input_dim=128, hidden_dim=256): super(FlowHead, self).__init__() self.conv1 = nn.Conv2d(input_dim, hidden_dim, 3, padding=1) self.conv2 = nn.Conv2d(hidden_dim, 2, 3, padding=1) self.relu = nn.ReLU(inplace=True) def forward(self, x): return self.conv2(self.relu(self.conv1(x))) class SepConvGRU(nn.Module): def __init__(self, hidden_dim=128, input_dim=192+128): super(SepConvGRU, self).__init__() self.convz1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2)) self.convr1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2)) self.convq1 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (1,5), padding=(0,2)) self.convz2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0)) self.convr2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0)) self.convq2 = nn.Conv2d(hidden_dim+input_dim, hidden_dim, (5,1), padding=(2,0)) def forward(self, h, x): # horizontal hx = torch.cat([h, x], dim=1) z = torch.sigmoid(self.convz1(hx)) r = torch.sigmoid(self.convr1(hx)) q = torch.tanh(self.convq1(torch.cat([r*h, x], dim=1))) h = (1-z) * h + z * q # vertical hx = torch.cat([h, x], dim=1) z = torch.sigmoid(self.convz2(hx)) r = torch.sigmoid(self.convr2(hx)) q = torch.tanh(self.convq2(torch.cat([r*h, x], dim=1))) h = (1-z) * h + z * q return h class BasicMotionEncoder(nn.Module): def __init__(self, cor_planes): super(BasicMotionEncoder, self).__init__() self.convc1 = nn.Conv2d(cor_planes, 256, 1, padding=0) self.convc2 = nn.Conv2d(256, 192, 3, padding=1) self.convf1 = nn.Conv2d(2, 128, 7, padding=3) self.convf2 = nn.Conv2d(128, 64, 3, padding=1) self.conv = nn.Conv2d(64+192, 128-2, 3, padding=1) def forward(self, flow, corr): cor = F.relu(self.convc1(corr)) cor = F.relu(self.convc2(cor)) flo = F.relu(self.convf1(flow)) flo = F.relu(self.convf2(flo)) cor_flo = torch.cat([cor, flo], dim=1) out = F.relu(self.conv(cor_flo)) return torch.cat([out, flow], dim=1) class BasicUpdateBlock(nn.Module): def __init__(self, hidden_dim, cor_planes, mask_size=8): super(BasicUpdateBlock, self).__init__() self.encoder = BasicMotionEncoder(cor_planes) self.gru = SepConvGRU(hidden_dim=hidden_dim, input_dim=128+hidden_dim) self.flow_head = FlowHead(hidden_dim, hidden_dim=256) self.mask = nn.Sequential( nn.Conv2d(128, 256, 3, padding=1), nn.ReLU(inplace=True), nn.Conv2d(256, mask_size**2 *9, 1, padding=0)) def forward(self, net, inp, corr, flow, upsample=True): # print(inp.shape, corr.shape, flow.shape) motion_features = self.encoder(flow, corr) # print(motion_features.shape, inp.shape) inp = torch.cat((inp, motion_features), dim=1) net = self.gru(net, inp) delta_flow = self.flow_head(net) # scale mask to balence gradients mask = .25 * self.mask(net) return net, mask, delta_flow