princeton-vl / RAFT

Geek Repo:Geek Repo

Github PK Tool:Github PK Tool

Question about the "class BasicEncoder" in extractor.py

lxp1997 opened this issue · comments

Hello, I have a question about the calss BasicEncode. The channelsLayer one to layer three are 64, 96 and 128. But I saw the channels are 64, 128 and 192 in Fig7. I cannot understand it. Could you help me?

Hello,
I faced the same problem and successfully solved it in this way.
May be it is helpful.

self.layer1 = self._make_layer(64,  stride=1)
self.layer2 = self._make_layer(128, stride=2)
self.layer3 = self._make_layer(192, stride=2)
# output convolution
self.conv2 = nn.Conv2d(192, output_dim, kernel_size=1)