# ----------------------------------------------------------------------
# Numenta Platform for Intelligent Computing (NuPIC)
# Copyright (C) 2019, Numenta, Inc. Unless you have an agreement
# with Numenta, Inc., for a separate license for this software code, the
# following terms and conditions apply:
#
# This program is free software: you can redistribute it and/or modify
# it under the terms of the GNU Affero Public License version 3 as
# published by the Free Software Foundation.
#
# This program is distributed in the hope that it will be useful,
# but WITHOUT ANY WARRANTY; without even the implied warranty of
# MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.
# See the GNU Affero Public License for more details.
#
# You should have received a copy of the GNU Affero Public License
# along with this program. If not, see http://www.gnu.org/licenses.
#
# http://numenta.org/licenses/
# ----------------------------------------------------------------------
"""Modified from torchvision."""
import math
import torch.nn as nn
import torch.nn.functional as F
from torchvision.models.resnet import (
BasicBlock,
resnet18,
resnet34,
resnet50,
resnet101,
resnet152,
)
__all__ = [
"ResNet",
"resnet9",
"resnet18",
"resnet34",
"resnet50",
"resnet101",
"resnet152",
]
[docs]class ResNet(nn.Module):
def __init__(self, block, layers, num_classes=1000, in_channels=3):
self.inplanes = 64
super(ResNet, self).__init__()
self.conv1 = nn.Conv2d(
in_channels, 64, kernel_size=7, stride=2, padding=3, bias=False
)
self.bn1 = nn.BatchNorm2d(64)
self.relu = nn.ReLU(inplace=True)
self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
self.layer1 = self._make_layer(block, 64, layers[0])
self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
self.avgpool = nn.AvgPool2d(1, stride=1)
self.fc = nn.Linear(512 * block.expansion, num_classes)
for m in self.modules():
if isinstance(m, nn.Conv2d):
n = m.kernel_size[0] * m.kernel_size[1] * m.out_channels
m.weight.data.normal_(0, math.sqrt(2.0 / n))
elif isinstance(m, nn.BatchNorm2d):
m.weight.data.fill_(1)
m.bias.data.zero_()
# Some additional useful stuff
self.learning_iterations = 0
def _make_layer(self, block, planes, blocks, stride=1):
downsample = None
if stride != 1 or self.inplanes != planes * block.expansion:
downsample = nn.Sequential(
nn.Conv2d(
self.inplanes,
planes * block.expansion,
kernel_size=1,
stride=stride,
bias=False,
),
nn.BatchNorm2d(planes * block.expansion),
)
layers = []
layers.append(block(self.inplanes, planes, stride, downsample))
self.inplanes = planes * block.expansion
for _ in range(1, blocks):
layers.append(block(self.inplanes, planes))
return nn.Sequential(*layers)
[docs] def forward(self, x):
if self.training:
self.learning_iterations += x.shape[0]
x = self.conv1(x)
x = self.bn1(x)
x = self.relu(x)
x = self.maxpool(x)
x = self.layer1(x)
x = self.layer2(x)
x = self.layer3(x)
x = self.layer4(x)
x = self.avgpool(x)
x = x.view(x.size(0), -1)
x = self.fc(x)
x = F.log_softmax(x, dim=1)
return x
[docs] def post_epoch(self):
"""Does nothing.
For compatibility with our scripts.
"""
pass
[docs] def max_entropy(self):
"""Does nothing.
For compatibility with our scripts.
"""
return 0
[docs] def entropy(self):
"""Does nothing.
For compatibility with our scripts.
"""
return 0
[docs]def resnet9(pretrained=False, **kwargs):
"""Constructs a ResNet-9 model. There is no pretrained version.
Args:
pretrained (bool): ignored.
"""
model = ResNet(BasicBlock, [1, 1, 1, 1], **kwargs)
return model
