637Submission Details

本文介绍了一种计算二叉树每一层节点值平均数的算法实现。通过递归方式,利用列表来保存每层节点,计算各层平均值,并最终输出所有层的平均值。适用于理解二叉树遍历及层次结构处理。

摘要生成于 C知道 ,由 DeepSeek-R1 满血版支持, 前往体验 >

637Submission Details

源自leetcode

思路

使用递归重复的往open表里面添加何删除待遍历的层数。

代码
vector<double> push(list <TreeNode> &open, vector<double> &averages) {
        if (!open.size())
            return averages;
        double sum = 0;
        int amout = 0;
        for (auto iter = open.begin(); iter != open.end(); iter++) {
            sum = (*iter).val + sum;
            amout++;
        }
        averages.push_back(sum / amout);
        list <TreeNode> list{};
        for (auto iter = open.begin(); iter != open.end(); iter++) {
            if ((*iter).left)
                list.push_back(*((*iter).left));
            if ((*iter).right)
                list.push_back(*((*iter).right));
        }
        averages = push(list, averages);
        return averages;
    }

    vector<double> averageOfLevels(TreeNode *root) {
        vector<double> averages{};
        averages.push_back(root->val);

        list <TreeNode> open{};
        if (root->left)
            open.push_back(*(root->left));
        if (root->right)
            open.push_back(*(root->right));
        averages=push(open, averages);
        for(auto iter=averages.begin();iter!=averages.end();iter++)
        {
            cout<<*iter<<ends;
        }
        return averages;
    }
Part 2: Image Classification Project (50 marks) - Submission All of your dataset, code (Python files and ipynb files) should be a package in a single ZIP file, with a PDF of your report (notebook with output cells, analysis, and answers). INCLUDE your dataset in the zip file. For this project, you will develop an image classification model to recognize objects in your custom dataset. The project involves the following steps: Step 1: Dataset Creation (10 marks) • Task: You can choose an existing dataset such as FashionMNIST and add one more class. • Deliverable: Include the dataset (images and labels) in the ZIP file submission. Step 2: Data Loading and Exploration (10 marks) • Task: Organize the dataset into training, validation, and test sets. Display dataset statistics and visualize samples with their labels. For instance, show the number of data entries, the number of classes, the number of data entries for each class, the shape of the image size, and randomly plot 5 images in the training set with their corresponding labels. Step 3: Model Implementation (10 marks) • Task: Implement a classification model, using frameworks like TensorFlow or PyTorch. Existing models like EfficientNet are allowed. Provide details on model parameters. Step 4: Model Training (10 marks) • Task: Train the model with proper settings (e.g., epochs, optimizer, learning rate). Include visualizations of training and validation performance (loss and accuracy). Step 5: Model Evaluation and Testing (10 marks) • Task: Evaluate the model on the test set. Display sample predictions, calculate accuracy, and generate a confusion matrix.
07-28
评论
添加红包

请填写红包祝福语或标题

红包个数最小为10个

红包金额最低5元

当前余额3.43前往充值 >
需支付:10.00
成就一亿技术人!
领取后你会自动成为博主和红包主的粉丝 规则
hope_wisdom
发出的红包
实付
使用余额支付
点击重新获取
扫码支付
钱包余额 0

抵扣说明:

1.余额是钱包充值的虚拟货币,按照1:1的比例进行支付金额的抵扣。
2.余额无法直接购买下载,可以购买VIP、付费专栏及课程。

余额充值