This is a repository that contains information on loading and using datasets in PyTorch, Tensorflow and Sklearn. The datasets are divided by modality, as shown below in "List of Datasets".
Each dataset has its own Jupyter Notebook with loading instructions, number of train and test samples, and plotted examples.
The author is responsible for the content and quality of the code. Please refer to The Learning Machine (thelearningmachine.ai) for any remarks.
- MNIST
- FashionMNIST
- CIFAR-10 and 100
- GLUE Benchmark: 11 NLP tasks
- WMT: Machine Translation
- Iris dataset