
Ports a paper's CV training recipe to your own dataset and checks for silent bugs
- Open source
- 4K GitHub stars
- Computer vision

Ports a paper's CV training recipe to your own dataset and checks for silent bugs

Guides an agent in porting cuTile Python GPU kernels to Julia cuTile.jl

Guides an agent in converting cuTile GPU kernels to Triton and debugging the result

Adds autotuning with cached config selection to CuTile GPU kernels

Guides an agent to write, debug and validate cuTile GPU kernels in Python

Composes and deploys an NVIDIA VSS vision stack with captioning, detection, search

Diagnoses and cuts cold-start compile time in Warp GPU code without changing results

Guides an agent through GPU DataFrame work with NVIDIA cuDF and dask-cuDF

Guides an agent through customizing NVIDIA's Nemotron Voice Agent for healthcare intake

Calibrates camera extrinsics from live RTSP streams via the AutoMagicCalib REST API

Calibrates multi-camera MP4 recordings through the AutoMagicCalib REST API

Validates coding-sequence CSVs and extracts frozen CodonFM embeddings for mRNA modeling

Fine-tunes public CodonFM Encodon checkpoints on labeled coding-sequence data

Scores existing PDB design files with refolding and interface or motif metrics

Runs and ranks cartesian-product parameter sweeps for Proteina-Complexa protein design

Guides building and debugging cuEquivariance PyTorch tensor products and equivariant GNNs

Generates DNA sequences with NVIDIA's Evo 2 model and extracts local layer outputs

Converts a GROVER checkpoint into a hybrid cMIM model and continues pretraining it

Continues KERMT molecular pretraining on a custom SMILES corpus inside a GPU container

Extracts per-molecule embeddings from KERMT checkpoints in a containerized GPU run

Finetunes a pretrained KERMT molecular encoder on your labeled SMILES CSV in Docker

Runs predictions with a finetuned KERMT checkpoint on a SMILES-only CSV

Pretrains a KERMT molecular model from scratch on your own SMILES corpus

Sets up a Docker and GPU environment for KERMT and verifies it runs on the GPU

Generates protein multiple sequence alignments and templates via the ColabFold MSA-Search

Guides NVIDIA Parabricks pbrun command planning, option translation and runtime checks

Designs protein sequences for a backbone PDB using ProteinMPNN via NVIDIA NIM

Runs RFD4-Proteina to generate protein structures and sequences via NVIDIA API or local

Generates synthetic PCB inspection images with defects on Kubernetes via a DAG

Runs an NVIDIA pipeline that turns seed images into anomaly video clips and datasets