File size: 5,989 Bytes
4479f79 |
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 |
# Copyright (c) 2025 Bytedance Ltd. and/or its affiliates
#
# Licensed under the Apache License, Version 2.0 (the "License");
# you may not use this file except in compliance with the License.
# You may obtain a copy of the License at
#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
from torch.nn import Linear, Conv2d, BatchNorm1d, BatchNorm2d, PReLU, ReLU, Sigmoid, Dropout2d, Dropout, AvgPool2d, MaxPool2d, AdaptiveAvgPool2d, Sequential, Module, Parameter
import torch.nn.functional as F
import torch
from collections import namedtuple
import math
import pdb
class Flatten(Module):
def forward(self, input):
return input.view(input.size(0), -1)
def l2_norm(input,axis=1):
norm = torch.norm(input,2,axis,True)
output = torch.div(input, norm)
return output
class SEModule(Module):
def __init__(self, channels, reduction):
super(SEModule, self).__init__()
self.avg_pool = AdaptiveAvgPool2d(1)
self.fc1 = Conv2d(
channels, channels // reduction, kernel_size=1, padding=0 ,bias=False)
self.relu = ReLU(inplace=True)
self.fc2 = Conv2d(
channels // reduction, channels, kernel_size=1, padding=0 ,bias=False)
self.sigmoid = Sigmoid()
def forward(self, x):
module_input = x
x = self.avg_pool(x)
x = self.fc1(x)
x = self.relu(x)
x = self.fc2(x)
x = self.sigmoid(x)
return module_input * x
class bottleneck_IR(Module):
def __init__(self, in_channel, depth, stride):
super(bottleneck_IR, self).__init__()
if in_channel == depth:
self.shortcut_layer = MaxPool2d(1, stride)
else:
self.shortcut_layer = Sequential(
Conv2d(in_channel, depth, (1, 1), stride ,bias=False), BatchNorm2d(depth))
self.res_layer = Sequential(
BatchNorm2d(in_channel),
Conv2d(in_channel, depth, (3, 3), (1, 1), 1 ,bias=False), PReLU(depth),
Conv2d(depth, depth, (3, 3), stride, 1 ,bias=False), BatchNorm2d(depth))
def forward(self, x):
shortcut = self.shortcut_layer(x)
res = self.res_layer(x)
return res + shortcut
class bottleneck_IR_SE(Module):
def __init__(self, in_channel, depth, stride):
super(bottleneck_IR_SE, self).__init__()
if in_channel == depth:
self.shortcut_layer = MaxPool2d(1, stride)
else:
self.shortcut_layer = Sequential(
Conv2d(in_channel, depth, (1, 1), stride ,bias=False),
BatchNorm2d(depth))
self.res_layer = Sequential(
BatchNorm2d(in_channel),
Conv2d(in_channel, depth, (3,3), (1,1),1 ,bias=False),
PReLU(depth),
Conv2d(depth, depth, (3,3), stride, 1 ,bias=False),
BatchNorm2d(depth),
SEModule(depth,16)
)
def forward(self,x):
shortcut = self.shortcut_layer(x)
res = self.res_layer(x)
return res + shortcut
class Bottleneck(namedtuple('Block', ['in_channel', 'depth', 'stride'])):
'''A named tuple describing a ResNet block.'''
def get_block(in_channel, depth, num_units, stride = 2):
return [Bottleneck(in_channel, depth, stride)] + [Bottleneck(depth, depth, 1) for i in range(num_units-1)]
def get_blocks(num_layers):
if num_layers == 50:
blocks = [
get_block(in_channel=64, depth=64, num_units = 3),
get_block(in_channel=64, depth=128, num_units=4),
get_block(in_channel=128, depth=256, num_units=14),
get_block(in_channel=256, depth=512, num_units=3)
]
elif num_layers == 100:
blocks = [
get_block(in_channel=64, depth=64, num_units=3),
get_block(in_channel=64, depth=128, num_units=13),
get_block(in_channel=128, depth=256, num_units=30),
get_block(in_channel=256, depth=512, num_units=3)
]
elif num_layers == 152:
blocks = [
get_block(in_channel=64, depth=64, num_units=3),
get_block(in_channel=64, depth=128, num_units=8),
get_block(in_channel=128, depth=256, num_units=36),
get_block(in_channel=256, depth=512, num_units=3)
]
return blocks
class Backbone(Module):
def __init__(self, num_layers, drop_ratio, mode='ir'):
super(Backbone, self).__init__()
assert num_layers in [50, 100, 152], 'num_layers should be 50,100, or 152'
assert mode in ['ir', 'ir_se'], 'mode should be ir or ir_se'
blocks = get_blocks(num_layers)
if mode == 'ir':
unit_module = bottleneck_IR
elif mode == 'ir_se':
unit_module = bottleneck_IR_SE
self.input_layer = Sequential(Conv2d(3, 64, (3, 3), 1, 1 ,bias=False),
BatchNorm2d(64),
PReLU(64))
self.output_layer = Sequential(BatchNorm2d(512),
Dropout(drop_ratio),
Flatten(),
Linear(512 * 7 * 7, 512),
BatchNorm1d(512))
modules = []
for block in blocks:
for bottleneck in block:
modules.append(
unit_module(bottleneck.in_channel,
bottleneck.depth,
bottleneck.stride))
self.body = Sequential(*modules)
def forward(self,x):
x = self.input_layer(x)
x = self.body(x)
x = self.output_layer(x)
return l2_norm(x)
|