Abay Bektursun's repositories
why-batchNorm-works
Source Code For: Why Does Batch Normalization Work?
multi-agent-pomm
(Under development)
austin-deep-learning-meetup
Deep Learning Meetup in Austin, TX
backprop_android
I am writing backprop on my Android Phone while watching The Office
Comp_Neuroscience_UoW
Computational Neuroscience by University of Washington
cs344
Introduction to Parallel Programming class code
differentiable-plasticity
Implementations of the algorithms described in Differentiable plasticity: training plastic networks with gradient descent, a research paper from Uber AI Labs.
dumb_time_tracker
Why tf is it so hard to find a simple working time tracker?
FashionFormer
Code for our ECCV-2022 work: Fashionformer A simple, effective and unified baseline for human fashion segmentation and recognition
openpose-plus
High-Performance and Flexible Pose Estimation Framework using TensorFlow, OpenPose and TensorRT
PyramidBox
A Context-assisted Single Shot Face Detector in TensorFlow
recurrent-entity-networks
TensorFlow implementation of "Tracking the World State with Recurrent Entity Networks".
RWKV-LM
RWKV is an RNN with transformer-level LLM performance. It can be directly trained like a GPT (parallelizable). So it's combining the best of RNN and transformer - great performance, fast inference, saves VRAM, fast training, "infinite" ctx_len, and free sentence embedding.