Author: Davide Liu

Tech graduated from Tsinghua University. Data explorer, running addicted, obstacles lover, blogging passionate.
Machine Learning, NLP

Speed benchmark einsum vs matmul in XL-Attention

The original Transformer can only attend to a fixed and limited segment of the input to compute its attention. The major drawback of this architecture is that no information can flow across separated segments which prevents the Transformer to model long-term dependencies. Transformer-XL is an enhancement to the vanilla Transformer which enables the latter to store the most recent hidden states in a fixed-length memory … Continue reading Speed benchmark einsum vs matmul in XL-Attention

Davide LiuLeave a comment
Spartan Race, Sport Science

Spartan Race obstacles: technique is all you need

In this article, we are going to introduce some of the most difficult and tricky Spartan Race obstacles and learn useful techniques to conquer them. Most competitors may think that strength is the key and that strong men are advantaged when going through obstacles. However, in this article, we are going to see that technique is (almost) all you need, and that no matter your … Continue reading Spartan Race obstacles: technique is all you need

Davide LiuLeave a comment
Technology, Tools

Rpg Maker MV Translator

🎮 Use AI to translate all the dialogs and texts of your favorite RPG Maker MV video games automatically and for free. 🎮 RPG Maker MV, created by Kadokawa and released by Degica in 2015, is a software used to create role-playing video games. It is the replacement for RPG Maker VX Ace, released in 2011. 👊 You worked hard to make your game, now let AI work hard for … Continue reading Rpg Maker MV Translator

Davide Liu1 Comment
Technology, Tools

Running Performance Calculator: Altitude, Elevation Gain, and Temperature

👉 Have you ever wondered if you ran 10km at 2000m altitude, how fast would you run the same distance at lower altitudes? How would elevation gain and temperature affect your performance? ðŸ¤” 👉 The goal of this running distance calculator is to estimate how your running pace and time would change given different elevation gain, altitude, and temperature. Features References Continue reading Running Performance Calculator: Altitude, Elevation Gain, and Temperature

Davide LiuLeave a comment
Sport Science

Four benefits of Contrast Hydrotherapy

Contrast showers, sometimes also known as contrast hydrotherapy, are showers in which our body temperature changes from hot to cold and back again by alternating between hot then cold water. A contrast shower usually consists of three to five complete cycles of hot and cold water. The hot water causes blood vessels to dilate, thereby pushing the blood to the skin’s surface, and cold water … Continue reading Four benefits of Contrast Hydrotherapy

Davide LiuLeave a comment
Experiences, Spartan Race

How I got top 5 in an Elite Beast Spartan Race

In this post, I’m going to talk about how I trained for my first Elite Beast Spartan Race and share my views and observations of it. It was my second Spartan Beast race ever and the first one in the Elite category. The race was held in Beijing in late October of 2021 when temperatures start to get chilly signaling a strong transition from autumn … Continue reading How I got top 5 in an Elite Beast Spartan Race

Davide LiuLeave a comment
Machine Learning, Reinforcement Learning

Visualizing Loss Landscape of GAIL

This post aims to visualize the loss landscape of some imitation policies (IL policies) trained with GAIL, and their discriminator trained in three common environments: Cartpole, Lunarlander, and Walker2d from Mujoco. The expert policy of Cartpole and Lunarlander is a simple Double DQN while the expert of Walker2d, which supports continuous actions, is a DDPG policy. The imitation policies are the same policies employed by their … Continue reading Visualizing Loss Landscape of GAIL

Davide Liu3 Comments
Machine Learning, Reinforcement Learning

Learning to imitate: using GAIL to imitate PPO

Usually, in reinforcement learning, the agent is provided with a reward according to the action it executes to interact with the environment and its goal is to optimize its total cumulative reward over multiple steps. Actions are selected according to some observations the agent has to learn to interpret. In this post, we are going to explore a new field called imitation learning: the agent … Continue reading Learning to imitate: using GAIL to imitate PPO

Davide Liu2 Comments
Experiences, Spartan Race

How I got top 10 in an Elite Super Spartan Race

The purpose of my previous Spartan Race was more to feel how a Spartan Super looks like rather than throwing myself into the real competition and I didn’t prepare it without pursuing any specific goal. However, for this second Elite race I aimed at finishing it inside the top 10. In this post, I’m going to share my impressions and my preparation plan for my … Continue reading How I got top 10 in an Elite Super Spartan Race

Davide LiuLeave a comment