CODE 39: Submission Details

本文介绍了一种不使用递归的方法来完成二叉树节点值的中序遍历。通过栈数据结构实现了迭代式的中序遍历算法,并提供了详细的Java实现代码。

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

Given a binary tree, return the inorder traversal of its nodes' values.

For example:
Given binary tree {1,#,2,3},

   1
    \
     2
    /
   3

return [1,3,2].

Note: Recursive solution is trivial, could you do it iteratively?

confused what "{1,#,2,3}" means? > read more on how binary tree is serialized on OJ.


OJ's Binary Tree Serialization:

The serialization of a binary tree follows a level order traversal, where '#' signifies a path terminator where no node exists below.

Here's an example:

   1
  / \
 2   3
    /
   4
    \
     5
The above binary tree is serialized as  "{1,2,3,#,#,4,#,#,5}".
	public ArrayList<Integer> inorderTraversal(TreeNode root) {
		// Start typing your Java solution below
		// DO NOT write main() function
		if (null == root) {
			return new ArrayList<Integer>();
		}
		ArrayList<Integer> inorder = new ArrayList<Integer>();
		Stack<TreeNode> stack = new Stack<TreeNode>();
		TreeNode node = root;
		while (!stack.isEmpty() || null != node) {
			if (null == node) {
				node = stack.pop();
				inorder.add(node.val);
				node = node.right;
			} else {
				stack.push(node);
				node = node.left;
			}
		}
		return inorder;
	}


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