機械学習 · GitHub

LoRA (Low-Rank Adaptation) inspector for Stable Diffusion

DataFrames for Go: For statistics, machine-learning, and data manipulation/exploration

• Importing from CSV, JSONL, Parquet, MySQL & PostgreSQL
• Exporting to CSV, JSONL, Excel, Parquet, MySQL & PostgreSQL

Deep Learning NLP Pipeline implemented on Tensorflow

AMD MIVisionX is a computer vision toolkit built around a highly optimized, conformant open-source implementation of the Khronos OpenVX™ 1.3.2 specification. As of the 4.0.0 release, MIVisionX ships three components: the AMD OpenVX™ engine, the AMD RPP OpenVX extension, and the RunVX graph executor — across CPU, HIP, and OpenCL backends.

A fully functional and simple Machine Learning library made entirely from scratch with Python.

• Automatic Differentiation (Value): A simple autograd engine that tracks operations and computes gradients automatically. (See smolml/core/value.py)
• N-dimensional Arrays (MLArray): A custom array implementation inspired by NumPy (though simplified), supporting common mathematical operations needed for ML. Extremely inefficient due to being written in Python, but ideal for understanding N-Dimensional Arrays, one of the most underrated skills of a ML engineer. (See smolml/core/ml_array.py)

The full collection of all codes for my Youtube Channel segregated as per topic.

DeepCatch: performance-weighted multi-modal fusion for ultra-early cfDNA cancer detection. Fragmentomics, methylation, sequence.

Easily compute clip embeddings and build a clip retrieval system with them

Easily turn large sets of image urls to an image dataset. Can download, resize and package 100M urls in 20h on one machine.

📖 A curated list of awesome resources dedicated to Relation Extraction, one of the most important tasks in Natural Language Processing (NLP).

Machine learning in Clojure