Xingyu L1aoXingyu

Basic Coding Style Rules

Based on these core principles, we have carefully designed a set of basic rules that SWE Agents or vibe coding tools should follow:

Minimize unnecessary indentation, spaces, and line breaks to keep the code compact.
For top-level functions, classes, and module names, adhere to proper and complete naming conventions as much as possible. For code within functions, classes, or modules — especially temporary variables — reduce variable name length to minimize code size.
Provide brief but necessary comments for top-level functions, classes, and modules to describe their purpose, inputs, and outputs. Inside functions, avoid comments unless absolutely necessary.
Where possible, implement more functions, classes, or modules within a single file, especially when they are interrelated. Separate code into different files only when they serve distinct modules or functionalities.
Use advanced language features and designs to reduce code size — for example, prefer lambda functio

Project Title

One Paragraph of project description goes here

Getting Started

These instructions will get you a copy of the project up and running on your local machine for development and testing purposes. See deployment for notes on how to deploy the project on a live system.

Prerequisites

Tmux 快捷键 & 速查表

启动新会话：

tmux [new -s 会话名 -n 窗口名]

恢复会话：

tmux at [-t 会话名]

	You are an assistant that engages in extremely thorough, self-questioning reasoning. Your approach mirrors human stream-of-consciousness thinking, characterized by continuous exploration, self-doubt, and iterative analysis.

	## Core Principles

	1. EXPLORATION OVER CONCLUSION
	- Never rush to conclusions
	- Keep exploring until a solution emerges naturally from the evidence
	- If uncertain, continue reasoning indefinitely
	- Question every assumption and inference

	# This isn't supposed to run as a bash script, i named it with ".sh" for syntax highlighting.

	# https://developer.nvidia.com/nsight-systems
	# https://docs.nvidia.com/nsight-systems/profiling/index.html

	# My preferred nsys (command line executable used to create profiles) commands
	#
	# In your script, write
	# torch.cuda.nvtx.range_push("region name")
	# ...

	$ git clone [email protected]:xxxxx/xxxx.git my-awesome-proj
	Cloning into 'my-awesome-proj'...
	ssh: connect to host github.com port 22: Connection timed out
	fatal: Could not read from remote repository.

	$ # This should also timeout
	$ ssh -T [email protected]
	ssh: connect to host github.com port 22: Connection timed out

	$ # but this might work

	import requests
	import json
	import cv2

	addr = 'http://localhost:5000'
	test_url = addr + '/api/test'

	# prepare headers for http request
	content_type = 'image/jpeg'
	headers = {'content-type': content_type}

	import torch
	import torch.nn as nn

	# Implementation of Deep Metric Learning by Online Soft Mining and Class-Aware Attention
	# https://arxiv.org/pdf/1811.01459v2.pdf

	class OSM_CAA_Loss(nn.Module):
	def __init__(self, alpha=1.2, l=0.5, osm_sigma=0.8,use_gpu=True):
	super(OSM_CAA_Loss, self).__init__()
	self.use_gpu = use_gpu


	from __future__ import print_function
	from nvidia.dali.pipeline import Pipeline
	import nvidia.dali.ops as ops
	import nvidia.dali.types as types
	from nvidia.dali.plugin.pytorch import DALIGenericIterator

	import logging
	import os
	import numpy as np

	syntax enable
	syntax on
	set number
	set cursorline
	set tabstop=4

	" 让配置变更立即生效
	autocmd BufWritePost $MYVIMRC source $MYVIMRC

	let mapleader=";"