深度学习（二十二）计算机视觉树叶分类竞赛新手入门及常见问题解决

最新推荐文章于 2024-10-09 00:00:00 发布

浮云白日303

最新推荐文章于 2024-10-09 00:00:00 发布

阅读量409

点赞数 8

文章标签：深度学习计算机视觉分类 python 学习人工智能数据挖掘

本文链接：https://blog.csdn.net/m0_68737530/article/details/136002188

版权

前半部分参考13th：Code and summary | Kaggle

自己后面利用resnet18 效果不太好

##树叶分类
import torch
import torchvision
from torch import nn
from d2l import torch as d2l
from torch.utils.data import Dataset,DataLoader
import pandas as pd
import os
import numpy as np
from PIL import Image
#如何读取自己下载的数据集
#<https://blog.csdn.net/lifei1229/article/details/105519924?ops_request_misc=%257B%2522request%255Fid%2522%253A%2522168440519716800184140603%2522%252C%2522scm%2522%253A%252220140713.130102334..%2522%257D&request_id=168440519716800184140603&biz_id=0&utm_medium=distribute.pc_search_result.none-task-blog-2~all~baidu_landing_v2~default-1-105519924-null-null.142^v87^insert_down28v1,239^v2^insert_chatgpt&utm_term=%E6%80%8E%E4%B9%88%E8%AF%BB%E5%8F%96%E8%87%AA%E5%B7%B1%E4%B8%8B%E8%BD%BD%E7%9A%84%E6%95%B0%E6%8D%AE%E9%9B%86&spm=1018.2226.3001.4187>

# class shuye(Dataset):
#     def __init__(self):#去读数据路径
#         super(shuye,self).__init__()
#         pass
#     def __len__(self):#返回数据长度
#         pass
#     def __getitem__(self, idx):#返回当前位置的数据和标签
#         pass

##看看label里面是什么样的
label = pd.read_csv('E:\\pythonProject/train.csv')
# train_img = np.asarray(label.iloc[1:10,0])
# print(la