PyTorch is a Python package that provides two high-level features: Tensor computation (like NumPy) with strong GPU acceleration Deep neural networks built on a tape-based autograd system You can reuse your favorite Python packages such as NumPy, SciPy, and Cython to extend PyTorch when needed. See also the ci.pytorch.org HUD. More About PyTorch At a granular level, PyTorch is a library that consists of the following components: Component Description torch a Tensor library like NumPy, with strong GPU support torch.autograd […]

This repository presents an implementation of the Wav2Vec2 model [1] in TensorFlow 2.0 as a part of Google Summer of Code. For a quick demo, please check out this. Final report of the project can be found here. Notebooks The repository comes with shiny Colab Notebooks. Below you can find a list of them. Spin them up and don’t forget to have fun! Checkpoints Below is a summary of checkpoints obtained during the project: To know more about the process […]

deep_autoviml Build keras pipelines and models in a single line of code! Build tensorflow keras model pipelines in a single line of code. Created by Ram Seshadri. Collaborators welcome. Permission granted upon request. Motivation ✨ deep_autoviml is a powerful new deep learning library with a very simple design goal: ✨ Make it as easy as possible for novices and experts alike to experiment with and build tensorflow.keras preprocessing pipelines and models in as few lines of code as possible. Watch […]

MIRNet Tensorflow implementation of the MIRNet architecture as proposed by Learning Enriched Features for Real Image Restoration and Enhancement. Pre-trained Weights Citation @misc{ 2003.06792, Author = {Syed Waqas Zamir and Aditya Arora and Salman Khan and Munawar Hayat and Fahad Shahbaz Khan and Ming-Hsuan Yang and Ling Shao}, Title = {Learning Enriched Features for Real Image Restoration and Enhancement}, Year = {2020}, Eprint = {arXiv:2003.06792}, } GitHub https://github.com/soumik12345/MIRNet    

Raspberry-Pi-TF-Lite-Object-Detection Using TensorFlow Lite with Python is great for embedded devices based on Linux, such as Raspberry Pi. This is the guide for installing TensorFlow Lite on the Raspberry Pi and running pre-trained object detection models on it. Step 1. Setting up Rasperry Pi Upgrade Raspbian Stretch to Buster (If you on Buster, skip this step and simply run sudo apt-get update and sudo apt-get dist-upgrade) $ sudo apt-get update && sudo apt-get upgrade -y Verify nothing is wrong. Verify […]

PAWS-TF Implementation of Semi-Supervised Learning of Visual Features by Non-Parametrically Predicting View Assignments with Support Samples (PAWS) in TensorFlow (2.4.1). PAWS introduces a simple way to combine a very small fraction of labeled data with a comparatively larger corpus of unlabeled data during pre-training. With its approach, it sets the state-of-the-art in semi-supervised learning (as of May 2021) beating methods like SimCLRV2, Meta Pseudo Labels that too with fewer parameters and a smaller pre-training schedule. For details, I recommend checking […]

MNIST_AttentionMap [TensorFlow] Attention mechanism with MNIST dataset Usage $ python run.py Result Training Loss graph. Test Each figure shows input digit, attention map, and overlapped image sequentially. Further usage The further usages. Detecting the location of digits can be conducted using an attention map. Requirements TensorFlow 2.3.0 Numpy 1.18.5 GitHub https://github.com/YeongHyeon/MNIST_AttentionMap