Nico Jahn's repositories
open-neural-apc
This repository contains my original implementation of an RNN-based APC (Automated Passenger Counting) system.
adversarial.js
Break neural networks in your browser 🦹♂️
amazon-sagemaker-examples
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
EPFD
Paper: Ensemble Pruning Based on Objection Maximization With a General Distributed Framework
EPFD-pipeline
The pipeline wrapper for the EPDF framework
charts
Helm Charts
cluster-api-control-plane-provider-talos
A control plane provider for CAPI + Talos
contrastive-unpaired-translation
Contrastive unpaired image-to-image translation, faster and lighter training than cyclegan (ECCV 2020, in PyTorch)
Determining-the-Relevance-of-Features-for-Deep-Neural-Networks
WIP: Implementation of "Determining the Relevance of Features for Deep Neural Networks" by Reimers et al. (2020)
flatten-dict
A flexible utility for flattening and unflattening dict-like objects in Python.
hyper-scale-tensorflow-with-minio
Hyper-Scale Machine Learning with MinIO and TensorFlow
java_genetic_algorithm
My old solution of creating a (poor) genetic algorithm in java
jupyterhub-ssh
SSH Access to JupyterHubs
kubernetes
Production-Grade Container Scheduling and Management
MooneyFaceGenerator
A Deep Learned Model for Generate Mooney Faces from Photos
openml-docker-dev
Docker compose for starting local OpenML instances
pyblur3
blurring routines
pymooney
This repository helds the python scripts to generate twotone, Mooney images. You can use search words that will be used to search images with these search words in online image databases and the Mooney images will be generated based on these images. Or you can give a path with images.
spectrocloud-problems
Fixed with terraform provider version 0.14.0-pre. Used for bug report
tdengine-problems
Fixed with after getting support. Used for bug report
tensorflow
An Open Source Machine Learning Framework for Everyone
terraform
Terraform enables you to safely and predictably create, change, and improve infrastructure. It is a source-available tool that codifies APIs into declarative configuration files that can be shared amongst team members, treated as code, edited, reviewed, and versioned.
the-algorithm
Source code for Twitter's Recommendation Algorithm
YOLOX
YOLOX is a high-performance anchor-free YOLO, exceeding yolov3~v5 with MegEngine, ONNX, TensorRT, ncnn, and OpenVINO supported. Documentation: https://yolox.readthedocs.io/