tfds

Emoji Drawings dataset

Load common open-source electrocardiogram databases as a tensorflow dataset

Convert ManiSkill HDF5 demonstration trajectories to RLDS / TFDS format for robot learning and VLA data pipelines.

This repository is a modified fork of the official Octo project.It extends the original Octo codebase with tools for adapting Octo to ManiSkill simulation tasks, including ManiSkill-to-RLDS data conversion, Octo fine-tuning scripts, and ManiSkill-based evaluation utilities.

This project focuses on classifying images from the CIFAR-10 dataset using deep learning models. A custom CNN is built with TensorFlow, and transfer learning is applied using ResNet18 with PyTorch for improved performance. Data preprocessing and augmentation techniques are used to enhance model generalization.

Loading, inspecting, and preprocessing datasets using TensorFlow Datasets (TFDS). Demonstrates train/test split handling, image normalization, batching, shuffling, caching, and visualization to build efficient, ready-to-train deep learning pipelines.

Demo of data augmentation: a technique to increase the diversity of your training set by applying random (but realistic) transformations, such as image rotation

This repo consists a Python Notebook file where I have performed transfer learning using Keras Xception Transformer.