第J3-1周：DenseNet算法實現乳腺癌識別

文章目錄

一、前言
二、前期準備
- 1.設置GPU
- 2.劃分數據集
三、搭建網絡模型
- 1.DenseLayer模塊
- 2.DenseBlock模塊
- 3.Transition模塊
- 4.構建DenseNet
- 5.構建densenet121
四、訓練模型
- 1.編寫訓練函數
- 2.編寫測試函數
- 3.正式訓練
五、結果可視化
- 1.Loss與Accuracy圖
- 2.模型評估
總結：

🍨 本文為🔗365天深度學習訓練營中的學習記錄博客
🍖 原作者：K同學啊

一、前言

二、前期準備

1.設置GPU

import torch
import torch.nn as nn
import torchvision.transforms as transforms
import torchvision
from torchvision import transforms, datasets
import os, PIL, pathlib, warningswarnings.filterwarnings("ignore")  ## 忽略警告信息device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
device

device(type=‘cpu’)

import os, PIL, random, pathlibdata_dir = './J3-data/'
data_dir = pathlib.Path(data_dir)data_paths = list(data_dir.glob('*'))
classeNames = [str(path).split("/")[1] for path in data_paths]
classeNames

[‘.DS_Store’, ‘0’, ‘1’]

train_transforms = transforms.Compose([transforms.Resize([224, 224]),  # 將輸入圖片resize成統一尺寸# transforms.RandomHorizontalFlip(), # 隨機水平翻轉transforms.ToTensor(),          # 將PIL Image或numpy.ndarray轉換為tensor，并歸一化到[0,1]之間transforms.Normalize(           # 標準化處理-->轉換為標準正太分布（高斯分布），使模型更容易收斂mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]與std=[0.229,0.224,0.225] 從數據集中隨機抽樣計算得到的。
])test_transform = transforms.Compose([transforms.Resize([224, 224]),  # 將輸入圖片resize成統一尺寸transforms.ToTensor(),          # 將PIL Image或numpy.ndarray轉換為tensor，并歸一化到[0,1]之間transforms.Normalize(           # 標準化處理-->轉換為標準正太分布（高斯分布），使模型更容易收斂mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])  # 其中 mean=[0.485,0.456,0.406]與std=[0.229,0.224,0.225] 從數據集中隨機抽樣計算得到的。
])total_data = datasets.ImageFolder(data_dir,transform=train_transforms)
total_data

Dataset ImageFolder
Number of datapoints: 13403
Root location: J3-data
StandardTransform
Transform: Compose(
Resize(size=[224, 224], interpolation=bilinear, max_size=None, antialias=True)
ToTensor()
Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
)

total_data.class_to_idx

{‘0’: 0, ‘1’: 1}

2.劃分數據集

train_size = int(0.8 * len(total_data))
test_size = len(total_data) - train_size
train_dataset, test_dataset = torch.utils.data.random_split(total_data, [train_size, test_size])
train_dataset, test_dataset

(<torch.utils.data.dataset.Subset at 0x17fc70760>,
<torch.utils.data.dataset.Subset at 0x17fc70430>)

batch_size = 32
train_dl = torch.utils.data.DataLoader(train_dataset,batch_size=batch_size,shuffle=True)test_dl = torch.utils.data.DataLoader(test_dataset,batch_size=batch_size,shuffle=True)

for X, y in test_dl:print("Shape of X [N, C, H, W]:", X.shape)print("Shape of y:", y.shape, y.dtype)break

Shape of X [N, C, H, W]: torch.Size([32, 3, 224, 224])
Shape of y: torch.Size([32]) torch.int64

三、搭建網絡模型

from collections import OrderedDict
import torch
import torch.nn as nn
import torch.nn.functional as F

1.DenseLayer模塊

class DenseLayer(nn.Sequential):def __init__(self, in_channel, growth_rate, bn_size, drop_rate):super(DenseLayer, self).__init__()self.add_module('norm1', nn.BatchNorm2d(in_channel))self.add_module('relu1', nn.ReLU(inplace=True))self.add_module('conv1', nn.Conv2d(in_channel, 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_ratedef forward(self, x):new_feature = super(DenseLayer, self).forward(x)if self.drop_rate>0:new_feature = F.dropout(new_feature, p=self.drop_rate, training=self.training)return torch.cat([x, new_feature], 1)

2.DenseBlock模塊

''' DenseBlock '''
class DenseBlock(nn.Sequential):def __init__(self, num_layers, in_channel, bn_size, growth_rate, drop_rate):super(DenseBlock, self).__init__()for i in range(num_layers):layer = DenseLayer(in_channel+i*growth_rate, growth_rate, bn_size, drop_rate)self.add_module('denselayer%d'%(i+1,), layer)

3.Transition模塊

''' Transition layer between two adjacent DenseBlock '''
class Transition(nn.Sequential):def __init__(self, in_channel, out_channel):super(Transition, self).__init__()self.add_module('norm', nn.BatchNorm2d(in_channel))self.add_module('relu', nn.ReLU(inplace=True))self.add_module('conv', nn.Conv2d(in_channel, out_channel,kernel_size=1, stride=1, bias=False))self.add_module('pool', nn.AvgPool2d(2, stride=2))

4.構建DenseNet

class DenseNet(nn.Module):def __init__(self, growth_rate=32, block_config=(6,12,24,16), init_channel=64, bn_size=4, compression_rate=0.5, drop_rate=0, num_classes=1000):''':param growth_rate: (int) number of filters used in DenseLayer, `k` in the paper:param block_config: (list of 4 ints) number of layers in eatch DenseBlock:param init_channel: (int) number of filters in the first Conv2d:param bn_size: (int) the factor using in the bottleneck layer:param compression_rate: (float) the compression rate used in Transition Layer:param drop_rate: (float) the drop rate after each DenseLayer:param num_classes: (int) 待分類的類別數'''super(DenseNet, self).__init__()# first Conv2dself.features = nn.Sequential(OrderedDict([('conv0', nn.Conv2d(3, init_channel, kernel_size=7, stride=2, padding=3, bias=False)),('norm0', nn.BatchNorm2d(init_channel)),('relu0', nn.ReLU(inplace=True)),('pool0', nn.MaxPool2d(3, stride=2, padding=1))]))# DenseBlocknum_features = init_channelfor i, num_layers in enumerate(block_config):block = DenseBlock(num_layers, num_features, bn_size, growth_rate, drop_rate)self.features.add_module('denseblock%d'%(i+1), block)num_features += num_layers*growth_rateif i != len(block_config)-1:transition = Transition(num_features, int(num_features*compression_rate))self.features.add_module('transition%d'%(i+1), transition)num_features = int(num_features*compression_rate)# final BN+ReLUself.features.add_module('norm5', nn.BatchNorm2d(num_features))self.features.add_module('relu5', nn.ReLU(inplace=True))# 分類層self.classifier = nn.Linear(num_features, num_classes)# 參數初始化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.bias, 0)nn.init.constant_(m.weight, 1)elif isinstance(m, nn.Linear):nn.init.constant_(m.bias, 0)def forward(self, x):x = self.features(x)x = F.avg_pool2d(x, 7, stride=1).view(x.size(0), -1)x = self.classifier(x)return x

5.構建densenet121

device = "cuda" if torch.cuda.is_available() else "cpu"
print("Using {} device".format(device))densenet121 = DenseNet(init_channel=64,growth_rate=32,block_config=(6,12,24,16),num_classes=len(classeNames))  model = densenet121.to(device)
model

Using cpu device

DenseNet(
(features): Sequential(
(conv0): Conv2d(3, 64, kernel_size=(7, 7), stride=(2, 2), padding=(3, 3), bias=False)
(norm0): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu0): ReLU(inplace=True)
(pool0): MaxPool2d(kernel_size=3, stride=2, padding=1, dilation=1, ceil_mode=False)
(denseblock1): DenseBlock(
(denselayer1): DenseLayer(
(norm1): BatchNorm2d(64, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(64, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer2): DenseLayer(
(norm1): BatchNorm2d(96, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(96, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer3): DenseLayer(
(norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer4): DenseLayer(
(norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer5): DenseLayer(
(norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer6): DenseLayer(
(norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
)
(transition1): Transition(
(norm): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
)
(denseblock2): DenseBlock(
(denselayer1): DenseLayer(
(norm1): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(128, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer2): DenseLayer(
(norm1): BatchNorm2d(160, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(160, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer3): DenseLayer(
(norm1): BatchNorm2d(192, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(192, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer4): DenseLayer(
(norm1): BatchNorm2d(224, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(224, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer5): DenseLayer(
(norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer6): DenseLayer(
(norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer7): DenseLayer(
(norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer8): DenseLayer(
(norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer9): DenseLayer(
(norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer10): DenseLayer(
(norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer11): DenseLayer(
(norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer12): DenseLayer(
(norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
)
(transition2): Transition(
(norm): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv): Conv2d(512, 256, kernel_size=(1, 1), stride=(1, 1), bias=False)
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
)
(denseblock3): DenseBlock(
(denselayer1): DenseLayer(
(norm1): BatchNorm2d(256, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(256, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer2): DenseLayer(
(norm1): BatchNorm2d(288, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(288, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer3): DenseLayer(
(norm1): BatchNorm2d(320, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(320, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer4): DenseLayer(
(norm1): BatchNorm2d(352, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(352, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer5): DenseLayer(
(norm1): BatchNorm2d(384, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(384, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer6): DenseLayer(
(norm1): BatchNorm2d(416, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(416, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer7): DenseLayer(
(norm1): BatchNorm2d(448, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(448, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer8): DenseLayer(
(norm1): BatchNorm2d(480, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(480, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer9): DenseLayer(
(norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer10): DenseLayer(
(norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer11): DenseLayer(
(norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer12): DenseLayer(
(norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer13): DenseLayer(
(norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer14): DenseLayer(
(norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer15): DenseLayer(
(norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer16): DenseLayer(
(norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer17): DenseLayer(
(norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer18): DenseLayer(
(norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer19): DenseLayer(
(norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer20): DenseLayer(
(norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer21): DenseLayer(
(norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer22): DenseLayer(
(norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer23): DenseLayer(
(norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer24): DenseLayer(
(norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
)
(transition3): Transition(
(norm): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu): ReLU(inplace=True)
(conv): Conv2d(1024, 512, kernel_size=(1, 1), stride=(1, 1), bias=False)
(pool): AvgPool2d(kernel_size=2, stride=2, padding=0)
)
(denseblock4): DenseBlock(
(denselayer1): DenseLayer(
(norm1): BatchNorm2d(512, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(512, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer2): DenseLayer(
(norm1): BatchNorm2d(544, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(544, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer3): DenseLayer(
(norm1): BatchNorm2d(576, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(576, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer4): DenseLayer(
(norm1): BatchNorm2d(608, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(608, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer5): DenseLayer(
(norm1): BatchNorm2d(640, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(640, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer6): DenseLayer(
(norm1): BatchNorm2d(672, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(672, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer7): DenseLayer(
(norm1): BatchNorm2d(704, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(704, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer8): DenseLayer(
(norm1): BatchNorm2d(736, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(736, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer9): DenseLayer(
(norm1): BatchNorm2d(768, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(768, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer10): DenseLayer(
(norm1): BatchNorm2d(800, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(800, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer11): DenseLayer(
(norm1): BatchNorm2d(832, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(832, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer12): DenseLayer(
(norm1): BatchNorm2d(864, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(864, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer13): DenseLayer(
(norm1): BatchNorm2d(896, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(896, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer14): DenseLayer(
(norm1): BatchNorm2d(928, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(928, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer15): DenseLayer(
(norm1): BatchNorm2d(960, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(960, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
(denselayer16): DenseLayer(
(norm1): BatchNorm2d(992, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu1): ReLU(inplace=True)
(conv1): Conv2d(992, 128, kernel_size=(1, 1), stride=(1, 1), bias=False)
(norm2): BatchNorm2d(128, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu2): ReLU(inplace=True)
(conv2): Conv2d(128, 32, kernel_size=(3, 3), stride=(1, 1), padding=(1, 1), bias=False)
)
)
(norm5): BatchNorm2d(1024, eps=1e-05, momentum=0.1, affine=True, track_running_stats=True)
(relu5): ReLU(inplace=True)
)
(classifier): Linear(in_features=1024, out_features=3, bias=True)
)

# 統計模型參數量以及其他指標
import torchsummary as summary
summary.summary(model, (3, 224, 224))

----------------------------------------------------------------Layer (type)               Output Shape         Param #
================================================================Conv2d-1         [-1, 64, 112, 112]           9,408BatchNorm2d-2         [-1, 64, 112, 112]             128ReLU-3         [-1, 64, 112, 112]               0MaxPool2d-4           [-1, 64, 56, 56]               0BatchNorm2d-5           [-1, 64, 56, 56]             128ReLU-6           [-1, 64, 56, 56]               0Conv2d-7          [-1, 128, 56, 56]           8,192BatchNorm2d-8          [-1, 128, 56, 56]             256ReLU-9          [-1, 128, 56, 56]               0Conv2d-10           [-1, 32, 56, 56]          36,864BatchNorm2d-11           [-1, 96, 56, 56]             192ReLU-12           [-1, 96, 56, 56]               0Conv2d-13          [-1, 128, 56, 56]          12,288BatchNorm2d-14          [-1, 128, 56, 56]             256ReLU-15          [-1, 128, 56, 56]               0Conv2d-16           [-1, 32, 56, 56]          36,864BatchNorm2d-17          [-1, 128, 56, 56]             256ReLU-18          [-1, 128, 56, 56]               0Conv2d-19          [-1, 128, 56, 56]          16,384BatchNorm2d-20          [-1, 128, 56, 56]             256ReLU-21          [-1, 128, 56, 56]               0Conv2d-22           [-1, 32, 56, 56]          36,864BatchNorm2d-23          [-1, 160, 56, 56]             320ReLU-24          [-1, 160, 56, 56]               0Conv2d-25          [-1, 128, 56, 56]          20,480BatchNorm2d-26          [-1, 128, 56, 56]             256ReLU-27          [-1, 128, 56, 56]               0Conv2d-28           [-1, 32, 56, 56]          36,864BatchNorm2d-29          [-1, 192, 56, 56]             384ReLU-30          [-1, 192, 56, 56]               0Conv2d-31          [-1, 128, 56, 56]          24,576BatchNorm2d-32          [-1, 128, 56, 56]             256ReLU-33          [-1, 128, 56, 56]               0Conv2d-34           [-1, 32, 56, 56]          36,864BatchNorm2d-35          [-1, 224, 56, 56]             448ReLU-36          [-1, 224, 56, 56]               0Conv2d-37          [-1, 128, 56, 56]          28,672BatchNorm2d-38          [-1, 128, 56, 56]             256ReLU-39          [-1, 128, 56, 56]               0Conv2d-40           [-1, 32, 56, 56]          36,864BatchNorm2d-41          [-1, 256, 56, 56]             512ReLU-42          [-1, 256, 56, 56]               0Conv2d-43          [-1, 128, 56, 56]          32,768AvgPool2d-44          [-1, 128, 28, 28]               0BatchNorm2d-45          [-1, 128, 28, 28]             256ReLU-46          [-1, 128, 28, 28]               0Conv2d-47          [-1, 128, 28, 28]          16,384BatchNorm2d-48          [-1, 128, 28, 28]             256ReLU-49          [-1, 128, 28, 28]               0Conv2d-50           [-1, 32, 28, 28]          36,864BatchNorm2d-51          [-1, 160, 28, 28]             320ReLU-52          [-1, 160, 28, 28]               0Conv2d-53          [-1, 128, 28, 28]          20,480BatchNorm2d-54          [-1, 128, 28, 28]             256ReLU-55          [-1, 128, 28, 28]               0Conv2d-56           [-1, 32, 28, 28]          36,864BatchNorm2d-57          [-1, 192, 28, 28]             384ReLU-58          [-1, 192, 28, 28]               0Conv2d-59          [-1, 128, 28, 28]          24,576BatchNorm2d-60          [-1, 128, 28, 28]             256ReLU-61          [-1, 128, 28, 28]               0Conv2d-62           [-1, 32, 28, 28]          36,864BatchNorm2d-63          [-1, 224, 28, 28]             448ReLU-64          [-1, 224, 28, 28]               0Conv2d-65          [-1, 128, 28, 28]          28,672BatchNorm2d-66          [-1, 128, 28, 28]             256ReLU-67          [-1, 128, 28, 28]               0Conv2d-68           [-1, 32, 28, 28]          36,864BatchNorm2d-69          [-1, 256, 28, 28]             512ReLU-70          [-1, 256, 28, 28]               0Conv2d-71          [-1, 128, 28, 28]          32,768BatchNorm2d-72          [-1, 128, 28, 28]             256ReLU-73          [-1, 128, 28, 28]               0Conv2d-74           [-1, 32, 28, 28]          36,864BatchNorm2d-75          [-1, 288, 28, 28]             576ReLU-76          [-1, 288, 28, 28]               0Conv2d-77          [-1, 128, 28, 28]          36,864BatchNorm2d-78          [-1, 128, 28, 28]             256ReLU-79          [-1, 128, 28, 28]               0Conv2d-80           [-1, 32, 28, 28]          36,864BatchNorm2d-81          [-1, 320, 28, 28]             640ReLU-82          [-1, 320, 28, 28]               0Conv2d-83          [-1, 128, 28, 28]          40,960BatchNorm2d-84          [-1, 128, 28, 28]             256ReLU-85          [-1, 128, 28, 28]               0Conv2d-86           [-1, 32, 28, 28]          36,864BatchNorm2d-87          [-1, 352, 28, 28]             704ReLU-88          [-1, 352, 28, 28]               0Conv2d-89          [-1, 128, 28, 28]          45,056BatchNorm2d-90          [-1, 128, 28, 28]             256ReLU-91          [-1, 128, 28, 28]               0Conv2d-92           [-1, 32, 28, 28]          36,864BatchNorm2d-93          [-1, 384, 28, 28]             768ReLU-94          [-1, 384, 28, 28]               0Conv2d-95          [-1, 128, 28, 28]          49,152BatchNorm2d-96          [-1, 128, 28, 28]             256ReLU-97          [-1, 128, 28, 28]               0Conv2d-98           [-1, 32, 28, 28]          36,864BatchNorm2d-99          [-1, 416, 28, 28]             832ReLU-100          [-1, 416, 28, 28]               0Conv2d-101          [-1, 128, 28, 28]          53,248BatchNorm2d-102          [-1, 128, 28, 28]             256ReLU-103          [-1, 128, 28, 28]               0Conv2d-104           [-1, 32, 28, 28]          36,864BatchNorm2d-105          [-1, 448, 28, 28]             896ReLU-106          [-1, 448, 28, 28]               0Conv2d-107          [-1, 128, 28, 28]          57,344BatchNorm2d-108          [-1, 128, 28, 28]             256ReLU-109          [-1, 128, 28, 28]               0Conv2d-110           [-1, 32, 28, 28]          36,864BatchNorm2d-111          [-1, 480, 28, 28]             960ReLU-112          [-1, 480, 28, 28]               0Conv2d-113          [-1, 128, 28, 28]          61,440BatchNorm2d-114          [-1, 128, 28, 28]             256ReLU-115          [-1, 128, 28, 28]               0Conv2d-116           [-1, 32, 28, 28]          36,864BatchNorm2d-117          [-1, 512, 28, 28]           1,024ReLU-118          [-1, 512, 28, 28]               0Conv2d-119          [-1, 256, 28, 28]         131,072AvgPool2d-120          [-1, 256, 14, 14]               0BatchNorm2d-121          [-1, 256, 14, 14]             512ReLU-122          [-1, 256, 14, 14]               0Conv2d-123          [-1, 128, 14, 14]          32,768BatchNorm2d-124          [-1, 128, 14, 14]             256ReLU-125          [-1, 128, 14, 14]               0Conv2d-126           [-1, 32, 14, 14]          36,864BatchNorm2d-127          [-1, 288, 14, 14]             576ReLU-128          [-1, 288, 14, 14]               0Conv2d-129          [-1, 128, 14, 14]          36,864BatchNorm2d-130          [-1, 128, 14, 14]             256ReLU-131          [-1, 128, 14, 14]               0Conv2d-132           [-1, 32, 14, 14]          36,864BatchNorm2d-133          [-1, 320, 14, 14]             640ReLU-134          [-1, 320, 14, 14]               0Conv2d-135          [-1, 128, 14, 14]          40,960BatchNorm2d-136          [-1, 128, 14, 14]             256ReLU-137          [-1, 128, 14, 14]               0Conv2d-138           [-1, 32, 14, 14]          36,864BatchNorm2d-139          [-1, 352, 14, 14]             704ReLU-140          [-1, 352, 14, 14]               0Conv2d-141          [-1, 128, 14, 14]          45,056BatchNorm2d-142          [-1, 128, 14, 14]             256ReLU-143          [-1, 128, 14, 14]               0Conv2d-144           [-1, 32, 14, 14]          36,864BatchNorm2d-145          [-1, 384, 14, 14]             768ReLU-146          [-1, 384, 14, 14]               0Conv2d-147          [-1, 128, 14, 14]          49,152BatchNorm2d-148          [-1, 128, 14, 14]             256ReLU-149          [-1, 128, 14, 14]               0Conv2d-150           [-1, 32, 14, 14]          36,864BatchNorm2d-151          [-1, 416, 14, 14]             832ReLU-152          [-1, 416, 14, 14]               0Conv2d-153          [-1, 128, 14, 14]          53,248BatchNorm2d-154          [-1, 128, 14, 14]             256ReLU-155          [-1, 128, 14, 14]               0Conv2d-156           [-1, 32, 14, 14]          36,864BatchNorm2d-157          [-1, 448, 14, 14]             896ReLU-158          [-1, 448, 14, 14]               0Conv2d-159          [-1, 128, 14, 14]          57,344BatchNorm2d-160          [-1, 128, 14, 14]             256ReLU-161          [-1, 128, 14, 14]               0Conv2d-162           [-1, 32, 14, 14]          36,864BatchNorm2d-163          [-1, 480, 14, 14]             960ReLU-164          [-1, 480, 14, 14]               0Conv2d-165          [-1, 128, 14, 14]          61,440BatchNorm2d-166          [-1, 128, 14, 14]             256ReLU-167          [-1, 128, 14, 14]               0Conv2d-168           [-1, 32, 14, 14]          36,864BatchNorm2d-169          [-1, 512, 14, 14]           1,024ReLU-170          [-1, 512, 14, 14]               0Conv2d-171          [-1, 128, 14, 14]          65,536BatchNorm2d-172          [-1, 128, 14, 14]             256ReLU-173          [-1, 128, 14, 14]               0Conv2d-174           [-1, 32, 14, 14]          36,864BatchNorm2d-175          [-1, 544, 14, 14]           1,088ReLU-176          [-1, 544, 14, 14]               0Conv2d-177          [-1, 128, 14, 14]          69,632BatchNorm2d-178          [-1, 128, 14, 14]             256ReLU-179          [-1, 128, 14, 14]               0Conv2d-180           [-1, 32, 14, 14]          36,864BatchNorm2d-181          [-1, 576, 14, 14]           1,152ReLU-182          [-1, 576, 14, 14]               0Conv2d-183          [-1, 128, 14, 14]          73,728BatchNorm2d-184          [-1, 128, 14, 14]             256ReLU-185          [-1, 128, 14, 14]               0Conv2d-186           [-1, 32, 14, 14]          36,864BatchNorm2d-187          [-1, 608, 14, 14]           1,216ReLU-188          [-1, 608, 14, 14]               0Conv2d-189          [-1, 128, 14, 14]          77,824BatchNorm2d-190          [-1, 128, 14, 14]             256ReLU-191          [-1, 128, 14, 14]               0Conv2d-192           [-1, 32, 14, 14]          36,864BatchNorm2d-193          [-1, 640, 14, 14]           1,280ReLU-194          [-1, 640, 14, 14]               0Conv2d-195          [-1, 128, 14, 14]          81,920BatchNorm2d-196          [-1, 128, 14, 14]             256ReLU-197          [-1, 128, 14, 14]               0Conv2d-198           [-1, 32, 14, 14]          36,864BatchNorm2d-199          [-1, 672, 14, 14]           1,344ReLU-200          [-1, 672, 14, 14]               0Conv2d-201          [-1, 128, 14, 14]          86,016BatchNorm2d-202          [-1, 128, 14, 14]             256ReLU-203          [-1, 128, 14, 14]               0Conv2d-204           [-1, 32, 14, 14]          36,864BatchNorm2d-205          [-1, 704, 14, 14]           1,408ReLU-206          [-1, 704, 14, 14]               0Conv2d-207          [-1, 128, 14, 14]          90,112BatchNorm2d-208          [-1, 128, 14, 14]             256ReLU-209          [-1, 128, 14, 14]               0Conv2d-210           [-1, 32, 14, 14]          36,864BatchNorm2d-211          [-1, 736, 14, 14]           1,472ReLU-212          [-1, 736, 14, 14]               0Conv2d-213          [-1, 128, 14, 14]          94,208BatchNorm2d-214          [-1, 128, 14, 14]             256ReLU-215          [-1, 128, 14, 14]               0Conv2d-216           [-1, 32, 14, 14]          36,864BatchNorm2d-217          [-1, 768, 14, 14]           1,536ReLU-218          [-1, 768, 14, 14]               0Conv2d-219          [-1, 128, 14, 14]          98,304BatchNorm2d-220          [-1, 128, 14, 14]             256ReLU-221          [-1, 128, 14, 14]               0Conv2d-222           [-1, 32, 14, 14]          36,864BatchNorm2d-223          [-1, 800, 14, 14]           1,600ReLU-224          [-1, 800, 14, 14]               0Conv2d-225          [-1, 128, 14, 14]         102,400BatchNorm2d-226          [-1, 128, 14, 14]             256ReLU-227          [-1, 128, 14, 14]               0Conv2d-228           [-1, 32, 14, 14]          36,864BatchNorm2d-229          [-1, 832, 14, 14]           1,664ReLU-230          [-1, 832, 14, 14]               0Conv2d-231          [-1, 128, 14, 14]         106,496BatchNorm2d-232          [-1, 128, 14, 14]             256ReLU-233          [-1, 128, 14, 14]               0Conv2d-234           [-1, 32, 14, 14]          36,864BatchNorm2d-235          [-1, 864, 14, 14]           1,728ReLU-236          [-1, 864, 14, 14]               0Conv2d-237          [-1, 128, 14, 14]         110,592BatchNorm2d-238          [-1, 128, 14, 14]             256ReLU-239          [-1, 128, 14, 14]               0Conv2d-240           [-1, 32, 14, 14]          36,864BatchNorm2d-241          [-1, 896, 14, 14]           1,792ReLU-242          [-1, 896, 14, 14]               0Conv2d-243          [-1, 128, 14, 14]         114,688BatchNorm2d-244          [-1, 128, 14, 14]             256ReLU-245          [-1, 128, 14, 14]               0Conv2d-246           [-1, 32, 14, 14]          36,864BatchNorm2d-247          [-1, 928, 14, 14]           1,856ReLU-248          [-1, 928, 14, 14]               0Conv2d-249          [-1, 128, 14, 14]         118,784BatchNorm2d-250          [-1, 128, 14, 14]             256ReLU-251          [-1, 128, 14, 14]               0Conv2d-252           [-1, 32, 14, 14]          36,864BatchNorm2d-253          [-1, 960, 14, 14]           1,920ReLU-254          [-1, 960, 14, 14]               0Conv2d-255          [-1, 128, 14, 14]         122,880BatchNorm2d-256          [-1, 128, 14, 14]             256ReLU-257          [-1, 128, 14, 14]               0Conv2d-258           [-1, 32, 14, 14]          36,864BatchNorm2d-259          [-1, 992, 14, 14]           1,984ReLU-260          [-1, 992, 14, 14]               0Conv2d-261          [-1, 128, 14, 14]         126,976BatchNorm2d-262          [-1, 128, 14, 14]             256ReLU-263          [-1, 128, 14, 14]               0Conv2d-264           [-1, 32, 14, 14]          36,864BatchNorm2d-265         [-1, 1024, 14, 14]           2,048ReLU-266         [-1, 1024, 14, 14]               0Conv2d-267          [-1, 512, 14, 14]         524,288AvgPool2d-268            [-1, 512, 7, 7]               0BatchNorm2d-269            [-1, 512, 7, 7]           1,024ReLU-270            [-1, 512, 7, 7]               0Conv2d-271            [-1, 128, 7, 7]          65,536BatchNorm2d-272            [-1, 128, 7, 7]             256ReLU-273            [-1, 128, 7, 7]               0Conv2d-274             [-1, 32, 7, 7]          36,864BatchNorm2d-275            [-1, 544, 7, 7]           1,088ReLU-276            [-1, 544, 7, 7]               0Conv2d-277            [-1, 128, 7, 7]          69,632BatchNorm2d-278            [-1, 128, 7, 7]             256ReLU-279            [-1, 128, 7, 7]               0Conv2d-280             [-1, 32, 7, 7]          36,864BatchNorm2d-281            [-1, 576, 7, 7]           1,152ReLU-282            [-1, 576, 7, 7]               0Conv2d-283            [-1, 128, 7, 7]          73,728BatchNorm2d-284            [-1, 128, 7, 7]             256ReLU-285            [-1, 128, 7, 7]               0Conv2d-286             [-1, 32, 7, 7]          36,864BatchNorm2d-287            [-1, 608, 7, 7]           1,216ReLU-288            [-1, 608, 7, 7]               0Conv2d-289            [-1, 128, 7, 7]          77,824BatchNorm2d-290            [-1, 128, 7, 7]             256ReLU-291            [-1, 128, 7, 7]               0Conv2d-292             [-1, 32, 7, 7]          36,864BatchNorm2d-293            [-1, 640, 7, 7]           1,280ReLU-294            [-1, 640, 7, 7]               0Conv2d-295            [-1, 128, 7, 7]          81,920BatchNorm2d-296            [-1, 128, 7, 7]             256ReLU-297            [-1, 128, 7, 7]               0Conv2d-298             [-1, 32, 7, 7]          36,864BatchNorm2d-299            [-1, 672, 7, 7]           1,344ReLU-300            [-1, 672, 7, 7]               0Conv2d-301            [-1, 128, 7, 7]          86,016BatchNorm2d-302            [-1, 128, 7, 7]             256ReLU-303            [-1, 128, 7, 7]               0Conv2d-304             [-1, 32, 7, 7]          36,864BatchNorm2d-305            [-1, 704, 7, 7]           1,408ReLU-306            [-1, 704, 7, 7]               0Conv2d-307            [-1, 128, 7, 7]          90,112BatchNorm2d-308            [-1, 128, 7, 7]             256ReLU-309            [-1, 128, 7, 7]               0Conv2d-310             [-1, 32, 7, 7]          36,864BatchNorm2d-311            [-1, 736, 7, 7]           1,472ReLU-312            [-1, 736, 7, 7]               0Conv2d-313            [-1, 128, 7, 7]          94,208BatchNorm2d-314            [-1, 128, 7, 7]             256ReLU-315            [-1, 128, 7, 7]               0Conv2d-316             [-1, 32, 7, 7]          36,864BatchNorm2d-317            [-1, 768, 7, 7]           1,536ReLU-318            [-1, 768, 7, 7]               0Conv2d-319            [-1, 128, 7, 7]          98,304BatchNorm2d-320            [-1, 128, 7, 7]             256ReLU-321            [-1, 128, 7, 7]               0Conv2d-322             [-1, 32, 7, 7]          36,864BatchNorm2d-323            [-1, 800, 7, 7]           1,600ReLU-324            [-1, 800, 7, 7]               0Conv2d-325            [-1, 128, 7, 7]         102,400BatchNorm2d-326            [-1, 128, 7, 7]             256ReLU-327            [-1, 128, 7, 7]               0Conv2d-328             [-1, 32, 7, 7]          36,864BatchNorm2d-329            [-1, 832, 7, 7]           1,664ReLU-330            [-1, 832, 7, 7]               0Conv2d-331            [-1, 128, 7, 7]         106,496BatchNorm2d-332            [-1, 128, 7, 7]             256ReLU-333            [-1, 128, 7, 7]               0Conv2d-334             [-1, 32, 7, 7]          36,864BatchNorm2d-335            [-1, 864, 7, 7]           1,728ReLU-336            [-1, 864, 7, 7]               0Conv2d-337            [-1, 128, 7, 7]         110,592BatchNorm2d-338            [-1, 128, 7, 7]             256ReLU-339            [-1, 128, 7, 7]               0Conv2d-340             [-1, 32, 7, 7]          36,864BatchNorm2d-341            [-1, 896, 7, 7]           1,792ReLU-342            [-1, 896, 7, 7]               0Conv2d-343            [-1, 128, 7, 7]         114,688BatchNorm2d-344            [-1, 128, 7, 7]             256ReLU-345            [-1, 128, 7, 7]               0Conv2d-346             [-1, 32, 7, 7]          36,864BatchNorm2d-347            [-1, 928, 7, 7]           1,856ReLU-348            [-1, 928, 7, 7]               0Conv2d-349            [-1, 128, 7, 7]         118,784BatchNorm2d-350            [-1, 128, 7, 7]             256ReLU-351            [-1, 128, 7, 7]               0Conv2d-352             [-1, 32, 7, 7]          36,864BatchNorm2d-353            [-1, 960, 7, 7]           1,920ReLU-354            [-1, 960, 7, 7]               0Conv2d-355            [-1, 128, 7, 7]         122,880BatchNorm2d-356            [-1, 128, 7, 7]             256ReLU-357            [-1, 128, 7, 7]               0Conv2d-358             [-1, 32, 7, 7]          36,864BatchNorm2d-359            [-1, 992, 7, 7]           1,984ReLU-360            [-1, 992, 7, 7]               0Conv2d-361            [-1, 128, 7, 7]         126,976BatchNorm2d-362            [-1, 128, 7, 7]             256ReLU-363            [-1, 128, 7, 7]               0Conv2d-364             [-1, 32, 7, 7]          36,864BatchNorm2d-365           [-1, 1024, 7, 7]           2,048ReLU-366           [-1, 1024, 7, 7]               0Linear-367                    [-1, 3]           3,075
================================================================
Total params: 6,956,931
Trainable params: 6,956,931
Non-trainable params: 0
----------------------------------------------------------------
Input size (MB): 0.57
Forward/backward pass size (MB): 294.57
Params size (MB): 26.54
Estimated Total Size (MB): 321.69
----------------------------------------------------------------

四、訓練模型

1.編寫訓練函數

# 訓練循環
def train(dataloader, model, loss_fn, optimizer):size = len(dataloader.dataset)  # 訓練集的大小num_batches = len(dataloader)   # 批次數目, (size/batch_size，向上取整)train_loss, train_acc = 0, 0  # 初始化訓練損失和正確率for X, y in dataloader:  # 獲取圖片及其標簽X, y = X.to(device), y.to(device)# 計算預測誤差pred = model(X)          # 網絡輸出loss = loss_fn(pred, y)  # 計算網絡輸出和真實值之間的差距，targets為真實值，計算二者差值即為損失# 反向傳播optimizer.zero_grad()  # grad屬性歸零loss.backward()        # 反向傳播optimizer.step()       # 每一步自動更新# 記錄acc與losstrain_acc  += (pred.argmax(1) == y).type(torch.float).sum().item()train_loss += loss.item()train_acc  /= sizetrain_loss /= num_batchesreturn train_acc, train_loss

2.編寫測試函數

def test (dataloader, model, loss_fn):size        = len(dataloader.dataset)  # 測試集的大小num_batches = len(dataloader)          # 批次數目, (size/batch_size，向上取整)test_loss, test_acc = 0, 0# 當不進行訓練時，停止梯度更新，節省計算內存消耗with torch.no_grad():for imgs, target in dataloader:imgs, target = imgs.to(device), target.to(device)# 計算losstarget_pred = model(imgs)loss        = loss_fn(target_pred, target)test_loss += loss.item()test_acc  += (target_pred.argmax(1) == target).type(torch.float).sum().item()test_acc  /= sizetest_loss /= num_batchesreturn test_acc, test_loss

3.正式訓練

import copyoptimizer  = torch.optim.Adam(model.parameters(), lr= 1e-4)
loss_fn    = nn.CrossEntropyLoss() # 創建損失函數epochs     = 20train_loss = []
train_acc  = []
test_loss  = []
test_acc   = []best_acc = 0    # 設置一個最佳準確率，作為最佳模型的判別指標for epoch in range(epochs):model.train()epoch_train_acc, epoch_train_loss = train(train_dl, model, loss_fn, optimizer)model.eval()epoch_test_acc, epoch_test_loss = test(test_dl, model, loss_fn)# 保存最佳模型到 best_modelif epoch_test_acc > best_acc:best_acc   = epoch_test_accbest_model = copy.deepcopy(model)train_acc.append(epoch_train_acc)train_loss.append(epoch_train_loss)test_acc.append(epoch_test_acc)test_loss.append(epoch_test_loss)# 獲取當前的學習率lr = optimizer.state_dict()['param_groups'][0]['lr']template = ('Epoch:{:2d}, Train_acc:{:.1f}%, Train_loss:{:.3f}, Test_acc:{:.1f}%, Test_loss:{:.3f}, Lr:{:.2E}')print(template.format(epoch+1, epoch_train_acc*100, epoch_train_loss, epoch_test_acc*100, epoch_test_loss, lr))# 保存最佳模型到文件中
PATH = './best_model.pth'  # 保存的參數文件名
torch.save(best_model.state_dict(), PATH)print('Done')

五、結果可視化

1.Loss與Accuracy圖

import matplotlib.pyplot as plt
#隱藏警告
import warnings
warnings.filterwarnings("ignore")               #忽略警告信息
plt.rcParams['font.sans-serif']    = ['SimHei'] # 用來正常顯示中文標簽
plt.rcParams['axes.unicode_minus'] = False      # 用來正常顯示負號
plt.rcParams['figure.dpi']         = 100        #分辨率epochs_range = range(epochs)plt.figure(figsize=(12, 3))
plt.subplot(1, 2, 1)plt.plot(epochs_range, train_acc, label='Training Accuracy')
plt.plot(epochs_range, test_acc, label='Test Accuracy')
plt.legend(loc='lower right')
plt.title('Training and Validation Accuracy')plt.subplot(1, 2, 2)
plt.plot(epochs_range, train_loss, label='Training Loss')
plt.plot(epochs_range, test_loss, label='Test Loss')
plt.legend(loc='upper right')
plt.title('Training and Validation Loss')
plt.show()

2.模型評估

# 將參數加載到model當中
best_model.load_state_dict(torch.load(PATH, map_location=device))
epoch_test_acc, epoch_test_loss = test(test_dl, best_model, loss_fn)