upload

ckpts/resnet/cifar10/Dense_SA_best.path.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7420c8d9158ebb948094e39a17cb22ec1bd269957a41930e7171b036baedd26c
+size 89489613

ckpts/resnet/cifar10/FF/fisher_newcheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fa0010529135002e07c81491bf1985212fa28470c6e77f0c90c1f6d659037731
+size 44775689

ckpts/resnet/cifar10/FF/fisher_neweval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5ce00ed2a06fbd1a20e8ece24df65f336af83b4dca24b7f305dff9437dc3d5ee
+size 1199

ckpts/resnet/cifar10/FT/FTcheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5bc1f381a0c2c0bdf35109b5b5195b90aa3826d20966df94f6cbf340f881f782
+size 44775689

ckpts/resnet/cifar10/FT/FTeval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:331b95208b29cc2202a4a92170cec0a8e3f52a338ee79c8f1437326056808c4f
+size 1199

ckpts/resnet/cifar10/GA/GAcheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:922ef6c25c17124489e6c0754c78c9d824179d34977d6206ac1387a75e7b5e6a
+size 44775689

ckpts/resnet/cifar10/GA/GAeval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:94266550c31fa9507cc09496cfc0f81f4017401827039a0b98150dbe7c249be1
+size 1199

ckpts/resnet/cifar10/IU/wfishercheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4aee7cbb80a5961ce44ea68a6534643835edf57c7518fe35faaabba8a33147df
+size 44775689

ckpts/resnet/cifar10/IU/wfishereval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:64b013e64a4db5a48085967e498b0e21f8d5ebd563804057a1fe3a1f11e9f597
+size 1199

ckpts/resnet/cifar10/l1_sparse/FT_prunecheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:55f9adfd0450ac743a8ab08558463d32ad32b624a21657cd0bae1e9f10cbc845
+size 44775689

ckpts/resnet/cifar10/l1_sparse/FT_pruneeval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0117231e0a39b0adc48cd5348a9de7a3deaadc1efbec87ae1aa076e1d6ff7721
+size 1199

ckpts/resnet/cifar10/retrain/retraincheckpoint.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:41a05992d8ee665c9466f0468f3c447691b5e5cde015189e7e86b6f21359ca00
+size 44775689

ckpts/resnet/cifar10/retrain/retraineval_result.pth.tar

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:db34432b11e493aee52501966d3e0bd0f4d4502e154231f463430bb930805912
+size 1199

models/ResNet.py

@@ -0,0 +1,460 @@
+import torch
+import torch.nn as nn
+
+# from torchvision.models.utils import load_state_dict_from_url
+
+
+class NormalizeByChannelMeanStd(torch.nn.Module):
+    def __init__(self, mean, std):
+        super(NormalizeByChannelMeanStd, self).__init__()
+        if not isinstance(mean, torch.Tensor):
+            mean = torch.tensor(mean)
+        if not isinstance(std, torch.Tensor):
+            std = torch.tensor(std)
+        self.register_buffer("mean", mean)
+        self.register_buffer("std", std)
+
+    def forward(self, tensor):
+        return self.normalize_fn(tensor, self.mean, self.std)
+
+    def extra_repr(self):
+        return "mean={}, std={}".format(self.mean, self.std)
+
+    def normalize_fn(self, tensor, mean, std):
+        """Differentiable version of torchvision.functional.normalize"""
+        # here we assume the color channel is in at dim=1
+        mean = mean[None, :, None, None]
+        std = std[None, :, None, None]
+        return tensor.sub(mean).div(std)
+
+
+__all__ = [
+    "ResNet",
+    "resnet18",
+    "resnet34",
+    "resnet50",
+    "resnet101",
+    "resnet152",
+    "resnext50_32x4d",
+    "resnext101_32x8d",
+    "wide_resnet50_2",
+    "wide_resnet101_2",
+]
+
+
+model_urls = {
+    "resnet18": "https://download.pytorch.org/models/resnet18-5c106cde.pth",
+    "resnet34": "https://download.pytorch.org/models/resnet34-333f7ec4.pth",
+    "resnet50": "https://download.pytorch.org/models/resnet50-19c8e357.pth",
+    "resnet101": "https://download.pytorch.org/models/resnet101-5d3b4d8f.pth",
+    "resnet152": "https://download.pytorch.org/models/resnet152-b121ed2d.pth",
+    "resnext50_32x4d": "https://download.pytorch.org/models/resnext50_32x4d-7cdf4587.pth",
+    "resnext101_32x8d": "https://download.pytorch.org/models/resnext101_32x8d-8ba56ff5.pth",
+    "wide_resnet50_2": "https://download.pytorch.org/models/wide_resnet50_2-95faca4d.pth",
+    "wide_resnet101_2": "https://download.pytorch.org/models/wide_resnet101_2-32ee1156.pth",
+}
+
+
+def conv3x3(in_planes, out_planes, stride=1, groups=1, dilation=1):
+    """3x3 convolution with padding"""
+    return nn.Conv2d(
+        in_planes,
+        out_planes,
+        kernel_size=3,
+        stride=stride,
+        padding=dilation,
+        groups=groups,
+        bias=False,
+        dilation=dilation,
+    )
+
+
+def conv1x1(in_planes, out_planes, stride=1):
+    """1x1 convolution"""
+    return nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=stride, bias=False)
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+    __constants__ = ["downsample"]
+
+    def __init__(
+        self,
+        inplanes,
+        planes,
+        stride=1,
+        downsample=None,
+        groups=1,
+        base_width=64,
+        dilation=1,
+        norm_layer=None,
+    ):
+        super(BasicBlock, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        if groups != 1 or base_width != 64:
+            raise ValueError("BasicBlock only supports groups=1 and base_width=64")
+        if dilation > 1:
+            raise NotImplementedError("Dilation > 1 not supported in BasicBlock")
+        # Both self.conv1 and self.downsample layers downsample the input when stride != 1
+        self.conv1 = conv3x3(inplanes, planes, stride)
+        self.bn1 = norm_layer(planes)
+        self.relu = nn.ReLU(inplace=True)
+        self.conv2 = conv3x3(planes, planes)
+        self.bn2 = norm_layer(planes)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        identity = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+
+class Bottleneck(nn.Module):
+    expansion = 4
+    __constants__ = ["downsample"]
+
+    def __init__(
+        self,
+        inplanes,
+        planes,
+        stride=1,
+        downsample=None,
+        groups=1,
+        base_width=64,
+        dilation=1,
+        norm_layer=None,
+    ):
+        super(Bottleneck, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        width = int(planes * (base_width / 64.0)) * groups
+        # Both self.conv2 and self.downsample layers downsample the input when stride != 1
+        self.conv1 = conv1x1(inplanes, width)
+        self.bn1 = norm_layer(width)
+        self.conv2 = conv3x3(width, width, stride, groups, dilation)
+        self.bn2 = norm_layer(width)
+        self.conv3 = conv1x1(width, planes * self.expansion)
+        self.bn3 = norm_layer(planes * self.expansion)
+        self.relu = nn.ReLU(inplace=True)
+        self.downsample = downsample
+        self.stride = stride
+
+    def forward(self, x):
+        identity = x
+
+        out = self.conv1(x)
+        out = self.bn1(out)
+        out = self.relu(out)
+
+        out = self.conv2(out)
+        out = self.bn2(out)
+        out = self.relu(out)
+
+        out = self.conv3(out)
+        out = self.bn3(out)
+
+        if self.downsample is not None:
+            identity = self.downsample(x)
+
+        out += identity
+        out = self.relu(out)
+
+        return out
+
+
+class ResNet(nn.Module):
+    def __init__(
+        self,
+        block,
+        layers,
+        num_classes=1000,
+        zero_init_residual=False,
+        groups=1,
+        width_per_group=64,
+        replace_stride_with_dilation=None,
+        norm_layer=None,
+        imagenet=False,
+    ):
+        super(ResNet, self).__init__()
+        if norm_layer is None:
+            norm_layer = nn.BatchNorm2d
+        self._norm_layer = norm_layer
+
+        self.inplanes = 64
+        self.dilation = 1
+        if replace_stride_with_dilation is None:
+            # each element in the tuple indicates if we should replace
+            # the 2x2 stride with a dilated convolution instead
+            replace_stride_with_dilation = [False, False, False]
+        if len(replace_stride_with_dilation) != 3:
+            raise ValueError(
+                "replace_stride_with_dilation should be None "
+                "or a 3-element tuple, got {}".format(replace_stride_with_dilation)
+            )
+        self.groups = groups
+        self.base_width = width_per_group
+
+        print("The normalize layer is contained in the network")
+        self.normalize = NormalizeByChannelMeanStd(
+            mean=[0.4914, 0.4822, 0.4465], std=[0.2470, 0.2435, 0.2616]
+        )
+
+        if not imagenet:
+            self.conv1 = nn.Conv2d(
+                3, self.inplanes, kernel_size=3, stride=1, padding=1, bias=False
+            )
+            self.bn1 = norm_layer(self.inplanes)
+            self.relu = nn.ReLU(inplace=True)
+            self.maxpool = nn.Identity()
+        else:
+            self.conv1 = nn.Conv2d(
+                3, self.inplanes, kernel_size=7, stride=2, padding=3, bias=False
+            )
+            self.bn1 = nn.BatchNorm2d(self.inplanes)
+            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, dilate=replace_stride_with_dilation[0]
+        )
+        self.layer3 = self._make_layer(
+            block, 256, layers[2], stride=2, dilate=replace_stride_with_dilation[1]
+        )
+        self.layer4 = self._make_layer(
+            block, 512, layers[3], stride=2, dilate=replace_stride_with_dilation[2]
+        )
+        self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
+        self.fc = nn.Linear(512 * block.expansion, num_classes)
+
+        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.GroupNorm)):
+                nn.init.constant_(m.weight, 1)
+                nn.init.constant_(m.bias, 0)
+
+        # Zero-initialize the last BN in each residual branch,
+        # so that the residual branch starts with zeros, and each residual block behaves like an identity.
+        # This improves the model by 0.2~0.3% according to https://arxiv.org/abs/1706.02677
+        if zero_init_residual:
+            for m in self.modules():
+                if isinstance(m, Bottleneck):
+                    nn.init.constant_(m.bn3.weight, 0)
+                elif isinstance(m, BasicBlock):
+                    nn.init.constant_(m.bn2.weight, 0)
+
+    def _make_layer(self, block, planes, blocks, stride=1, dilate=False):
+        norm_layer = self._norm_layer
+        downsample = None
+        previous_dilation = self.dilation
+        if dilate:
+            self.dilation *= stride
+            stride = 1
+        if stride != 1 or self.inplanes != planes * block.expansion:
+            downsample = nn.Sequential(
+                conv1x1(self.inplanes, planes * block.expansion, stride),
+                norm_layer(planes * block.expansion),
+            )
+
+        layers = []
+        layers.append(
+            block(
+                self.inplanes,
+                planes,
+                stride,
+                downsample,
+                self.groups,
+                self.base_width,
+                previous_dilation,
+                norm_layer,
+            )
+        )
+        self.inplanes = planes * block.expansion
+        for _ in range(1, blocks):
+            layers.append(
+                block(
+                    self.inplanes,
+                    planes,
+                    groups=self.groups,
+                    base_width=self.base_width,
+                    dilation=self.dilation,
+                    norm_layer=norm_layer,
+                )
+            )
+
+        return nn.Sequential(*layers)
+
+    def _forward_impl(self, x):
+        # See note [TorchScript super()]
+        x = self.normalize(x)
+
+        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 = torch.flatten(x, 1)
+        # print(x.shape)
+        x = self.fc(x)
+
+        return x
+
+    def forward(self, x):
+        return self._forward_impl(x)
+
+
+def _resnet(arch, block, layers, pretrained, progress, **kwargs):
+    model = ResNet(block, layers, **kwargs)
+    if pretrained:
+        state_dict = load_state_dict_from_url(model_urls[arch], progress=progress)
+        model.load_state_dict(state_dict)
+    return model
+
+
+def resnet18(pretrained=False, progress=True, **kwargs):
+    r"""ResNet-18 model from
+    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet("resnet18", BasicBlock, [2, 2, 2, 2], pretrained, progress, **kwargs)
+
+
+def resnet34(pretrained=False, progress=True, **kwargs):
+    r"""ResNet-34 model from
+    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet("resnet34", BasicBlock, [3, 4, 6, 3], pretrained, progress, **kwargs)
+
+
+def resnet50(pretrained=False, progress=True, **kwargs):
+    r"""ResNet-50 model from
+    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet("resnet50", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs)
+
+
+def resnet101(pretrained=False, progress=True, **kwargs):
+    r"""ResNet-101 model from
+    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet(
+        "resnet101", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs
+    )
+
+
+def resnet152(pretrained=False, progress=True, **kwargs):
+    r"""ResNet-152 model from
+    `"Deep Residual Learning for Image Recognition" <https://arxiv.org/pdf/1512.03385.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 _resnet(
+        "resnet152", Bottleneck, [3, 8, 36, 3], pretrained, progress, **kwargs
+    )
+
+
+def resnext50_32x4d(pretrained=False, progress=True, **kwargs):
+    r"""ResNeXt-50 32x4d model from
+    `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
+    """
+    kwargs["groups"] = 32
+    kwargs["width_per_group"] = 4
+    return _resnet(
+        "resnext50_32x4d", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs
+    )
+
+
+def resnext101_32x8d(pretrained=False, progress=True, **kwargs):
+    r"""ResNeXt-101 32x8d model from
+    `"Aggregated Residual Transformation for Deep Neural Networks" <https://arxiv.org/pdf/1611.05431.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
+    """
+    kwargs["groups"] = 32
+    kwargs["width_per_group"] = 8
+    return _resnet(
+        "resnext101_32x8d", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs
+    )
+
+
+def wide_resnet50_2(pretrained=False, progress=True, **kwargs):
+    r"""Wide ResNet-50-2 model from
+    `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
+
+    The model is the same as ResNet except for the bottleneck number of channels
+    which is twice larger in every block. The number of channels in outer 1x1
+    convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
+    channels, and in Wide ResNet-50-2 has 2048-1024-2048.
+
+    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
+    """
+    kwargs["width_per_group"] = 64 * 2
+    return _resnet(
+        "wide_resnet50_2", Bottleneck, [3, 4, 6, 3], pretrained, progress, **kwargs
+    )
+
+
+def wide_resnet101_2(pretrained=False, progress=True, **kwargs):
+    r"""Wide ResNet-101-2 model from
+    `"Wide Residual Networks" <https://arxiv.org/pdf/1605.07146.pdf>`_
+
+    The model is the same as ResNet except for the bottleneck number of channels
+    which is twice larger in every block. The number of channels in outer 1x1
+    convolutions is the same, e.g. last block in ResNet-50 has 2048-512-2048
+    channels, and in Wide ResNet-50-2 has 2048-1024-2048.
+
+    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
+    """
+    kwargs["width_per_group"] = 64 * 2
+    return _resnet(
+        "wide_resnet101_2", Bottleneck, [3, 4, 23, 3], pretrained, progress, **kwargs
+    )