paddlepaddle 实现AlexNet模型，复现原创论文

Vertira

已于 2022-09-03 00:21:02 修改

阅读量613

点赞数 1

分类专栏： paddlepaddle 文章标签： paddlepaddle 人工智能

于 2022-09-02 23:37:19 首次发布

本文链接：https://blog.csdn.net/Vertira/article/details/126671494

版权

paddlepaddle 专栏收录该内容

45 篇文章 19 订阅

订阅专栏

，AlexNet是与LeNet不同的一种新的深度学习模型。

论文原文百度云资源链接：链接：https://pan.baidu.com/s/1WdZnD6aVzUXvzs9XxshROQ 提取码：hans

第一步：模型实现

import os
import cv2
import numpy as np
import paddle
from paddle.io import Dataset
import paddle.vision.transforms as T
import matplotlib.pyplot as plt
from paddle.io import Dataset
from PIL import Image
from PIL import ImageFile
import paddle.nn as nn
import paddle.nn.functional as F
# 打印所使用的GPU编号
print(paddle.device.get_device())
ImageFile.LOAD_TRUNCATED_IMAGES = True

# 搭建Alexnet网络

class alexnet(paddle.nn.Layer):
    def __init__(self, ):
        super(alexnet, self).__init__()
        self.conv1 = paddle.nn.Conv2D(in_channels=3, out_channels=96, kernel_size=7, stride=2, padding=2)
        self.conv2 = paddle.nn.Conv2D(in_channels=96, out_channels=256, kernel_size=5, stride=1, padding=2)
        self.conv3 = paddle.nn.Conv2D(in_channels=256, out_channels=384, kernel_size=3, stride=1, padding=1)
        self.conv4 = paddle.nn.Conv2D(in_channels=384, out_channels=384, kernel_size=3, stride=1, padding=1)
        self.conv5 = paddle.nn.Conv2D(in_channels=384, out_channels=256, kernel_size=3, stride=1, padding=1)
        self.mp1 = paddle.nn.MaxPool2D(kernel_size=3, stride=2)
        self.mp2 = paddle.nn.MaxPool2D(kernel_size=3, stride=2)
        self.L1 = paddle.nn.Linear(in_features=256*3*3, out_features=1024)
        self.L2 = paddle.nn.Linear(in_features=1024, out_features=512)
        self.L3 = paddle.nn.Linear(in_features=512, out_features=10)

    def forward(self, x):
        x = self.conv1(x)
        x = paddle.nn.functional.relu(x)
        x = self.mp1(x)
        x = self.conv2(x)
        x = paddle.nn.functional.relu(x)
        x = self.mp2(x)
        x = self.conv3(x)
        x = paddle.nn.functional.relu(x)
        x = self.conv4(x)
        x = paddle.nn.functional.relu(x)
        x = self.conv5(x)
        x = paddle.nn.functional.relu(x)
        x = paddle.flatten(x, start_axis=1, stop_axis=-1)
        x = self.L1(x)
        x = paddle.nn.functional.relu(x)
        x = self.L2(x)
        x = paddle.nn.functional.relu(x)
        x = self.L3(x)
        return x

第二步：查看一下网络结构；

# 网络结构   应用paddle.summary检查网络结构是否正确。
model = alexnet()

paddle.summary(model, (100,3,32,32))

运行后的输出结果。

---------------------------------------------------------------------------
 Layer (type)       Input Shape          Output Shape         Param #    
===========================================================================
   Conv2D-1      [[100, 3, 32, 32]]   [100, 96, 15, 15]       14,208     
  MaxPool2D-1   [[100, 96, 15, 15]]    [100, 96, 7, 7]           0       
   Conv2D-2      [[100, 96, 7, 7]]     [100, 256, 7, 7]       614,656    
  MaxPool2D-2    [[100, 256, 7, 7]]    [100, 256, 3, 3]          0       
   Conv2D-3      [[100, 256, 3, 3]]    [100, 384, 3, 3]       885,120    
   Conv2D-4      [[100, 384, 3, 3]]    [100, 384, 3, 3]      1,327,488   
   Conv2D-5      [[100, 384, 3, 3]]    [100, 256, 3, 3]       884,992    
   Linear-1        [[100, 2304]]         [100, 1024]         2,360,320   
   Linear-2        [[100, 1024]]          [100, 512]          524,800    
   Linear-3         [[100, 512]]          [100, 10]            5,130     
===========================================================================
Total params: 6,616,714
Trainable params: 6,616,714
Non-trainable params: 0
---------------------------------------------------------------------------
Input size (MB): 1.17
Forward/backward pass size (MB): 39.61
Params size (MB): 25.24
Estimated Total Size (MB): 66.02
---------------------------------------------------------------------------

在网络设计过程中，往往会出现结构性差错的地方就在卷积层与全连接层之间出现，在进行Flatten（扁平化）之后，出现数据维度对不上。可以在网络定义的过程中，首先将Flatten之后的全连接层去掉，通过paddle.summary输出结构确认卷积层数出为 256×3×3之后，再将全连接层接上。如果出现差错，可以进行每一层校验。

在上面模型的基础上，进行下面相关操作（加载数据，训练，预测）

第三步，加载Cifar10数据

原文根据AlexNet的结构，结合 The CIFAR-10 dataset 图片的特点（32×32×3），对AlexNet网络结构进行了微调：

import sys,os,math,time
import matplotlib.pyplot as plt
from numpy import *

import paddle
from paddle.vision.transforms import Normalize
normalize = Normalize(mean=[0.5,0.5,0.5], std=[0.5,0.5,0.5], data_format='HWC')

from paddle.vision.datasets import Cifar10
cifar10_train = Cifar10(mode='train', transform=normalize)
cifar10_test = Cifar10(mode='test', transform=normalize)

train_dataset = [cifar10_train.data[id][0].reshape(3,32,32) for id in range(len(cifar10_train.data))]
train_labels = [cifar10_train.data[id][1] for id in range(len(cifar10_train.data))]

class Dataset(paddle.io.Dataset):
    def __init__(self, num_samples):
        super(Dataset, self).__init__()
        self.num_samples = num_samples

    def __getitem__(self, index):
        data = train_dataset[index]
        label = train_labels[index]
        return paddle.to_tensor(data,dtype='float32'), paddle.to_tensor(label,dtype='int64')

    def __len__(self):
        return self.num_samples

_dataset = Dataset(len(cifar10_train.data))
train_loader = paddle.io.DataLoader(_dataset, batch_size=100, shuffle=True)

第四步训练网络

test_dataset = [cifar10_test.data[id][0].reshape(3,32,32) for id in range(len(cifar10_test.data))]
test_label = [cifar10_test.data[id][1] for id in range(len(cifar10_test.data))]

test_input = paddle.to_tensor(test_dataset, dtype='float32')
test_l = paddle.to_tensor(array(test_label)[:,newaxis])

optimizer = paddle.optimizer.Adam(learning_rate=0.001, parameters=model.parameters())
def train(model):
    model.train()
    epochs = 2
    accdim = []
    lossdim = []
    testaccdim = []

    for epoch in range(epochs):
        for batch, data in enumerate(train_loader()):
            out = model(data[0])
            loss = paddle.nn.functional.cross_entropy(out, data[1])
            acc = paddle.metric.accuracy(out, data[1])
            loss.backward()
            optimizer.step()
            optimizer.clear_grad()

            accdim.append(acc.numpy())
            lossdim.append(loss.numpy())

            predict = model(test_input)
            testacc = paddle.metric.accuracy(predict, test_l)
            testaccdim.append(testacc.numpy())

            if batch%10 == 0 and batch>0:
                print('Epoch:{}, Batch: {}, Loss:{}, Accuracys:{}{}'.format(epoch, batch, loss.numpy(), acc.numpy(), testacc.numpy()))

    plt.figure(figsize=(10, 6))
    plt.plot(accdim, label='Accuracy')
    plt.plot(testaccdim, label='Test')
    plt.xlabel('Step')
    plt.ylabel('Acc')
    plt.grid(True)
    plt.legend(loc='upper left')
    plt.tight_layout()

train(model)

训练参数：

BatchSize：100
LearningRate：0.001

如果BatchSize过小，训练速度变慢。