There are 2 repositories under tpu-acceleration topic.
CodeGen is a family of open-source model for program synthesis. Trained on TPU-v4. Competitive with OpenAI Codex.
Dual Edge TPU Adapter to use it on a system with single PCIe port on m.2 A/B/E/M slot
Small-scale Tensor Processing Unit built on an FPGA
Community gathering point for Google Coral dev board and dongle knowledge.
FREE TPU V3plus for FPGA is the free version of a commercial AI processor (EEP-TPU) for Deep Learning EDGE Inference
Implements sharpness-aware minimization (https://arxiv.org/abs/2010.01412) in TensorFlow 2.
Object and face recognition using Google's edge TPU
TensorFlow Lite Erlang bindings with optional EdgeTPU support.
Website for Eclipse ioFog, a distributed Edge Compute Network (ECN) platform
Track how multiple objects of type(s) you specify are moving through the field of vision.
Collection of machine learning related notebooks to share.
TPU에서 한국어용 LLM 추론을 위한 Jax/Flax 구현체입니다.
:3rd_place_medal: (Bronze medal - 241st place - Top 8%) Repository for the "SIIM-ISIC Melanoma Classification" Kaggle competition.
m.2 B+M Coral TPU card for Raspberry Pi CM4
Real time object detection with Raspberry Pi, Google Edge TPU and Python
Semi/Self-Supervised Learning on a Pediatric Pneumonia Dataset
An application of realtime object-detection running on an Edge TPU for making cycling in busy cities a little less terrifying.
Switching from GPU to the future of Machine learning the TPU. Over 1 million images trained Resnet50 in under 20 mins compared to days or weeks on GPU and all for 0$ free on Google Colab Notebooks in Google Drive, clone repo and jump right in!!
A much-needed implementation of a bi-directional MIDI processor for symbolic music generation with NLP based Music AI architectures.
Created an algorithm to identify metastatic cancer in small image patches taken from larger digital pathology scans. The data used for this competition is a slightly modified version of the PatchCamelyon (PCam) benchmark dataset.
Webstreaming classification with Google edge TPU on the picamera and balenaFin
WaveGLow -- A Flow-based Generative Network for Speech Synthesis . PyTorch Code modified to run on TPUs .
Implementation of famous Optic disc and cup segmentation research papers in python.
This work focuses on the development of machine learning models, in particular neural networks and SVM, where they can detect toxicity in comments. The topics we will be dealing with: a) Cost-sensitive learning, b) Class imbalance
A collection of deep learning exercises collected while completing an Intro to Deep Learning course. We use TensorFlow and Keras to build and train neural networks for structured data.
Official code for the paper "VoloGAN: Adversarial Domain Adaptation for Synthetic Depth Data"
Semi/Self-Supervised Learning on a Pediatric Pneumonia Dataset
Identify melanoma in lesion images using CNN
Shopee Code League 2020 image competition 7th place solution