OpenNMT/OpenNMT-tf

Adding benchmarks to Readme

Open

#464 创建于 2019年7月1日

在 GitHub 查看
 (1 评论) (0 反应) (0 负责人)Python (1,428 star) (394 fork)batch import
documentationhelp wanted

描述

Hi, Is it possible to add benchmarks of some models into documentation for comparison purposes ? Also run time would be helpful. For example 1M iteration takes a weekend with GTX 1080.

贡献者指南

技术栈
pythontensorflow
领域
documentationmachine learning
议题类型
documentation
难度面向新贡献者的预计实现难度，1 表示很小改动，5 表示专家级工作。
2
预计时间有经验贡献者完成调查、实现、测试并准备 pull request 的粗略时间范围。
1-3 hours
活动状态议题当前的可参与程度：新鲜、活跃、陈旧、阻塞或等待维护者输入。
stale
清晰度议题是否清楚说明期望改动、验收标准和下一步。
clear
前置要求
Basic knowledge of OpenNMT tfAccess to GPU for benchmarking
新手友好度1-100 的估计分数，表示该议题对首次贡献者的友好程度。
70
研究方向
Start by exploring the repository for existing benchmark scripts or model configurations. Check if there are any precomputed benchmark results elsewhere. Run the training scripts on a GPU (e.g., GTX 1080) for a small number of iterations and record time per iteration and final metrics. Update the README.md with a new 'Benchmarks' section including a table of models, hardware used, and runtime. Reference any relevant files like 'scripts/benchmark.py' or 'configs/*.yml'.