File size: 2,211 Bytes
91126af |
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 |
# Copyright (C) 2024-present Naver Corporation. All rights reserved.
# Licensed under CC BY-NC-SA 4.0 (non-commercial use only).
#
# --------------------------------------------------------
# DUSt3R model class
# --------------------------------------------------------
from copy import deepcopy
import torch
import os
from packaging import version
import torch.nn as nn
import dust3r.utils.path_to_croco # noqa: F401
inf = float('inf')
import torch.nn as nn
import torch.nn.functional as F
class ConvBnReLU(nn.Module):
def __init__(self, in_channels, out_channels,
kernel_size=3, stride=1, pad=1):
super(ConvBnReLU, self).__init__()
self.conv = nn.Conv2d(in_channels, out_channels,
kernel_size, stride=stride, padding=pad, bias=False)
self.relu = nn.ReLU(inplace=True)
def forward(self, x):
return self.relu(self.conv(x))
class FeatureNet(nn.Module):
def __init__(self, norm_act=nn.BatchNorm2d):
super(FeatureNet, self).__init__()
self.conv0 = nn.Sequential(
ConvBnReLU(3, 8, 3, 1, 1),
ConvBnReLU(8, 8, 3, 1, 1))
self.conv1 = nn.Sequential(
ConvBnReLU(8, 16, 5, 2, 2),
ConvBnReLU(16, 16, 3, 1, 1))
self.conv2 = nn.Sequential(
ConvBnReLU(16, 32, 5, 2, 2),
ConvBnReLU(32, 32, 3, 1, 1))
self.toplayer = nn.Conv2d(32, 32, 1)
self.lat1 = nn.Conv2d(16, 32, 1)
self.lat0 = nn.Conv2d(8, 32, 1)
self.smooth1 = nn.Conv2d(32, 32, 3, padding=1)
self.smooth0 = nn.Conv2d(32, 32, 3, padding=1)
def _upsample_add(self, x, y):
return F.interpolate(x, scale_factor=2, mode='bilinear', align_corners=True) + y
def forward(self, x):
conv0 = self.conv0(x)
conv1 = self.conv1(conv0)
conv2 = self.conv2(conv1)
feat2 = self.toplayer(conv2)
feat1 = self._upsample_add(feat2, self.lat1(conv1))
feat0 = self._upsample_add(feat1, self.lat0(conv0))
feat1 = self.smooth1(feat1)
feat0 = self.smooth0(feat0)
return feat2, feat1, feat0
|