Here's a small set of resources that I would like to share with the group.

1. Jupyter Notebooks (around 20) on pytorch - a set of tutorials: https://github.com/Tessellate-Imaging/Pytorch_Tutorial
Notebooks on
Crucial tensor functions
Data Loaders
Layers, activations, optimizers, initializers and losses
Classification examples and transfer learning

2. OpenSource Transfer learning library Monk: https://github.com/Tessellate-Imaging/monk_v1
Monk features
low-code
unified wrapper over major deep learning framework - keras, pytorch, gluoncv
syntax invariant wrapper
Enables
to create, manage and version control deep learning experiments
to compare experiments across training metrics
to quickly find best hyper-parameters
At present it only supports transfer learning, but we are working each day to incorporate
various object detection and segmentation algorithms
deployment pipelines to cloud and local platforms
acceleration libraries such as TensorRT
preprocessing and post processing libraries

3. Jupyter Notebooks blog series on Monk-Pytorch - Building classification applications: https://medium.com/@monkai.betasignup
American sign language classification
Leaf Disease Classification
Food Classification
Indoor Scene Classification
Fashion Classification

P.S - Inviting computer vision enthusiats to contribute to Monk tool.

Keep Learning!!!

Posted by uniqueone
,