ML | Time Series
Conda env is built as, 12345678910micromamba env create -n MLmicromamba activate MLmicromamba install python==3.10micromamba install pytorch torchvision torchaudio pytorch-cuda=12.4 -c pytorch -c nvid
ML | stable-video-diffusion-img2vid-xt
stable-video-diffusion-img2vid-xt Stable Video Diffusion (SVD) Image-to-Video is a diffusion model that takes in a still image as a conditioning frame, and generates a video from it. Stable Video Diff
ML | stable-diffusion
stable-diffusion-xl-base-1.0 https://huggingface.co/stabilityai/stable-diffusion-xl-base-1.0 The stable-diffusion-xl-base-1.0 is a text-to-image generative model developed by Stability AI. Inputs
ML | huggingface
Conda env 123456789# check CUDA Version:$ nvidia-smimicromamba env create -n huggingfacemicromamba activate huggingface micromamba install python==3.10micromamba install pytorch torchvision torchaudio
ML | Scaling Law
Scaling Law In machine learning, a neural scaling law is an empirical scaling law that describes how neural network performance changes as key factors are scaled up or down. These factors typically in
ML | GPU Memory for ML model
GPU Memory you need to serve any ML models System Memory (RAM) is not ideal for this purpose because it is slower than GPU memory. GPU memory, also known as VRAM (Video Memory) or GDDR (Graphics DDR),
CFD | Boussinesq approximation (buoyancy)
Boussinesq approximation (buoyancy) In fluid dynamics, the Boussinesq approximation is used in the field of buoyancy-driven flow (also known as natural convection). It ignores density differences exce
ML | PINN | DeepXDE
DeepXDE DeepXDE 是一款开源且高度模块化的科学计算工具，以深度学习为核心，提供多种数据、物理机理及数理融合的模型，如PINN、DeepONet、MFNN等，同时支持多种类型微分方程，如常微分方程、偏微分方程的定义及求解，可有效解决复杂科学计算问题。 基于所提供的深度学习求解模型，DeepXDE具备以下典型的功能特点： 高度模块化：DeepXDE提供多种支持调用、组合的模块，如计算域
