[icarl] Huge ugly commit, reached icarl paper performances.

Author: Arthur Douillard

inclearn/__init__.py

@@ -1 +1 @@
-from inclearn import data, factory, models, resnet, utils, results_utils
+from inclearn import parser, train

inclearn/__main__.py

@@ -6,5 +6,6 @@
 
 if args["seed_range"] is not None:
     args["seed"] = list(range(args["seed_range"][0], args["seed_range"][1] + 1))
+    print("Seed range", args["seed"])
 
 train(args)

inclearn/convnet/__init__.py

@@ -0,0 +1 @@
+from . import cifar_resnet, densenet, my_resnet, resnet

inclearn/convnet/cifar_resnet.py

@@ -0,0 +1,197 @@
+''' Incremental-Classifier Learning
+ Authors : Khurram Javed, Muhammad Talha Paracha
+ Maintainer : Khurram Javed
+ Lab : TUKL-SEECS R&D Lab
+ Email : [email protected] '''
+
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+from torch.nn import init
+
+
+class DownsampleA(nn.Module):
+    def __init__(self, nIn, nOut, stride):
+        super(DownsampleA, self).__init__()
+        assert stride == 2
+        self.avg = nn.AvgPool2d(kernel_size=1, stride=stride)
+
+    def forward(self, x):
+        x = self.avg(x)
+        return torch.cat((x, x.mul(0)), 1)
+
+
+class ResNetBasicblock(nn.Module):
+    expansion = 1
+    """
+    RexNet basicblock (https://github.com/facebook/fb.resnet.torch/blob/master/models/resnet.lua)
+    """
+
+    def __init__(self, inplanes, planes, stride=1, downsample=None):
+        super(ResNetBasicblock, self).__init__()
+
+        self.conv_a = nn.Conv2d(inplanes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn_a = nn.BatchNorm2d(planes)
+
+        self.conv_b = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn_b = nn.BatchNorm2d(planes)
+
+        self.downsample = downsample
+        self.featureSize = 64
+
+    def forward(self, x):
+        residual = x
+
+        basicblock = self.conv_a(x)
+        basicblock = self.bn_a(basicblock)
+        basicblock = F.relu(basicblock, inplace=True)
+
+        basicblock = self.conv_b(basicblock)
+        basicblock = self.bn_b(basicblock)
+
+        if self.downsample is not None:
+            residual = self.downsample(x)
+
+        return F.relu(residual + basicblock, inplace=True)
+
+
+class CifarResNet(nn.Module):
+    """
+    ResNet optimized for the Cifar Dataset, as specified in
+    https://arxiv.org/abs/1512.03385.pdf
+    """
+
+    def __init__(self, block, depth, num_classes, channels=3):
+        """ Constructor
+        Args:
+          depth: number of layers.
+          num_classes: number of classes
+          base_width: base width
+        """
+        super(CifarResNet, self).__init__()
+
+        self.featureSize = 64
+        # Model type specifies number of layers for CIFAR-10 and CIFAR-100 model
+        assert (depth - 2) % 6 == 0, 'depth should be one of 20, 32, 44, 56, 110'
+        layer_blocks = (depth - 2) // 6
+
+        self.num_classes = num_classes
+
+        self.conv_1_3x3 = nn.Conv2d(channels, 16, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn_1 = nn.BatchNorm2d(16)
+
+        self.inplanes = 16
+        self.stage_1 = self._make_layer(block, 16, layer_blocks, 1)
+        self.stage_2 = self._make_layer(block, 32, layer_blocks, 2)
+        self.stage_3 = self._make_layer(block, 64, layer_blocks, 2)
+        self.avgpool = nn.AvgPool2d(8)
+        self.out_dim = 64 * block.expansion
+
+        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. / n))
+                # m.bias.data.zero_()
+            elif isinstance(m, nn.BatchNorm2d):
+                m.weight.data.fill_(1)
+                m.bias.data.zero_()
+            elif isinstance(m, nn.Linear):
+                init.kaiming_normal(m.weight)
+                m.bias.data.zero_()
+
+    def _make_layer(self, block, planes, blocks, stride=1):
+        downsample = None
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = DownsampleA(self.inplanes, planes * block.expansion, stride)
+
+        layers = []
+        layers.append(block(self.inplanes, planes, stride, downsample))
+        self.inplanes = planes * block.expansion
+        for i in range(1, blocks):
+            layers.append(block(self.inplanes, planes))
+
+        return nn.Sequential(*layers)
+
+    def forward(self, x, feature=False, T=1, labels=False, scale=None, keep=None):
+
+        x = self.conv_1_3x3(x)
+        x = F.relu(self.bn_1(x), inplace=True)
+        x = self.stage_1(x)
+        x = self.stage_2(x)
+        x = self.stage_3(x)
+        x = self.avgpool(x)
+        x = x.view(x.size(0), -1)
+        return x
+
+    def forwardFeature(self, x):
+        pass
+
+
+def resnet20(num_classes=10):
+    """Constructs a ResNet-20 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 20, num_classes)
+    return model
+
+
+def resnet10mnist(num_classes=10):
+    """Constructs a ResNet-20 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 10, num_classes, 1)
+    return model
+
+
+def resnet20mnist(num_classes=10):
+    """Constructs a ResNet-20 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 20, num_classes, 1)
+    return model
+
+
+def resnet32mnist(num_classes=10, channels=1):
+    model = CifarResNet(ResNetBasicblock, 32, num_classes, channels)
+    return model
+
+
+def resnet32(num_classes=10):
+    """Constructs a ResNet-32 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 32, num_classes)
+    return model
+
+
+def resnet44(num_classes=10):
+    """Constructs a ResNet-44 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 44, num_classes)
+    return model
+
+
+def resnet56(num_classes=10):
+    """Constructs a ResNet-56 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 56, num_classes)
+    return model
+
+
+def resnet110(num_classes=10):
+    """Constructs a ResNet-110 model for CIFAR-10 (by default)
+    Args:
+      num_classes (uint): number of classes
+    """
+    model = CifarResNet(ResNetBasicblock, 110, num_classes)
+    return model

inclearn/convnet/densenet.py

@@ -0,0 +1,181 @@
+import re
+from collections import OrderedDict
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+__all__ = ['DenseNet', 'densenet121', 'densenet169', 'densenet201', 'densenet161']
+
+model_urls = {
+    'densenet121': 'https://download.pytorch.org/models/densenet121-a639ec97.pth',
+    'densenet169': 'https://download.pytorch.org/models/densenet169-b2777c0a.pth',
+    'densenet201': 'https://download.pytorch.org/models/densenet201-c1103571.pth',
+    'densenet161': 'https://download.pytorch.org/models/densenet161-8d451a50.pth',
+}
+
+
+class _DenseLayer(nn.Sequential):
+    def __init__(self, num_input_features, growth_rate, bn_size, drop_rate):
+        super(_DenseLayer, self).__init__()
+        self.add_module('norm1', nn.BatchNorm2d(num_input_features)),
+        self.add_module('relu1', nn.ReLU(inplace=True)),
+        self.add_module('conv1', nn.Conv2d(num_input_features, bn_size *
+                                           growth_rate, kernel_size=1, stride=1,
+                                           bias=False)),
+        self.add_module('norm2', nn.BatchNorm2d(bn_size * growth_rate)),
+        self.add_module('relu2', nn.ReLU(inplace=True)),
+        self.add_module('conv2', nn.Conv2d(bn_size * growth_rate, growth_rate,
+                                           kernel_size=3, stride=1, padding=1,
+                                           bias=False)),
+        self.drop_rate = drop_rate
+
+    def forward(self, x):
+        new_features = super(_DenseLayer, self).forward(x)
+        if self.drop_rate > 0:
+            new_features = F.dropout(new_features, p=self.drop_rate,
+                                     training=self.training)
+        return torch.cat([x, new_features], 1)
+
+
+class _DenseBlock(nn.Sequential):
+    def __init__(self, num_layers, num_input_features, bn_size, growth_rate, drop_rate):
+        super(_DenseBlock, self).__init__()
+        for i in range(num_layers):
+            layer = _DenseLayer(num_input_features + i * growth_rate, growth_rate,
+                                bn_size, drop_rate)
+            self.add_module('denselayer%d' % (i + 1), layer)
+
+
+class _Transition(nn.Sequential):
+    def __init__(self, num_input_features, num_output_features):
+        super(_Transition, self).__init__()
+        self.add_module('norm', nn.BatchNorm2d(num_input_features))
+        self.add_module('relu', nn.ReLU(inplace=True))
+        self.add_module('conv', nn.Conv2d(num_input_features, num_output_features,
+                                          kernel_size=1, stride=1, bias=False))
+        self.add_module('pool', nn.AvgPool2d(kernel_size=2, stride=2))
+
+
+class DenseNet(nn.Module):
+    r"""Densenet-BC model class, based on
+    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
+
+    Args:
+        growth_rate (int) - how many filters to add each layer (`k` in paper)
+        block_config (list of 4 ints) - how many layers in each pooling block
+        num_init_features (int) - the number of filters to learn in the first convolution layer
+        bn_size (int) - multiplicative factor for number of bottle neck layers
+          (i.e. bn_size * k features in the bottleneck layer)
+        drop_rate (float) - dropout rate after each dense layer
+        num_classes (int) - number of classification classes
+    """
+
+    def __init__(self, growth_rate=32, block_config=(6, 12, 24, 16),
+                 num_init_features=64, bn_size=4, drop_rate=0, num_classes=1000,
+                 **kwargs):
+
+        super(DenseNet, self).__init__()
+
+        # First convolution
+        self.features = nn.Sequential(OrderedDict([
+            ('conv0', nn.Conv2d(3, num_init_features, kernel_size=7, stride=2,
+                                padding=3, bias=False)),
+            ('norm0', nn.BatchNorm2d(num_init_features)),
+            ('relu0', nn.ReLU(inplace=True)),
+            ('pool0', nn.MaxPool2d(kernel_size=3, stride=2, padding=1)),
+        ]))
+
+        # Each denseblock
+        num_features = num_init_features
+        for i, num_layers in enumerate(block_config):
+            block = _DenseBlock(num_layers=num_layers, num_input_features=num_features,
+                                bn_size=bn_size, growth_rate=growth_rate,
+                                drop_rate=drop_rate)
+            self.features.add_module('denseblock%d' % (i + 1), block)
+            num_features = num_features + num_layers * growth_rate
+            if i != len(block_config) - 1:
+                trans = _Transition(num_input_features=num_features,
+                                    num_output_features=num_features // 2)
+                self.features.add_module('transition%d' % (i + 1), trans)
+                num_features = num_features // 2
+
+        # Final batch norm
+        self.features.add_module('norm5', nn.BatchNorm2d(num_features))
+
+        self.out_dim = num_features
+
+        # Official init from torch repo.
+        for m in self.modules():
+            if isinstance(m, nn.Conv2d):
+                nn.init.kaiming_normal_(m.weight)
+            elif isinstance(m, nn.BatchNorm2d):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+            elif isinstance(m, nn.Linear):
+                nn.init.constant_(m.bias, 0)
+
+    def forward(self, x):
+        features = self.features(x)
+        out = F.relu(features, inplace=True)
+        out = F.adaptive_avg_pool2d(out, (1, 1)).view(features.size(0), -1)
+        return out
+
+
+def _load_state_dict(model, model_url, progress):
+   pass
+
+def _densenet(arch, growth_rate, block_config, num_init_features, pretrained, progress,
+              **kwargs):
+    model = DenseNet(growth_rate, block_config, num_init_features, **kwargs)
+    if pretrained:
+        _load_state_dict(model, model_urls[arch], progress)
+    return model
+
+
+def densenet121(pretrained=False, progress=True, **kwargs):
+    r"""Densenet-121 model from
+    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+        progress (bool): If True, displays a progress bar of the download to stderr
+    """
+    return _densenet('densenet121', 32, (6, 12, 24, 16), 64, pretrained, progress,
+                     **kwargs)
+
+
+def densenet161(pretrained=False, progress=True, **kwargs):
+    r"""Densenet-161 model from
+    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+        progress (bool): If True, displays a progress bar of the download to stderr
+    """
+    return _densenet('densenet161', 48, (6, 12, 36, 24), 96, pretrained, progress,
+                     **kwargs)
+
+
+def densenet169(pretrained=False, progress=True, **kwargs):
+    r"""Densenet-169 model from
+    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+        progress (bool): If True, displays a progress bar of the download to stderr
+    """
+    return _densenet('densenet169', 32, (6, 12, 32, 32), 64, pretrained, progress,
+                     **kwargs)
+
+
+def densenet201(pretrained=False, progress=True, **kwargs):
+    r"""Densenet-201 model from
+    `"Densely Connected Convolutional Networks" <https://arxiv.org/pdf/1608.06993.pdf>`_
+
+    Args:
+        pretrained (bool): If True, returns a model pre-trained on ImageNet
+        progress (bool): If True, displays a progress bar of the download to stderr
+    """
+    return _densenet('densenet201', 32, (6, 12, 48, 32), 64, pretrained, progress,
+                     **kwargs)