如何将aaa云主机做网站创意网页设计论文

12种猫分类比赛传送门

要求很简单，给train和test集，训练模型实现图像分类。

这里使用的是残差连接模型，这个平台有预训练好的模型，可以直接拿来主义。

训练十几个迭代，每个批次60左右，准确率达到90%以上

一、导入库，解压文件

import os
import zipfile
import random
import json
import cv2
import numpy as np
from PIL import Imageimport matplotlib.pyplot as plt
from sklearn.model_selection import train_test_split
import paddle
import paddle.nn as nn
from paddle.io import Dataset,DataLoader
from paddle.nn import \Layer, \Conv2D, Linear, \Embedding, MaxPool2D, \BatchNorm2D, ReLUimport paddle.vision.transforms as transforms
from paddle.vision.models import resnet50
from paddle.metric import Accuracytrain_parameters = {"input_size": [3, 224, 224],                     # 输入图片的shape"class_dim": 12,                                 # 分类数"src_path":"data/data10954/cat_12_train.zip",   # 原始数据集路径"src_test_path":"data/data10954/cat_12_test.zip",   # 原始数据集路径"target_path":"/home/aistudio/data/dataset",     # 要解压的路径 "train_list_path": "./train.txt",                # train_data.txt路径"eval_list_path": "./eval.txt",                  # eval_data.txt路径"label_dict":{},                                 # 标签字典"readme_path": "/home/aistudio/data/readme.json",# readme.json路径"num_epochs":6,                                 # 训练轮数"train_batch_size": 16,                          # 批次的大小"learning_strategy": {                           # 优化函数相关的配置"lr": 0.0005                                  # 超参数学习率} 
}scr_path=train_parameters['src_path']
target_path=train_parameters['target_path']
src_test_path=train_parameters["src_test_path"]
z = zipfile.ZipFile(scr_path, 'r')
z.extractall(path=target_path)
z = zipfile.ZipFile(src_test_path, 'r')
z.extractall(path=target_path)
z.close()
for imgpath in os.listdir(target_path + '/cat_12_train'):src = os.path.join(target_path + '/cat_12_train/', imgpath)img = Image.open(src)if img.mode != 'RGB':img = img.convert('RGB')img.save(src)for imgpath in os.listdir(target_path + '/cat_12_test'):src = os.path.join(target_path + '/cat_12_test/', imgpath)img = Image.open(src)if img.mode != 'RGB':img = img.convert('RGB')img.save(src)

 解压后将所有图像变为RGB图像

二、加载训练集，进行预处理、数据增强、格式变换

transform = transforms.Compose([transforms.Resize(size=224),transforms.ColorJitter(0.2, 0.2, 0.2, 0.2),transforms.RandomHorizontalFlip(),transforms.RandomRotation(15),transforms.RandomResizedCrop(size=224, scale=(0.8, 1.0)),transforms.ToTensor(),transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])
])x_train,x_eval,y_train=[],[],[]#获取训练图像和标签、测试图像和标签
contents=[]
with open('data/data10954/train_list.txt')as f:contents=f.read().split('\n')for item in contents:if item=='':continuepath='data/dataset/'+item.split('\t')[0]data=np.array(Image.open(path).convert('RGB'))data=np.array(transform(data))x_train.append(data)y_train.append(int(item.split('\t')[-1]))contetns=os.listdir('data/dataset/cat_12_test')
for item in contetns:path='data/dataset/cat_12_test/'+itemdata=np.array(Image.open(path).convert('RGB'))data=np.array(transform(data))x_eval.append(data)

重点是transforms变换的预处理

三、划分训练集和测试集

x_train=np.array(x_train)y_train=np.array(y_train)x_eval=np.array(x_eval)x_train,x_test,y_train,y_test=train_test_split(x_train,y_train,test_size=0.2,random_state=42,stratify=y_train)x_train=paddle.to_tensor(x_train,dtype='float32')
y_train=paddle.to_tensor(y_train,dtype='int64')
x_test=paddle.to_tensor(x_test,dtype='float32')
y_test=paddle.to_tensor(y_test,dtype='int64')
x_eval=paddle.to_tensor(x_eval,dtype='float32')

 这是必要的，可以随时利用测试集查看准确率

四、加载预训练模型，选择损失函数和优化器

learning_rate=0.001
epochs =5  # 迭代轮数
batch_size = 50  # 批次大小
weight_decay=1e-5
num_class=12cnn=resnet50(pretrained=True)
checkpoint=paddle.load('checkpoint.pdparams')for param in cnn.parameters():param.requires_grad=False
cnn.fc = nn.Linear(2048, num_class)
cnn.set_dict(checkpoint['cnn_state_dict'])
criterion=nn.CrossEntropyLoss()
optimizer = paddle.optimizer.Adam(learning_rate=learning_rate, parameters=cnn.fc.parameters(),weight_decay=weight_decay)

第一次训练把加载模型注释掉即可，优化器包含最后一层全连接的参数

五、模型训练 

if x_train.shape[3]==3:x_train=paddle.transpose(x_train,perm=(0,3,1,2))dataset = paddle.io.TensorDataset([x_train, y_train])
data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=True)
for epoch in range(epochs):for batch_data, batch_labels in data_loader:outputs = cnn(batch_data)loss = criterion(outputs, batch_labels)print(epoch)loss.backward()optimizer.step()optimizer.clear_grad()print(f"Epoch [{epoch+1}/{epochs}], Loss: {loss.numpy()[0]}")#保存参数
paddle.save({'cnn_state_dict': cnn.state_dict(),}, 'checkpoint.pdparams')

 使用批处理，这个很重要，不然平台分分钟炸了

六、测试集准确率

num_class=12
batch_size=64
cnn=resnet50(pretrained=True)
checkpoint=paddle.load('checkpoint.pdparams')for param in cnn.parameters():param.requires_grad=False
cnn.fc = nn.Linear(2048, num_class)
cnn.set_dict(checkpoint['cnn_state_dict'])cnn.eval()if x_test.shape[3]==3:x_test=paddle.transpose(x_test,perm=(0,3,1,2))
dataset = paddle.io.TensorDataset([x_test, y_test])
data_loader = DataLoader(dataset, batch_size=batch_size, shuffle=True)with paddle.no_grad():score=0for batch_data, batch_labels in data_loader:predictions = cnn(batch_data)predicted_probabilities = paddle.nn.functional.softmax(predictions, axis=1)predicted_labels = paddle.argmax(predicted_probabilities, axis=1) print(predicted_labels)for i in range(len(predicted_labels)):if predicted_labels[i].numpy()==batch_labels[i]:score+=1print(score/len(y_test))

设置eval模式，使用批处理测试准确率