Phil's repositories
contiguous_pytorch_params
Accelerate training by storing parameters in one contiguous chunk of memory.
freiburg_groceries_dataset
Freiburg Groceries Dataset
tf-quaternion
An implementation of quaternions for and written in tensorflow. Fully differentiable.
generalize_spatial_relations
Code for the paper "Optimization Beyond the Convolution: Generalizing Spatial Relations with End-to-End Metric Learning" (ICRA 2018)
squeeze_excitation
Experiments on squeeze and excitation networks for the bio-medical image analysis seminar.
thesis-template
A latex template for writing a Bachelor/Master thesis. (mirror of https://git.fachschaft.tf/fachschaft-public/thesis-template)
accelerate
🚀 A simple way to train and use PyTorch models with multi-GPU, TPU, mixed-precision
AdamW_benchmark
Benchmark for optimizers with decoupled weight decay.
FlashAttention20Triton
Annotated Triton implementation of Flash Attention2.0
nanoGPT
The simplest, fastest repository for training/finetuning medium-sized GPTs.
Open-Assistant
OpenAssistant is a chat-based assistant that understands tasks, can interact with third-party systems, and retrieve information dynamically to do so.
philjd.github.io
https://philjd.github.io
pytorch-lightning
The lightweight PyTorch wrapper for ML researchers. Scale your models. Write less boilerplate
secr
Spatially Explicit Capture-Recapture
segmentation_models
Segmentation models with pretrained backbones. Keras.
tensorflow
Development fork.
transformers
🤗 Transformers: State-of-the-art Machine Learning for Pytorch, TensorFlow, and JAX.