File size: 4,694 Bytes
2c76547 |
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 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
import torch
import torch.nn as nn
# -- Added by Chu King on 16th November 2025 for debugging purposes.
import os, signal
import logging
import torch.distributed as dist
class ResidualBlock(nn.Module):
def __init__(self, in_planes, planes, norm_fn="group", stride=1):
super(ResidualBlock, self).__init__()
self.conv1 = nn.Conv2d(
in_planes, planes, kernel_size=3, padding=1, stride=stride
)
self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, padding=1)
self.relu = nn.ReLU(inplace=True)
num_groups = planes // 8
if norm_fn == "group":
self.norm1 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
self.norm2 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
self.norm3 = nn.GroupNorm(num_groups=num_groups, num_channels=planes)
elif norm_fn == "batch":
self.norm1 = nn.BatchNorm2d(planes)
self.norm2 = nn.BatchNorm2d(planes)
self.norm3 = nn.BatchNorm2d(planes)
elif norm_fn == "instance":
self.norm1 = nn.InstanceNorm2d(planes, affine=False)
self.norm2 = nn.InstanceNorm2d(planes, affine=False)
self.norm3 = nn.InstanceNorm2d(planes, affine=False)
elif norm_fn == "none":
self.norm1 = nn.Sequential()
self.norm2 = nn.Sequential()
self.norm3 = nn.Sequential()
self.downsample = nn.Sequential(
nn.Conv2d(in_planes, planes, kernel_size=1, stride=stride), self.norm3
)
def forward(self, x):
y = x
y = self.relu(self.norm1(self.conv1(y)))
y = self.relu(self.norm2(self.conv2(y)))
# -- ensures that x is transformed to the correct shape so it can be added to y.
x = self.downsample(x)
return self.relu(x + y)
class BasicEncoder(nn.Module):
def __init__(self, output_dim=128, norm_fn="batch", dropout=0.0):
super(BasicEncoder, self).__init__()
self.norm_fn = norm_fn
if self.norm_fn == "group":
self.norm1 = nn.GroupNorm(num_groups=8, num_channels=64)
elif self.norm_fn == "batch":
self.norm1 = nn.BatchNorm2d(64)
elif self.norm_fn == "instance":
self.norm1 = nn.InstanceNorm2d(64, affine=False)
elif self.norm_fn == "none":
self.norm1 = nn.Sequential()
self.conv1 = nn.Conv2d(3, 64, kernel_size=7, stride=2, padding=3)
self.relu1 = nn.ReLU(inplace=True)
self.in_planes = 64
self.layer1 = self._make_layer(64, stride=1)
self.layer2 = self._make_layer(96, stride=2)
self.layer3 = self._make_layer(128, stride=1)
# output convolution
self.conv2 = nn.Conv2d(128, output_dim, kernel_size=1)
self.dropout = None
if dropout > 0:
self.dropout = nn.Dropout2d(p=dropout)
# -- self.modules() is a PyTorch utility function that returns all submodules of this nn.Module recursively.
# -- This means it will looop through every layer: conv1, layer1, layer2, layer3, conv2 and so on.
for m in self.modules():
if isinstance(m, nn.Conv2d):
nn.init.kaiming_normal_(m.weight, mode="fan_out", nonlinearity="relu")
elif isinstance(m, (nn.BatchNorm2d, nn.InstanceNorm2d, nn.GroupNorm)):
if m.weight is not None:
nn.init.constant_(m.weight, 1)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
def _make_layer(self, dim, stride=1):
layer1 = ResidualBlock(self.in_planes, dim, self.norm_fn, stride=stride)
layer2 = ResidualBlock(dim, dim, self.norm_fn, stride=1)
layers = (layer1, layer2)
self.in_planes = dim
return nn.Sequential(*layers)
def forward(self, x):
# -- x = [L, R]
# -- L, R ~ (b*t, c, h, w)
# if input is list, combine batch dimension
is_list = isinstance(x, tuple) or isinstance(x, list)
if is_list:
batch_dim = x[0].shape[0]
x = torch.cat(x, dim=0)
x = self.conv1(x)
x = self.norm1(x)
x = self.relu1(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.conv2(x)
if self.dropout is not None:
x = self.dropout(x)
if is_list:
x = torch.split(x, x.shape[0] // 2, dim=0)
return x
|