Initial commit.

CV_benchmark/config/logger.conf

@@ -0,0 +1,53 @@
+[loggers]
+keys=root,TRAIN,TEST,EVAL
+
+[handlers]
+keys=consoleHandler,fileHandler
+
+[formatters]
+keys=simpleFormatter
+
+[logger_root]
+level=INFO
+handlers=consoleHandler,fileHandler
+
+[logger_TRAIN]
+level=INFO
+handlers=consoleHandler,fileHandler
+qualname=TRAIN
+propagate=0
+
+[logger_VAL]
+level=INFO
+handlers=consoleHandler,fileHandler
+qualname=VAL
+propagate=0
+
+[logger_TEST]
+level=INFO
+handlers=consoleHandler,fileHandler
+qualname=TEST
+propagate=0
+
+[logger_EVAL]
+level=INFO
+handlers=consoleHandler,fileHandler
+qualname=simpleExample
+propagate=0
+
+[handler_consoleHandler]
+class=StreamHandler
+level=INFO
+formatter=simpleFormatter
+args=(sys.stdout,)
+
+[handler_fileHandler]
+class = FileHandler
+level=INFO
+formatter=simpleFormatter
+args=('/output/log/log.txt','a')
+
+
+[formatter_simpleFormatter]
+format=%(asctime)s - %(name)s - %(levelname)s - %(message)s
+datefmt=%Y-%m-%d %H:%M:%S

CV_benchmark/config/mainconfig.py

@@ -0,0 +1,25 @@
+# file location
+
+# ROOT_DIR="/home/xujiahong/VeRi_try/openI"
+ROOT_DIR=""
+
+# output dir
+CODE_ROOT_DIR = ROOT_DIR + "/code"
+# CODE_ROOT_DIR = '/home/xujiahong/openI_benchmark/BoT_person_reID'
+
+# config dir
+CONFIG_PATH = CODE_ROOT_DIR + "/config/re_ID.yaml"
+
+# output dir 
+OUTPUT_RESULT_DIR= "/output/result/"
+EVAL_RESULT_PATH = "/output/log/eval_result.json"
+FULL_INFO_PATH = "/output/log/full_info.json"
+LOGGER_PATH = "/output/log/log.txt" #与logger.conf 中的值保持一致
+
+# upload API
+UPLOAD_EVAL_RESULT_API = "http://192.168.202.90:6134/api/benchmark-result/"
+DEBUG_MODE = True
+REID_TYPE = {1: "vehicle reid", 2:"image-based person reid", 3:"person search", 4:"video-based person reid"}
+ALG_TYPE = "Re-ID"
+USER_INFO_PATH = "/benchmark/taskInfo"
+

CV_benchmark/config/re_ID.yaml

@@ -0,0 +1,35 @@
+# scene: type of re-ID
+# four types in total:
+# 1. vehicle reid
+# 2. image_based person reid
+# 3. person search
+# 4. video-based person reid
+scene: 2
+attr_name: 
+attr_value: 
+
+input:
+  dataset:
+    # data_dir: /root/small_market1501
+    # data_dir: /dataset/small_market1501
+    data_dir: /dataset/benchmark_vehicle_reID
+    # data_dir: /dataset/1_Market1501
+
+  config: 
+    adam: True
+    batchsize: 128
+    droprate: 0.2
+    erasing_p: 0
+    h: 256
+    w: 256
+    inputsize: 256
+    lr: 0.00035
+    name: Res50
+    nclass: 2304  #class number of benchmark_person_reID
+    num_epochs: 1
+    pool: avg
+    stride: 1
+    warm_epoch: 0
+
+test:
+  flip_test: True

CV_benchmark/data_utils/__init__.py

@@ -0,0 +1,3 @@
+from .label_smooth import *
+from .model_train import *
+from .triplet import *

CV_benchmark/data_utils/label_smooth.py

@@ -0,0 +1,33 @@
+from __future__ import print_function, absolute_import
+
+import torch
+from torch import nn
+
+
+class LSR_loss(nn.Module):
+
+    def __init__(self, e=0.1):
+        super().__init__()
+        self.log_softmax = nn.LogSoftmax(dim=1)
+        self.e = e
+
+    def _one_hot(self, labels, classes, value=1):
+        one_hot = torch.zeros(labels.size(0), classes)
+        # labels and value_added  size must match
+        labels = labels.view(labels.size(0), -1)
+        value_added = torch.Tensor(labels.size(0), 1).fill_(value)
+        value_added = value_added.to(labels.device)
+        one_hot = one_hot.to(labels.device)
+        one_hot.scatter_add_(1, labels, value_added)
+        return one_hot
+
+    def _smooth_label(self, target, length, smooth_factor):
+        one_hot = self._one_hot(target, length, value=1 - smooth_factor)
+        one_hot += smooth_factor / length
+        return one_hot.to(target.device)
+
+    def forward(self, x, target):
+        smoothed_target = self._smooth_label(target, x.size(1), self.e)
+        x = self.log_softmax(x)
+        loss = torch.sum(- x * smoothed_target, dim=1)
+        return torch.mean(loss)

CV_benchmark/data_utils/model_train.py

@@ -0,0 +1,157 @@
+import argparse
+import torch
+import torch.nn as nn
+from torch.nn import init
+from torchvision import models
+from torch.autograd import Variable
+#from efficientnet_pytorch import EfficientNet
+#import pretrainedmodels
+from torch.nn import functional as F
+
+######################################################################
+def weights_init_kaiming(m):
+    classname = m.__class__.__name__
+    # print(classname)
+    if classname.find('Conv') != -1:
+        init.kaiming_normal_(m.weight.data, a=0, mode='fan_in') # For old pytorch, you may use kaiming_normal.
+    elif classname.find('Linear') != -1:
+        init.kaiming_normal_(m.weight.data, a=0, mode='fan_out')
+        init.constant_(m.bias.data, 0.0)
+    elif classname.find('BatchNorm1d') != -1:
+        init.normal_(m.weight.data, 1.0, 0.02)
+        init.constant_(m.bias.data, 0.0)
+
+def weights_init_classifier(m):
+    classname = m.__class__.__name__
+    if classname.find('Linear') != -1:
+        init.normal_(m.weight.data, std=0.001)
+        init.constant_(m.bias.data, 0.0)
+
+def fix_relu(m):
+    classname = m.__class__.__name__
+    if classname.find('ReLU') != -1:
+        m.inplace=True
+# Defines the new fc layer and classification layer
+# |--Linear--|--bn--|--relu--|--Linear--|
+class ClassBlock(nn.Module):
+    '''
+    xjh_notes: 
+    -----------------------
+    Defines the linear layers after the adp avg pooling layer in the backbone
+    -----------------------
+    Parameters:
+        linear - if add a fc layer of size [input_dim, num_bottleneck]
+        bnorm  - if add a bn layer
+        relu   - if add a leakyReLU layer
+        droprate - if droprate > 0, using dropout in add_block
+
+    '''
+    def __init__(self, input_dim, class_num, droprate, relu=True, bnorm=True, num_bottleneck=2048, linear=True, return_f = False):
+        super(ClassBlock, self).__init__()
+        self.return_f = return_f
+        add_block = []
+        if linear:
+            add_block += [nn.Linear(input_dim, num_bottleneck)]
+        else:
+            num_bottleneck = input_dim
+        if bnorm:
+            add_block += [nn.BatchNorm1d(num_bottleneck)]
+        if relu:
+            add_block += [nn.LeakyReLU(0.1)]
+        if droprate>0:
+            add_block += [nn.Dropout(p=droprate)]
+        add_block = nn.Sequential(*add_block)
+        add_block.apply(weights_init_kaiming)
+
+        classifier = []
+        classifier += [nn.Linear(num_bottleneck, class_num)]
+        classifier = nn.Sequential(*classifier)
+        classifier.apply(weights_init_classifier)
+
+        self.add_block = add_block
+        self.classifier = classifier
+    def forward(self, x):
+        f = x
+        x = self.add_block(x)
+        x = self.classifier(x)
+        if self.return_f:
+            return x,f
+        else:
+            return x
+
+# Define the ResNet50-based Model
+class ft_net(nn.Module):
+
+    def __init__(self, class_num, droprate=0.5, stride=2, init_model=None, pool='avg', return_f=True):
+        self.return_f=return_f
+        super(ft_net, self).__init__()
+        model_ft = models.resnet50(pretrained=True)
+        # avg pooling to global pooling
+        if stride == 1:
+            model_ft.layer4[0].downsample[0].stride = (1,1)
+            model_ft.layer4[0].conv2.stride = (1,1)
+
+        self.pool = pool
+        if pool =='avg+max':
+            model_ft.avgpool2 = nn.AdaptiveAvgPool2d((1,1))
+            model_ft.maxpool2 = nn.AdaptiveMaxPool2d((1,1))
+            self.model = model_ft
+            self.classifier= ClassBlock(2048, class_num, droprate, return_f=self.return_f, linear=False)
+        elif pool=='avg':
+            model_ft.avgpool = nn.AdaptiveAvgPool2d((1,1))
+            self.model = model_ft
+            self.classifier= ClassBlock(2048, class_num, droprate, return_f=self.return_f, linear=False)
+
+        if init_model!=None:
+            self.flag = True
+            self.model = init_model.model
+            self.pool = init_model.pool
+            self.classifier.add_block = init_model.classifier.add_block
+        # avg pooling to global pooling
+
+    def forward(self, x):
+        x = self.model.conv1(x)
+        x = self.model.bn1(x)
+        x = self.model.relu(x)
+        x = self.model.maxpool(x)
+        x = self.model.layer1(x)
+        x = self.model.layer2(x)
+        x = self.model.layer3(x)
+        x = self.model.layer4(x)
+        if self.pool == 'avg+max':
+            x1 = self.model.avgpool2(x)
+            x2 = self.model.maxpool2(x)
+            x = torch.cat((x1,x2), dim = 1)
+            x = x.view(x.size(0), x.size(1))
+        elif self.pool == 'avg':
+            x = self.model.avgpool(x)
+            x = x.view(x.size(0), x.size(1))
+            
+        output = self.classifier(x)  #if return_f: return (fc, feature) else return fc
+        return output
+
+
+'''
+# debug model structure
+# Run this code with:
+python model.py
+'''
+if __name__ == '__main__':
+# Here I left a simple forward function.
+# Test the model, before you train it. 
+
+    '''
+    net = CPB(751)
+    #net = ft_net_SE(751)
+    print(net)
+    input = Variable(torch.FloatTensor(4, 3, 320, 320))
+    output = net(input)
+    print('net output size:')
+    #print(output.shape)
+    '''
+
+    xjh_net = ft_net(333)
+    print(xjh_net)
+    input = Variable(torch.FloatTensor(2,3,384,384))
+    output = xjh_net(input)
+    print(output.shape)

CV_benchmark/data_utils/triplet.py

@@ -0,0 +1,170 @@
+from __future__ import absolute_import
+
+import torch
+from torch import nn
+
+
+def normalize(x, axis=-1):
+    """Normalizing to unit length along the specified dimension.
+    Args:
+        x: pytorch Variable
+    Returns:
+        x: pytorch Variable, same shape as input
+    """
+    x = 1. * x / (torch.norm(x, 2, axis, keepdim=True).expand_as(x) + 1e-12)
+    return x
+
+
+def euclidean_dist(x, y):
+    """
+    Args:
+        x: pytorch Variable, with shape [m, d]
+        y: pytorch Variable, with shape [n, d]
+    Returns:
+        dist: pytorch Variable, with shape [m, n]
+    """
+    m, n = x.size(0), y.size(0)
+    xx = torch.pow(x, 2).sum(1, keepdim=True).expand(m, n)
+    yy = torch.pow(y, 2).sum(1, keepdim=True).expand(n, m).t()
+    dist = xx + yy
+    # dist.addmm_(1, -2, x, y.t())
+    dist.addmm_( x, y.t(), beta = 1, alpha = -2)
+    dist = dist.clamp(min=1e-12).sqrt()  # for numerical stability
+    return dist
+
+
+def hard_example_mining(dist_mat, labels, return_inds=False):
+    """For each anchor, find the hardest positive and negative sample.
+    Args:
+        dist_mat: pytorch Variable, pair wise distance between samples, shape [N, N]
+        labels: pytorch LongTensor, with shape [N]
+        return_inds: whether to return the indices. Save time if `False`(?)
+    Returns:
+        dist_ap: pytorch Variable, distance(anchor, positive); shape [N]
+        dist_an: pytorch Variable, distance(anchor, negative); shape [N]
+        p_inds: pytorch LongTensor, with shape [N];
+            indices of selected hard positive samples; 0 <= p_inds[i] <= N - 1
+        n_inds: pytorch LongTensor, with shape [N];
+            indices of selected hard negative samples; 0 <= n_inds[i] <= N - 1
+    NOTE: Only consider the case in which all labels have same num of samples,
+        thus we can cope with all anchors in parallel.
+    """
+
+    assert len(dist_mat.size()) == 2
+    assert dist_mat.size(0) == dist_mat.size(1)
+    N = dist_mat.size(0)
+
+    # shape [N, N]
+    is_pos = labels.expand(N, N).eq(labels.expand(N, N).t())
+    is_neg = labels.expand(N, N).ne(labels.expand(N, N).t())
+
+    '''
+    # `dist_ap` means distance(anchor, positive)
+    # both `dist_ap` and `relative_p_inds` with shape [N, 1]
+
+    dist_ap, relative_p_inds = torch.max(dist_mat[is_pos].contiguous().view(N, -1), 1, keepdim=True)
+    # `dist_an` means distance(anchor, negative)
+    # both `dist_an` and `relative_n_inds` with shape [N, 1]
+    dist_an, relative_n_inds = torch.min(dist_mat[is_neg].contiguous().view(N, -1), 1, keepdim=True)
+    # shape [N]
+    dist_ap = dist_ap.squeeze(1)
+    dist_an = dist_an.squeeze(1)
+    '''
+
+    dist_ap, relative_p_inds = torch.max(dist_mat.masked_fill(is_neg, 0), 1, keepdim=True)
+    dist_an, relative_n_inds = torch.min(dist_mat.masked_fill(is_pos, float("inf")), 1, keepdim=True)
+
+    # dist_ap1, dist_an1 = [], []
+    # for i in range(N):
+    #     dist_ap1.append(dist_mat[i][is_pos[i]].max().unsqueeze(0))
+    #     dist_an1.append(dist_mat[i][is_pos[i] == 0].min().unsqueeze(0))
+
+    # dist_ap1, dist_an1 = torch.tensor(dist_ap1), torch.tensor(dist_an1)
+
+    if return_inds:
+        # shape [N, N]
+        ind = (labels.new().resize_as_(labels).copy_(torch.arange(0, N).long()).unsqueeze(0).expand(N, N))
+        # shape [N, 1]
+        p_inds = torch.gather(ind[is_pos].contiguous().view(N, -1), 1, relative_p_inds.data)
+        n_inds = torch.gather(ind[is_neg].contiguous().view(N, -1), 1, relative_n_inds.data)
+        # shape [N]
+        p_inds = p_inds.squeeze(1)
+        n_inds = n_inds.squeeze(1)
+        return dist_ap, dist_an, p_inds, n_inds
+
+    return dist_ap, dist_an
+
+
+class TripletLoss(nn.Module):
+    def __init__(self, margin=None):
+        super(TripletLoss, self).__init__()
+        self.margin = margin
+        if self.margin is not None:
+            self.ranking_loss = nn.MarginRankingLoss(margin=margin)
+        else:
+            self.ranking_loss = nn.SoftMarginLoss()
+
+    def forward(self, global_feat, labels, normalize_feature=False):
+        if normalize_feature:
+            global_feat = normalize(global_feat, axis=-1)
+        # shape [N, N]
+        dist_mat = euclidean_dist(global_feat, global_feat)
+        dist_ap, dist_an = hard_example_mining(dist_mat, labels)
+        y = dist_an.new().resize_as_(dist_an).fill_(1)
+        if self.margin is not None:
+            loss = self.ranking_loss(dist_an, dist_ap, y)
+        else:
+            loss = self.ranking_loss(dist_an - dist_ap, y)
+        prec = (dist_an.data > dist_ap.data).sum().float() / y.size(0)
+        return loss, prec, dist_ap, dist_an
+
+
+class Center_loss(nn.Module):
+    """Center loss.
+    Reference:
+    Wen et al. A Discriminative Feature Learning Approach for Deep Face Recognition. ECCV 2016.
+    Args:
+        num_classes (int): number of classes.
+        feat_dim (int): feature dimension.
+    """
+
+    def __init__(self, num_classes=751, feat_dim=2048, use_gpu=True):
+        super(Center_loss, self).__init__()
+        self.num_classes = num_classes
+        self.feat_dim = feat_dim
+        self.use_gpu = use_gpu
+
+        if self.use_gpu:
+            self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim).cuda())
+        else:
+            self.centers = nn.Parameter(torch.randn(self.num_classes, self.feat_dim))
+
+    def forward(self, x, labels):
+        """
+        Args:
+            x: feature matrix with shape (batch_size, feat_dim).
+            labels: ground truth labels with shape (num_classes).
+        """
+        assert x.size(0) == labels.size(0), "features.size(0) is not equal to labels.size(0)"
+
+        batch_size = x.size(0)
+        distmat = torch.pow(x, 2).sum(dim=1, keepdim=True).expand(batch_size, self.num_classes) + \
+                  torch.pow(self.centers, 2).sum(dim=1, keepdim=True).expand(self.num_classes, batch_size).t()
+        distmat.addmm_(1, -2, x, self.centers.t())
+
+        classes = torch.arange(self.num_classes).long()
+        if self.use_gpu: classes = classes.cuda()
+        labels = labels.unsqueeze(1).expand(batch_size, self.num_classes)
+        mask = labels.eq(classes.expand(batch_size, self.num_classes))
+
+        dist = distmat * mask.float()
+        loss = dist.clamp(min=1e-12, max=1e+12).sum() / batch_size
+        #dist = []
+        #for i in range(batch_size):
+        #    value = distmat[i][mask[i]]
+        #    value = value.clamp(min=1e-12, max=1e+12)  # for numerical stability
+        #    dist.append(value)
+        #dist = torch.cat(dist)
+        #loss = dist.mean()
+        return loss
+

Case_CIFAR10/README.md

@@ -0,0 +1,56 @@
+# CIFAR-10图像识别项目实战
+
+本实战项目是一个CIFAR-10的图像分类任务，基于CIFAR10的数据集和【PyTorch】，通过在云脑环境调试和训练模型，最终评估模型的准确率。
+
+## 文件资料说明
+
+- 《Case1》文件夹，是基于云脑1算力资源（CPU/GPU）进行任务调试与训练的代码文件
+
+- 《Case2》文件夹，是基于云脑2算力资源（Ascend NPU）进行任务调试与训练的代码文件
+
+- 《教程》文件夹，是本次项目实战的详细教程 
+
+- CIFAR.zip，是本次项目使用的数据集
+
+## 前置条件
+- Python 3.6+
+- PyTorch 1.0+
+
+## 云脑1（CPU/GPU）模型调试与训练
+```
+ls
+
+#（相应代码放在/code下，相应数据集放在/dataset下）
+cd /code/case1 
+
+python main.py
+```
+<div align="center">
+<img src= ./case1/img/train.png width=100%>
+</div>
+<br>
+
+## 云脑2（Ascend NPU）模型调试
+```
+#克隆代码，在代码页的HTTPS点击复制链接，在此处!git clone后面粘贴链接
+!git clone 
+
+#解压数据集
+!unzip cifar.zip
+
+#运行代码
+!python OpenI_test/case2/train.py --dataset_path ./cifar-10-batches-bin/
+```
+
+## 云脑2（Ascend NPU）模型训练
+
+在新建训练任务中，输入指定文件为“case2/train.py”，数据集指定为cifar.zip，点击提交即可
+
+
+## 部分模型准确率训练结果：
+
+| Model             | Acc.        |
+| ----------------- | ----------- |
+| [VGG16](https://arxiv.org/abs/1409.1556)              | 92.64%      |
+| [DLA](https://arxiv.org/pdf/1707.06484.pdf)           | 95.47%      |
+

Case_CIFAR10/case1/LICENSE

@@ -0,0 +1,21 @@
+MIT License
+
+Copyright (c) 2017 liukuang
+
+Permission is hereby granted, free of charge, to any person obtaining a copy
+of this software and associated documentation files (the "Software"), to deal
+in the Software without restriction, including without limitation the rights
+to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
+copies of the Software, and to permit persons to whom the Software is
+furnished to do so, subject to the following conditions:
+
+The above copyright notice and this permission notice shall be included in all
+copies or substantial portions of the Software.
+
+THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+SOFTWARE.

Case_CIFAR10/case1/main.py

@@ -0,0 +1,154 @@
+'''Train CIFAR10 with PyTorch.'''
+import torch
+import torch.nn as nn
+import torch.optim as optim
+import torch.nn.functional as F
+import torch.backends.cudnn as cudnn
+
+import torchvision
+import torchvision.transforms as transforms
+
+import os
+import argparse
+
+from models import *
+from utils import progress_bar
+
+
+parser = argparse.ArgumentParser(description='PyTorch CIFAR10 Training')
+parser.add_argument('--lr', default=0.1, type=float, help='learning rate')
+parser.add_argument('--resume', '-r', action='store_true',
+                    help='resume from checkpoint')
+args = parser.parse_args()
+
+device = 'cuda' if torch.cuda.is_available() else 'cpu'
+best_acc = 0  # best test accuracy
+start_epoch = 0  # start from epoch 0 or last checkpoint epoch
+
+# Data
+print('==> Preparing data..')
+transform_train = transforms.Compose([
+    transforms.RandomCrop(32, padding=4),
+    transforms.RandomHorizontalFlip(),
+    transforms.ToTensor(),
+    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
+])
+
+transform_test = transforms.Compose([
+    transforms.ToTensor(),
+    transforms.Normalize((0.4914, 0.4822, 0.4465), (0.2023, 0.1994, 0.2010)),
+])
+
+trainset = torchvision.datasets.CIFAR10(
+    root='/dataset/', train=True, download=False, transform=transform_train)
+trainloader = torch.utils.data.DataLoader(
+    trainset, batch_size=128, shuffle=True, num_workers=2)
+
+testset = torchvision.datasets.CIFAR10(
+    root='/dataset/', train=False, download=False, transform=transform_test)
+testloader = torch.utils.data.DataLoader(
+    testset, batch_size=100, shuffle=False, num_workers=2)
+
+classes = ('plane', 'car', 'bird', 'cat', 'deer',
+           'dog', 'frog', 'horse', 'ship', 'truck')
+
+# Model
+print('==> Building model..')
+# net = VGG('VGG19')
+# net = ResNet18()
+# net = PreActResNet18()
+# net = GoogLeNet()
+# net = DenseNet121()
+# net = ResNeXt29_2x64d()
+# net = MobileNet()
+# net = MobileNetV2()
+# net = DPN92()
+# net = ShuffleNetG2()
+# net = SENet18()
+# net = ShuffleNetV2(1)
+# net = EfficientNetB0()
+# net = RegNetX_200MF()
+net = SimpleDLA()
+net = net.to(device)
+if device == 'cuda':
+    net = torch.nn.DataParallel(net)
+    cudnn.benchmark = True
+
+if args.resume:
+    # Load checkpoint.
+    print('==> Resuming from checkpoint..')
+    assert os.path.isdir('checkpoint'), 'Error: no checkpoint directory found!'
+    checkpoint = torch.load('./checkpoint/ckpt.pth')
+    net.load_state_dict(checkpoint['net'])
+    best_acc = checkpoint['acc']
+    start_epoch = checkpoint['epoch']
+
+criterion = nn.CrossEntropyLoss()
+optimizer = optim.SGD(net.parameters(), lr=args.lr,
+                      momentum=0.9, weight_decay=5e-4)
+scheduler = torch.optim.lr_scheduler.CosineAnnealingLR(optimizer, T_max=200)
+
+
+# Training
+def train(epoch):
+    print('\nEpoch: %d' % epoch)
+    net.train()
+    train_loss = 0
+    correct = 0
+    total = 0
+    for batch_idx, (inputs, targets) in enumerate(trainloader):
+        inputs, targets = inputs.to(device), targets.to(device)
+        optimizer.zero_grad()
+        outputs = net(inputs)
+        loss = criterion(outputs, targets)
+        loss.backward()
+        optimizer.step()
+
+        train_loss += loss.item()
+        _, predicted = outputs.max(1)
+        total += targets.size(0)
+        correct += predicted.eq(targets).sum().item()
+
+        progress_bar(batch_idx, len(trainloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
+                     % (train_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+
+def test(epoch):
+    global best_acc
+    net.eval()
+    test_loss = 0
+    correct = 0
+    total = 0
+    with torch.no_grad():
+        for batch_idx, (inputs, targets) in enumerate(testloader):
+            inputs, targets = inputs.to(device), targets.to(device)
+            outputs = net(inputs)
+            loss = criterion(outputs, targets)
+
+            test_loss += loss.item()
+            _, predicted = outputs.max(1)
+            total += targets.size(0)
+            correct += predicted.eq(targets).sum().item()
+
+            progress_bar(batch_idx, len(testloader), 'Loss: %.3f | Acc: %.3f%% (%d/%d)'
+                         % (test_loss/(batch_idx+1), 100.*correct/total, correct, total))
+
+    # Save checkpoint.
+    acc = 100.*correct/total
+    if acc > best_acc:
+        print('Saving..')
+        state = {
+            'net': net.state_dict(),
+            'acc': acc,
+            'epoch': epoch,
+        }
+        if not os.path.isdir('checkpoint'):
+            os.mkdir('checkpoint')
+        torch.save(state, './checkpoint/ckpt.pth')
+        best_acc = acc
+
+
+for epoch in range(start_epoch, start_epoch+200):
+    train(epoch)
+    test(epoch)
+    scheduler.step()

Case_CIFAR10/case1/models/__init__.py

@@ -0,0 +1,18 @@
+from .vgg import *
+from .dpn import *
+from .lenet import *
+from .senet import *
+from .pnasnet import *
+from .densenet import *
+from .googlenet import *
+from .shufflenet import *
+from .shufflenetv2 import *
+from .resnet import *
+from .resnext import *
+from .preact_resnet import *
+from .mobilenet import *
+from .mobilenetv2 import *
+from .efficientnet import *
+from .regnet import *
+from .dla_simple import *
+from .dla import *

Case_CIFAR10/case1/models/densenet.py

@@ -0,0 +1,107 @@
+'''DenseNet in PyTorch.'''
+import math
+
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Bottleneck(nn.Module):
+    def __init__(self, in_planes, growth_rate):
+        super(Bottleneck, self).__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(in_planes, 4*growth_rate, kernel_size=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(4*growth_rate)
+        self.conv2 = nn.Conv2d(4*growth_rate, growth_rate, kernel_size=3, padding=1, bias=False)
+
+    def forward(self, x):
+        out = self.conv1(F.relu(self.bn1(x)))
+        out = self.conv2(F.relu(self.bn2(out)))
+        out = torch.cat([out,x], 1)
+        return out
+
+
+class Transition(nn.Module):
+    def __init__(self, in_planes, out_planes):
+        super(Transition, self).__init__()
+        self.bn = nn.BatchNorm2d(in_planes)
+        self.conv = nn.Conv2d(in_planes, out_planes, kernel_size=1, bias=False)
+
+    def forward(self, x):
+        out = self.conv(F.relu(self.bn(x)))
+        out = F.avg_pool2d(out, 2)
+        return out
+
+
+class DenseNet(nn.Module):
+    def __init__(self, block, nblocks, growth_rate=12, reduction=0.5, num_classes=10):
+        super(DenseNet, self).__init__()
+        self.growth_rate = growth_rate
+
+        num_planes = 2*growth_rate
+        self.conv1 = nn.Conv2d(3, num_planes, kernel_size=3, padding=1, bias=False)
+
+        self.dense1 = self._make_dense_layers(block, num_planes, nblocks[0])
+        num_planes += nblocks[0]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans1 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense2 = self._make_dense_layers(block, num_planes, nblocks[1])
+        num_planes += nblocks[1]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans2 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense3 = self._make_dense_layers(block, num_planes, nblocks[2])
+        num_planes += nblocks[2]*growth_rate
+        out_planes = int(math.floor(num_planes*reduction))
+        self.trans3 = Transition(num_planes, out_planes)
+        num_planes = out_planes
+
+        self.dense4 = self._make_dense_layers(block, num_planes, nblocks[3])
+        num_planes += nblocks[3]*growth_rate
+
+        self.bn = nn.BatchNorm2d(num_planes)
+        self.linear = nn.Linear(num_planes, num_classes)
+
+    def _make_dense_layers(self, block, in_planes, nblock):
+        layers = []
+        for i in range(nblock):
+            layers.append(block(in_planes, self.growth_rate))
+            in_planes += self.growth_rate
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = self.conv1(x)
+        out = self.trans1(self.dense1(out))
+        out = self.trans2(self.dense2(out))
+        out = self.trans3(self.dense3(out))
+        out = self.dense4(out)
+        out = F.avg_pool2d(F.relu(self.bn(out)), 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+def DenseNet121():
+    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=32)
+
+def DenseNet169():
+    return DenseNet(Bottleneck, [6,12,32,32], growth_rate=32)
+
+def DenseNet201():
+    return DenseNet(Bottleneck, [6,12,48,32], growth_rate=32)
+
+def DenseNet161():
+    return DenseNet(Bottleneck, [6,12,36,24], growth_rate=48)
+
+def densenet_cifar():
+    return DenseNet(Bottleneck, [6,12,24,16], growth_rate=12)
+
+def test():
+    net = densenet_cifar()
+    x = torch.randn(1,3,32,32)
+    y = net(x)
+    print(y)
+
+# test()

Case_CIFAR10/case1/models/dla.py

@@ -0,0 +1,135 @@
+'''DLA in PyTorch.
+
+Reference:
+    Deep Layer Aggregation. https://arxiv.org/abs/1707.06484
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, in_planes, planes, stride=1):
+        super(BasicBlock, self).__init__()
+        self.conv1 = nn.Conv2d(
+            in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
+                               stride=1, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+
+        self.shortcut = nn.Sequential()
+        if stride != 1 or in_planes != self.expansion*planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, self.expansion*planes,
+                          kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(self.expansion*planes)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.bn2(self.conv2(out))
+        out += self.shortcut(x)
+        out = F.relu(out)
+        return out
+
+
+class Root(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size=1):
+        super(Root, self).__init__()
+        self.conv = nn.Conv2d(
+            in_channels, out_channels, kernel_size,
+            stride=1, padding=(kernel_size - 1) // 2, bias=False)
+        self.bn = nn.BatchNorm2d(out_channels)
+
+    def forward(self, xs):
+        x = torch.cat(xs, 1)
+        out = F.relu(self.bn(self.conv(x)))
+        return out
+
+
+class Tree(nn.Module):
+    def __init__(self, block, in_channels, out_channels, level=1, stride=1):
+        super(Tree, self).__init__()
+        self.level = level
+        if level == 1:
+            self.root = Root(2*out_channels, out_channels)
+            self.left_node = block(in_channels, out_channels, stride=stride)
+            self.right_node = block(out_channels, out_channels, stride=1)
+        else:
+            self.root = Root((level+2)*out_channels, out_channels)
+            for i in reversed(range(1, level)):
+                subtree = Tree(block, in_channels, out_channels,
+                               level=i, stride=stride)
+                self.__setattr__('level_%d' % i, subtree)
+            self.prev_root = block(in_channels, out_channels, stride=stride)
+            self.left_node = block(out_channels, out_channels, stride=1)
+            self.right_node = block(out_channels, out_channels, stride=1)
+
+    def forward(self, x):
+        xs = [self.prev_root(x)] if self.level > 1 else []
+        for i in reversed(range(1, self.level)):
+            level_i = self.__getattr__('level_%d' % i)
+            x = level_i(x)
+            xs.append(x)
+        x = self.left_node(x)
+        xs.append(x)
+        x = self.right_node(x)
+        xs.append(x)
+        out = self.root(xs)
+        return out
+
+
+class DLA(nn.Module):
+    def __init__(self, block=BasicBlock, num_classes=10):
+        super(DLA, self).__init__()
+        self.base = nn.Sequential(
+            nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(16),
+            nn.ReLU(True)
+        )
+
+        self.layer1 = nn.Sequential(
+            nn.Conv2d(16, 16, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(16),
+            nn.ReLU(True)
+        )
+
+        self.layer2 = nn.Sequential(
+            nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(32),
+            nn.ReLU(True)
+        )
+
+        self.layer3 = Tree(block,  32,  64, level=1, stride=1)
+        self.layer4 = Tree(block,  64, 128, level=2, stride=2)
+        self.layer5 = Tree(block, 128, 256, level=2, stride=2)
+        self.layer6 = Tree(block, 256, 512, level=1, stride=2)
+        self.linear = nn.Linear(512, num_classes)
+
+    def forward(self, x):
+        out = self.base(x)
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = self.layer5(out)
+        out = self.layer6(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def test():
+    net = DLA()
+    print(net)
+    x = torch.randn(1, 3, 32, 32)
+    y = net(x)
+    print(y.size())
+
+
+if __name__ == '__main__':
+    test()

Case_CIFAR10/case1/models/dla_simple.py

@@ -0,0 +1,128 @@
+'''Simplified version of DLA in PyTorch.
+
+Note this implementation is not identical to the original paper version.
+But it seems works fine.
+
+See dla.py for the original paper version.
+
+Reference:
+    Deep Layer Aggregation. https://arxiv.org/abs/1707.06484
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class BasicBlock(nn.Module):
+    expansion = 1
+
+    def __init__(self, in_planes, planes, stride=1):
+        super(BasicBlock, self).__init__()
+        self.conv1 = nn.Conv2d(
+            in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3,
+                               stride=1, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+
+        self.shortcut = nn.Sequential()
+        if stride != 1 or in_planes != self.expansion*planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, self.expansion*planes,
+                          kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(self.expansion*planes)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.bn2(self.conv2(out))
+        out += self.shortcut(x)
+        out = F.relu(out)
+        return out
+
+
+class Root(nn.Module):
+    def __init__(self, in_channels, out_channels, kernel_size=1):
+        super(Root, self).__init__()
+        self.conv = nn.Conv2d(
+            in_channels, out_channels, kernel_size,
+            stride=1, padding=(kernel_size - 1) // 2, bias=False)
+        self.bn = nn.BatchNorm2d(out_channels)
+
+    def forward(self, xs):
+        x = torch.cat(xs, 1)
+        out = F.relu(self.bn(self.conv(x)))
+        return out
+
+
+class Tree(nn.Module):
+    def __init__(self, block, in_channels, out_channels, level=1, stride=1):
+        super(Tree, self).__init__()
+        self.root = Root(2*out_channels, out_channels)
+        if level == 1:
+            self.left_tree = block(in_channels, out_channels, stride=stride)
+            self.right_tree = block(out_channels, out_channels, stride=1)
+        else:
+            self.left_tree = Tree(block, in_channels,
+                                  out_channels, level=level-1, stride=stride)
+            self.right_tree = Tree(block, out_channels,
+                                   out_channels, level=level-1, stride=1)
+
+    def forward(self, x):
+        out1 = self.left_tree(x)
+        out2 = self.right_tree(out1)
+        out = self.root([out1, out2])
+        return out
+
+
+class SimpleDLA(nn.Module):
+    def __init__(self, block=BasicBlock, num_classes=10):
+        super(SimpleDLA, self).__init__()
+        self.base = nn.Sequential(
+            nn.Conv2d(3, 16, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(16),
+            nn.ReLU(True)
+        )
+
+        self.layer1 = nn.Sequential(
+            nn.Conv2d(16, 16, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(16),
+            nn.ReLU(True)
+        )
+
+        self.layer2 = nn.Sequential(
+            nn.Conv2d(16, 32, kernel_size=3, stride=1, padding=1, bias=False),
+            nn.BatchNorm2d(32),
+            nn.ReLU(True)
+        )
+
+        self.layer3 = Tree(block,  32,  64, level=1, stride=1)
+        self.layer4 = Tree(block,  64, 128, level=2, stride=2)
+        self.layer5 = Tree(block, 128, 256, level=2, stride=2)
+        self.layer6 = Tree(block, 256, 512, level=1, stride=2)
+        self.linear = nn.Linear(512, num_classes)
+
+    def forward(self, x):
+        out = self.base(x)
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = self.layer5(out)
+        out = self.layer6(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def test():
+    net = SimpleDLA()
+    print(net)
+    x = torch.randn(1, 3, 32, 32)
+    y = net(x)
+    print(y.size())
+
+
+if __name__ == '__main__':
+    test()

Case_CIFAR10/case1/models/dpn.py

@@ -0,0 +1,98 @@
+'''Dual Path Networks in PyTorch.'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Bottleneck(nn.Module):
+    def __init__(self, last_planes, in_planes, out_planes, dense_depth, stride, first_layer):
+        super(Bottleneck, self).__init__()
+        self.out_planes = out_planes
+        self.dense_depth = dense_depth
+
+        self.conv1 = nn.Conv2d(last_planes, in_planes, kernel_size=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv2 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=32, bias=False)
+        self.bn2 = nn.BatchNorm2d(in_planes)
+        self.conv3 = nn.Conv2d(in_planes, out_planes+dense_depth, kernel_size=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(out_planes+dense_depth)
+
+        self.shortcut = nn.Sequential()
+        if first_layer:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(last_planes, out_planes+dense_depth, kernel_size=1, stride=stride, bias=False),
+                nn.BatchNorm2d(out_planes+dense_depth)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = F.relu(self.bn2(self.conv2(out)))
+        out = self.bn3(self.conv3(out))
+        x = self.shortcut(x)
+        d = self.out_planes
+        out = torch.cat([x[:,:d,:,:]+out[:,:d,:,:], x[:,d:,:,:], out[:,d:,:,:]], 1)
+        out = F.relu(out)
+        return out
+
+
+class DPN(nn.Module):
+    def __init__(self, cfg):
+        super(DPN, self).__init__()
+        in_planes, out_planes = cfg['in_planes'], cfg['out_planes']
+        num_blocks, dense_depth = cfg['num_blocks'], cfg['dense_depth']
+
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(64)
+        self.last_planes = 64
+        self.layer1 = self._make_layer(in_planes[0], out_planes[0], num_blocks[0], dense_depth[0], stride=1)
+        self.layer2 = self._make_layer(in_planes[1], out_planes[1], num_blocks[1], dense_depth[1], stride=2)
+        self.layer3 = self._make_layer(in_planes[2], out_planes[2], num_blocks[2], dense_depth[2], stride=2)
+        self.layer4 = self._make_layer(in_planes[3], out_planes[3], num_blocks[3], dense_depth[3], stride=2)
+        self.linear = nn.Linear(out_planes[3]+(num_blocks[3]+1)*dense_depth[3], 10)
+
+    def _make_layer(self, in_planes, out_planes, num_blocks, dense_depth, stride):
+        strides = [stride] + [1]*(num_blocks-1)
+        layers = []
+        for i,stride in enumerate(strides):
+            layers.append(Bottleneck(self.last_planes, in_planes, out_planes, dense_depth, stride, i==0))
+            self.last_planes = out_planes + (i+2) * dense_depth
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def DPN26():
+    cfg = {
+        'in_planes': (96,192,384,768),
+        'out_planes': (256,512,1024,2048),
+        'num_blocks': (2,2,2,2),
+        'dense_depth': (16,32,24,128)
+    }
+    return DPN(cfg)
+
+def DPN92():
+    cfg = {
+        'in_planes': (96,192,384,768),
+        'out_planes': (256,512,1024,2048),
+        'num_blocks': (3,4,20,3),
+        'dense_depth': (16,32,24,128)
+    }
+    return DPN(cfg)
+
+
+def test():
+    net = DPN92()
+    x = torch.randn(1,3,32,32)
+    y = net(x)
+    print(y)
+
+# test()

Case_CIFAR10/case1/models/efficientnet.py

@@ -0,0 +1,175 @@
+'''EfficientNet in PyTorch.
+
+Paper: "EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks".
+
+Reference: https://github.com/keras-team/keras-applications/blob/master/keras_applications/efficientnet.py
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+def swish(x):
+    return x * x.sigmoid()
+
+
+def drop_connect(x, drop_ratio):
+    keep_ratio = 1.0 - drop_ratio
+    mask = torch.empty([x.shape[0], 1, 1, 1], dtype=x.dtype, device=x.device)
+    mask.bernoulli_(keep_ratio)
+    x.div_(keep_ratio)
+    x.mul_(mask)
+    return x
+
+
+class SE(nn.Module):
+    '''Squeeze-and-Excitation block with Swish.'''
+
+    def __init__(self, in_channels, se_channels):
+        super(SE, self).__init__()
+        self.se1 = nn.Conv2d(in_channels, se_channels,
+                             kernel_size=1, bias=True)
+        self.se2 = nn.Conv2d(se_channels, in_channels,
+                             kernel_size=1, bias=True)
+
+    def forward(self, x):
+        out = F.adaptive_avg_pool2d(x, (1, 1))
+        out = swish(self.se1(out))
+        out = self.se2(out).sigmoid()
+        out = x * out
+        return out
+
+
+class Block(nn.Module):
+    '''expansion + depthwise + pointwise + squeeze-excitation'''
+
+    def __init__(self,
+                 in_channels,
+                 out_channels,
+                 kernel_size,
+                 stride,
+                 expand_ratio=1,
+                 se_ratio=0.,
+                 drop_rate=0.):
+        super(Block, self).__init__()
+        self.stride = stride
+        self.drop_rate = drop_rate
+        self.expand_ratio = expand_ratio
+
+        # Expansion
+        channels = expand_ratio * in_channels
+        self.conv1 = nn.Conv2d(in_channels,
+                               channels,
+                               kernel_size=1,
+                               stride=1,
+                               padding=0,
+                               bias=False)
+        self.bn1 = nn.BatchNorm2d(channels)
+
+        # Depthwise conv
+        self.conv2 = nn.Conv2d(channels,
+                               channels,
+                               kernel_size=kernel_size,
+                               stride=stride,
+                               padding=(1 if kernel_size == 3 else 2),
+                               groups=channels,
+                               bias=False)
+        self.bn2 = nn.BatchNorm2d(channels)
+
+        # SE layers
+        se_channels = int(in_channels * se_ratio)
+        self.se = SE(channels, se_channels)
+
+        # Output
+        self.conv3 = nn.Conv2d(channels,
+                               out_channels,
+                               kernel_size=1,
+                               stride=1,
+                               padding=0,
+                               bias=False)
+        self.bn3 = nn.BatchNorm2d(out_channels)
+
+        # Skip connection if in and out shapes are the same (MV-V2 style)
+        self.has_skip = (stride == 1) and (in_channels == out_channels)
+
+    def forward(self, x):
+        out = x if self.expand_ratio == 1 else swish(self.bn1(self.conv1(x)))
+        out = swish(self.bn2(self.conv2(out)))
+        out = self.se(out)
+        out = self.bn3(self.conv3(out))
+        if self.has_skip:
+            if self.training and self.drop_rate > 0:
+                out = drop_connect(out, self.drop_rate)
+            out = out + x
+        return out
+
+
+class EfficientNet(nn.Module):
+    def __init__(self, cfg, num_classes=10):
+        super(EfficientNet, self).__init__()
+        self.cfg = cfg
+        self.conv1 = nn.Conv2d(3,
+                               32,
+                               kernel_size=3,
+                               stride=1,
+                               padding=1,
+                               bias=False)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.layers = self._make_layers(in_channels=32)
+        self.linear = nn.Linear(cfg['out_channels'][-1], num_classes)
+
+    def _make_layers(self, in_channels):
+        layers = []
+        cfg = [self.cfg[k] for k in ['expansion', 'out_channels', 'num_blocks', 'kernel_size',
+                                     'stride']]
+        b = 0
+        blocks = sum(self.cfg['num_blocks'])
+        for expansion, out_channels, num_blocks, kernel_size, stride in zip(*cfg):
+            strides = [stride] + [1] * (num_blocks - 1)
+            for stride in strides:
+                drop_rate = self.cfg['drop_connect_rate'] * b / blocks
+                layers.append(
+                    Block(in_channels,
+                          out_channels,
+                          kernel_size,
+                          stride,
+                          expansion,
+                          se_ratio=0.25,
+                          drop_rate=drop_rate))
+                in_channels = out_channels
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = swish(self.bn1(self.conv1(x)))
+        out = self.layers(out)
+        out = F.adaptive_avg_pool2d(out, 1)
+        out = out.view(out.size(0), -1)
+        dropout_rate = self.cfg['dropout_rate']
+        if self.training and dropout_rate > 0:
+            out = F.dropout(out, p=dropout_rate)
+        out = self.linear(out)
+        return out
+
+
+def EfficientNetB0():
+    cfg = {
+        'num_blocks': [1, 2, 2, 3, 3, 4, 1],
+        'expansion': [1, 6, 6, 6, 6, 6, 6],
+        'out_channels': [16, 24, 40, 80, 112, 192, 320],
+        'kernel_size': [3, 3, 5, 3, 5, 5, 3],
+        'stride': [1, 2, 2, 2, 1, 2, 1],
+        'dropout_rate': 0.2,
+        'drop_connect_rate': 0.2,
+    }
+    return EfficientNet(cfg)
+
+
+def test():
+    net = EfficientNetB0()
+    x = torch.randn(2, 3, 32, 32)
+    y = net(x)
+    print(y.shape)
+
+
+if __name__ == '__main__':
+    test()

Case_CIFAR10/case1/models/googlenet.py

@@ -0,0 +1,107 @@
+'''GoogLeNet with PyTorch.'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Inception(nn.Module):
+    def __init__(self, in_planes, n1x1, n3x3red, n3x3, n5x5red, n5x5, pool_planes):
+        super(Inception, self).__init__()
+        # 1x1 conv branch
+        self.b1 = nn.Sequential(
+            nn.Conv2d(in_planes, n1x1, kernel_size=1),
+            nn.BatchNorm2d(n1x1),
+            nn.ReLU(True),
+        )
+
+        # 1x1 conv -> 3x3 conv branch
+        self.b2 = nn.Sequential(
+            nn.Conv2d(in_planes, n3x3red, kernel_size=1),
+            nn.BatchNorm2d(n3x3red),
+            nn.ReLU(True),
+            nn.Conv2d(n3x3red, n3x3, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n3x3),
+            nn.ReLU(True),
+        )
+
+        # 1x1 conv -> 5x5 conv branch
+        self.b3 = nn.Sequential(
+            nn.Conv2d(in_planes, n5x5red, kernel_size=1),
+            nn.BatchNorm2d(n5x5red),
+            nn.ReLU(True),
+            nn.Conv2d(n5x5red, n5x5, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n5x5),
+            nn.ReLU(True),
+            nn.Conv2d(n5x5, n5x5, kernel_size=3, padding=1),
+            nn.BatchNorm2d(n5x5),
+            nn.ReLU(True),
+        )
+
+        # 3x3 pool -> 1x1 conv branch
+        self.b4 = nn.Sequential(
+            nn.MaxPool2d(3, stride=1, padding=1),
+            nn.Conv2d(in_planes, pool_planes, kernel_size=1),
+            nn.BatchNorm2d(pool_planes),
+            nn.ReLU(True),
+        )
+
+    def forward(self, x):
+        y1 = self.b1(x)
+        y2 = self.b2(x)
+        y3 = self.b3(x)
+        y4 = self.b4(x)
+        return torch.cat([y1,y2,y3,y4], 1)
+
+
+class GoogLeNet(nn.Module):
+    def __init__(self):
+        super(GoogLeNet, self).__init__()
+        self.pre_layers = nn.Sequential(
+            nn.Conv2d(3, 192, kernel_size=3, padding=1),
+            nn.BatchNorm2d(192),
+            nn.ReLU(True),
+        )
+
+        self.a3 = Inception(192,  64,  96, 128, 16, 32, 32)
+        self.b3 = Inception(256, 128, 128, 192, 32, 96, 64)
+
+        self.maxpool = nn.MaxPool2d(3, stride=2, padding=1)
+
+        self.a4 = Inception(480, 192,  96, 208, 16,  48,  64)
+        self.b4 = Inception(512, 160, 112, 224, 24,  64,  64)
+        self.c4 = Inception(512, 128, 128, 256, 24,  64,  64)
+        self.d4 = Inception(512, 112, 144, 288, 32,  64,  64)
+        self.e4 = Inception(528, 256, 160, 320, 32, 128, 128)
+
+        self.a5 = Inception(832, 256, 160, 320, 32, 128, 128)
+        self.b5 = Inception(832, 384, 192, 384, 48, 128, 128)
+
+        self.avgpool = nn.AvgPool2d(8, stride=1)
+        self.linear = nn.Linear(1024, 10)
+
+    def forward(self, x):
+        out = self.pre_layers(x)
+        out = self.a3(out)
+        out = self.b3(out)
+        out = self.maxpool(out)
+        out = self.a4(out)
+        out = self.b4(out)
+        out = self.c4(out)
+        out = self.d4(out)
+        out = self.e4(out)
+        out = self.maxpool(out)
+        out = self.a5(out)
+        out = self.b5(out)
+        out = self.avgpool(out)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def test():
+    net = GoogLeNet()
+    x = torch.randn(1,3,32,32)
+    y = net(x)
+    print(y.size())
+
+# test()

Case_CIFAR10/case1/models/lenet.py

@@ -0,0 +1,23 @@
+'''LeNet in PyTorch.'''
+import torch.nn as nn
+import torch.nn.functional as F
+
+class LeNet(nn.Module):
+    def __init__(self):
+        super(LeNet, self).__init__()
+        self.conv1 = nn.Conv2d(3, 6, 5)
+        self.conv2 = nn.Conv2d(6, 16, 5)
+        self.fc1   = nn.Linear(16*5*5, 120)
+        self.fc2   = nn.Linear(120, 84)
+        self.fc3   = nn.Linear(84, 10)
+
+    def forward(self, x):
+        out = F.relu(self.conv1(x))
+        out = F.max_pool2d(out, 2)
+        out = F.relu(self.conv2(out))
+        out = F.max_pool2d(out, 2)
+        out = out.view(out.size(0), -1)
+        out = F.relu(self.fc1(out))
+        out = F.relu(self.fc2(out))
+        out = self.fc3(out)
+        return out

Case_CIFAR10/case1/models/mobilenet.py

@@ -0,0 +1,61 @@
+'''MobileNet in PyTorch.
+
+See the paper "MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications"
+for more details.
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Block(nn.Module):
+    '''Depthwise conv + Pointwise conv'''
+    def __init__(self, in_planes, out_planes, stride=1):
+        super(Block, self).__init__()
+        self.conv1 = nn.Conv2d(in_planes, in_planes, kernel_size=3, stride=stride, padding=1, groups=in_planes, bias=False)
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv2 = nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
+        self.bn2 = nn.BatchNorm2d(out_planes)
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = F.relu(self.bn2(self.conv2(out)))
+        return out
+
+
+class MobileNet(nn.Module):
+    # (128,2) means conv planes=128, conv stride=2, by default conv stride=1
+    cfg = [64, (128,2), 128, (256,2), 256, (512,2), 512, 512, 512, 512, 512, (1024,2), 1024]
+
+    def __init__(self, num_classes=10):
+        super(MobileNet, self).__init__()
+        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.layers = self._make_layers(in_planes=32)
+        self.linear = nn.Linear(1024, num_classes)
+
+    def _make_layers(self, in_planes):
+        layers = []
+        for x in self.cfg:
+            out_planes = x if isinstance(x, int) else x[0]
+            stride = 1 if isinstance(x, int) else x[1]
+            layers.append(Block(in_planes, out_planes, stride))
+            in_planes = out_planes
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.layers(out)
+        out = F.avg_pool2d(out, 2)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def test():
+    net = MobileNet()
+    x = torch.randn(1,3,32,32)
+    y = net(x)
+    print(y.size())
+
+# test()

Case_CIFAR10/case1/models/mobilenetv2.py

@@ -0,0 +1,86 @@
+'''MobileNetV2 in PyTorch.
+
+See the paper "Inverted Residuals and Linear Bottlenecks:
+Mobile Networks for Classification, Detection and Segmentation" for more details.
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class Block(nn.Module):
+    '''expand + depthwise + pointwise'''
+    def __init__(self, in_planes, out_planes, expansion, stride):
+        super(Block, self).__init__()
+        self.stride = stride
+
+        planes = expansion * in_planes
+        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, stride=1, padding=0, bias=False)
+        self.bn1 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, groups=planes, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv3 = nn.Conv2d(planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
+        self.bn3 = nn.BatchNorm2d(out_planes)
+
+        self.shortcut = nn.Sequential()
+        if stride == 1 and in_planes != out_planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False),
+                nn.BatchNorm2d(out_planes),
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = F.relu(self.bn2(self.conv2(out)))
+        out = self.bn3(self.conv3(out))
+        out = out + self.shortcut(x) if self.stride==1 else out
+        return out
+
+
+class MobileNetV2(nn.Module):
+    # (expansion, out_planes, num_blocks, stride)
+    cfg = [(1,  16, 1, 1),
+           (6,  24, 2, 1),  # NOTE: change stride 2 -> 1 for CIFAR10
+           (6,  32, 3, 2),
+           (6,  64, 4, 2),
+           (6,  96, 3, 1),
+           (6, 160, 3, 2),
+           (6, 320, 1, 1)]
+
+    def __init__(self, num_classes=10):
+        super(MobileNetV2, self).__init__()
+        # NOTE: change conv1 stride 2 -> 1 for CIFAR10
+        self.conv1 = nn.Conv2d(3, 32, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(32)
+        self.layers = self._make_layers(in_planes=32)
+        self.conv2 = nn.Conv2d(320, 1280, kernel_size=1, stride=1, padding=0, bias=False)
+        self.bn2 = nn.BatchNorm2d(1280)
+        self.linear = nn.Linear(1280, num_classes)
+
+    def _make_layers(self, in_planes):
+        layers = []
+        for expansion, out_planes, num_blocks, stride in self.cfg:
+            strides = [stride] + [1]*(num_blocks-1)
+            for stride in strides:
+                layers.append(Block(in_planes, out_planes, expansion, stride))
+                in_planes = out_planes
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.layers(out)
+        out = F.relu(self.bn2(self.conv2(out)))
+        # NOTE: change pooling kernel_size 7 -> 4 for CIFAR10
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def test():
+    net = MobileNetV2()
+    x = torch.randn(2,3,32,32)
+    y = net(x)
+    print(y.size())
+
+# test()

Case_CIFAR10/case1/models/pnasnet.py

@@ -0,0 +1,125 @@
+'''PNASNet in PyTorch.
+
+Paper: Progressive Neural Architecture Search
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class SepConv(nn.Module):
+    '''Separable Convolution.'''
+    def __init__(self, in_planes, out_planes, kernel_size, stride):
+        super(SepConv, self).__init__()
+        self.conv1 = nn.Conv2d(in_planes, out_planes,
+                               kernel_size, stride,
+                               padding=(kernel_size-1)//2,
+                               bias=False, groups=in_planes)
+        self.bn1 = nn.BatchNorm2d(out_planes)
+
+    def forward(self, x):
+        return self.bn1(self.conv1(x))
+
+
+class CellA(nn.Module):
+    def __init__(self, in_planes, out_planes, stride=1):
+        super(CellA, self).__init__()
+        self.stride = stride
+        self.sep_conv1 = SepConv(in_planes, out_planes, kernel_size=7, stride=stride)
+        if stride==2:
+            self.conv1 = nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
+            self.bn1 = nn.BatchNorm2d(out_planes)
+
+    def forward(self, x):
+        y1 = self.sep_conv1(x)
+        y2 = F.max_pool2d(x, kernel_size=3, stride=self.stride, padding=1)
+        if self.stride==2:
+            y2 = self.bn1(self.conv1(y2))
+        return F.relu(y1+y2)
+
+class CellB(nn.Module):
+    def __init__(self, in_planes, out_planes, stride=1):
+        super(CellB, self).__init__()
+        self.stride = stride
+        # Left branch
+        self.sep_conv1 = SepConv(in_planes, out_planes, kernel_size=7, stride=stride)
+        self.sep_conv2 = SepConv(in_planes, out_planes, kernel_size=3, stride=stride)
+        # Right branch
+        self.sep_conv3 = SepConv(in_planes, out_planes, kernel_size=5, stride=stride)
+        if stride==2:
+            self.conv1 = nn.Conv2d(in_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
+            self.bn1 = nn.BatchNorm2d(out_planes)
+        # Reduce channels
+        self.conv2 = nn.Conv2d(2*out_planes, out_planes, kernel_size=1, stride=1, padding=0, bias=False)
+        self.bn2 = nn.BatchNorm2d(out_planes)
+
+    def forward(self, x):
+        # Left branch
+        y1 = self.sep_conv1(x)
+        y2 = self.sep_conv2(x)
+        # Right branch
+        y3 = F.max_pool2d(x, kernel_size=3, stride=self.stride, padding=1)
+        if self.stride==2:
+            y3 = self.bn1(self.conv1(y3))
+        y4 = self.sep_conv3(x)
+        # Concat & reduce channels
+        b1 = F.relu(y1+y2)
+        b2 = F.relu(y3+y4)
+        y = torch.cat([b1,b2], 1)
+        return F.relu(self.bn2(self.conv2(y)))
+
+class PNASNet(nn.Module):
+    def __init__(self, cell_type, num_cells, num_planes):
+        super(PNASNet, self).__init__()
+        self.in_planes = num_planes
+        self.cell_type = cell_type
+
+        self.conv1 = nn.Conv2d(3, num_planes, kernel_size=3, stride=1, padding=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(num_planes)
+
+        self.layer1 = self._make_layer(num_planes, num_cells=6)
+        self.layer2 = self._downsample(num_planes*2)
+        self.layer3 = self._make_layer(num_planes*2, num_cells=6)
+        self.layer4 = self._downsample(num_planes*4)
+        self.layer5 = self._make_layer(num_planes*4, num_cells=6)
+
+        self.linear = nn.Linear(num_planes*4, 10)
+
+    def _make_layer(self, planes, num_cells):
+        layers = []
+        for _ in range(num_cells):
+            layers.append(self.cell_type(self.in_planes, planes, stride=1))
+            self.in_planes = planes
+        return nn.Sequential(*layers)
+
+    def _downsample(self, planes):
+        layer = self.cell_type(self.in_planes, planes, stride=2)
+        self.in_planes = planes
+        return layer
+
+    def forward(self, x):
+        out = F.relu(self.bn1(self.conv1(x)))
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = self.layer5(out)
+        out = F.avg_pool2d(out, 8)
+        out = self.linear(out.view(out.size(0), -1))
+        return out
+
+
+def PNASNetA():
+    return PNASNet(CellA, num_cells=6, num_planes=44)
+
+def PNASNetB():
+    return PNASNet(CellB, num_cells=6, num_planes=32)
+
+
+def test():
+    net = PNASNetB()
+    x = torch.randn(1,3,32,32)
+    y = net(x)
+    print(y)
+
+# test()

Case_CIFAR10/case1/models/preact_resnet.py

@@ -0,0 +1,118 @@
+'''Pre-activation ResNet in PyTorch.
+
+Reference:
+[1] Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
+    Identity Mappings in Deep Residual Networks. arXiv:1603.05027
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class PreActBlock(nn.Module):
+    '''Pre-activation version of the BasicBlock.'''
+    expansion = 1
+
+    def __init__(self, in_planes, planes, stride=1):
+        super(PreActBlock, self).__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=1, padding=1, bias=False)
+
+        if stride != 1 or in_planes != self.expansion*planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(x))
+        shortcut = self.shortcut(out) if hasattr(self, 'shortcut') else x
+        out = self.conv1(out)
+        out = self.conv2(F.relu(self.bn2(out)))
+        out += shortcut
+        return out
+
+
+class PreActBottleneck(nn.Module):
+    '''Pre-activation version of the original Bottleneck module.'''
+    expansion = 4
+
+    def __init__(self, in_planes, planes, stride=1):
+        super(PreActBottleneck, self).__init__()
+        self.bn1 = nn.BatchNorm2d(in_planes)
+        self.conv1 = nn.Conv2d(in_planes, planes, kernel_size=1, bias=False)
+        self.bn2 = nn.BatchNorm2d(planes)
+        self.conv2 = nn.Conv2d(planes, planes, kernel_size=3, stride=stride, padding=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(planes)
+        self.conv3 = nn.Conv2d(planes, self.expansion*planes, kernel_size=1, bias=False)
+
+        if stride != 1 or in_planes != self.expansion*planes:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(in_planes, self.expansion*planes, kernel_size=1, stride=stride, bias=False)
+            )
+
+    def forward(self, x):
+        out = F.relu(self.bn1(x))
+        shortcut = self.shortcut(out) if hasattr(self, 'shortcut') else x
+        out = self.conv1(out)
+        out = self.conv2(F.relu(self.bn2(out)))
+        out = self.conv3(F.relu(self.bn3(out)))
+        out += shortcut
+        return out
+
+
+class PreActResNet(nn.Module):
+    def __init__(self, block, num_blocks, num_classes=10):
+        super(PreActResNet, self).__init__()
+        self.in_planes = 64
+
+        self.conv1 = nn.Conv2d(3, 64, kernel_size=3, stride=1, padding=1, bias=False)
+        self.layer1 = self._make_layer(block, 64, num_blocks[0], stride=1)
+        self.layer2 = self._make_layer(block, 128, num_blocks[1], stride=2)
+        self.layer3 = self._make_layer(block, 256, num_blocks[2], stride=2)
+        self.layer4 = self._make_layer(block, 512, num_blocks[3], stride=2)
+        self.linear = nn.Linear(512*block.expansion, num_classes)
+
+    def _make_layer(self, block, planes, num_blocks, stride):
+        strides = [stride] + [1]*(num_blocks-1)
+        layers = []
+        for stride in strides:
+            layers.append(block(self.in_planes, planes, stride))
+            self.in_planes = planes * block.expansion
+        return nn.Sequential(*layers)
+
+    def forward(self, x):
+        out = self.conv1(x)
+        out = self.layer1(out)
+        out = self.layer2(out)
+        out = self.layer3(out)
+        out = self.layer4(out)
+        out = F.avg_pool2d(out, 4)
+        out = out.view(out.size(0), -1)
+        out = self.linear(out)
+        return out
+
+
+def PreActResNet18():
+    return PreActResNet(PreActBlock, [2,2,2,2])
+
+def PreActResNet34():
+    return PreActResNet(PreActBlock, [3,4,6,3])
+
+def PreActResNet50():
+    return PreActResNet(PreActBottleneck, [3,4,6,3])
+
+def PreActResNet101():
+    return PreActResNet(PreActBottleneck, [3,4,23,3])
+
+def PreActResNet152():
+    return PreActResNet(PreActBottleneck, [3,8,36,3])
+
+
+def test():
+    net = PreActResNet18()
+    y = net((torch.randn(1,3,32,32)))
+    print(y.size())
+
+# test()

Case_CIFAR10/case1/models/regnet.py

@@ -0,0 +1,155 @@
+'''RegNet in PyTorch.
+
+Paper: "Designing Network Design Spaces".
+
+Reference: https://github.com/keras-team/keras-applications/blob/master/keras_applications/efficientnet.py
+'''
+import torch
+import torch.nn as nn
+import torch.nn.functional as F
+
+
+class SE(nn.Module):
+    '''Squeeze-and-Excitation block.'''
+
+    def __init__(self, in_planes, se_planes):
+        super(SE, self).__init__()
+        self.se1 = nn.Conv2d(in_planes, se_planes, kernel_size=1, bias=True)
+        self.se2 = nn.Conv2d(se_planes, in_planes, kernel_size=1, bias=True)
+
+    def forward(self, x):
+        out = F.adaptive_avg_pool2d(x, (1, 1))
+        out = F.relu(self.se1(out))
+        out = self.se2(out).sigmoid()
+        out = x * out
+        return out
+
+
+class Block(nn.Module):
+    def __init__(self, w_in, w_out, stride, group_width, bottleneck_ratio, se_ratio):
+        super(Block, self).__init__()
+        # 1x1
+        w_b = int(round(w_out * bottleneck_ratio))
+        self.conv1 = nn.Conv2d(w_in, w_b, kernel_size=1, bias=False)
+        self.bn1 = nn.BatchNorm2d(w_b)
+        # 3x3
+        num_groups = w_b // group_width
+        self.conv2 = nn.Conv2d(w_b, w_b, kernel_size=3,
+                               stride=stride, padding=1, groups=num_groups, bias=False)
+        self.bn2 = nn.BatchNorm2d(w_b)
+        # se
+        self.with_se = se_ratio > 0
+        if self.with_se:
+            w_se = int(round(w_in * se_ratio))
+            self.se = SE(w_b, w_se)
+        # 1x1
+        self.conv3 = nn.Conv2d(w_b, w_out, kernel_size=1, bias=False)
+        self.bn3 = nn.BatchNorm2d(w_out)
+
+        self.shortcut = nn.Sequential()
+        if stride != 1 or w_in != w_out:
+            self.shortcut = nn.Sequential(
+                nn.Conv2d(w_in, w_out,
+                          kernel_size=1, stride=stride, bias=False),