https://github.com/lc0/deeplearning-playground

Experiments and ideas in notebooks🤖💻
https://github.com/lc0/deeplearning-playground

playground tensorflow

Last synced: over 1 year ago
JSON representation

Experiments and ideas in notebooks🤖💻

• Host: GitHub
• URL: https://github.com/lc0/deeplearning-playground
• Owner: lc0
• Created: 2017-08-06T21:40:43.000Z (almost 9 years ago)
• Default Branch: master
• Last Pushed: 2020-11-12T15:09:22.000Z (over 5 years ago)
• Last Synced: 2025-02-10T02:36:03.510Z (over 1 year ago)
• Topics: playground, tensorflow
• Language: Jupyter Notebook
• Homepage:
• Size: 27 MB
• Stars: 0
• Watchers: 2
• Forks: 2
• Open Issues: 0
• Metadata Files:
  • Readme: readme.md

Awesome Lists containing this project

README

          
# Experiments and examples

A bunch of different code notebooks of experiments and explorations. Should be `python3` with a big number of TensorFlow ones

## Experiments

- Loading TIFF images with TensorFlow - [link](TF2/tf2_tiff_images_dataset_pipeline.ipynb)

    * Example of a custom function to load an image with PIL

    * using [tensorflow_io](https://github.com/tensorflow/io) to load an image with `TIFFDataset`

- TFHub activity recognition from mp4 video.

In the example, the video of Olympic Weightlifting activity is used, a squat clean to be more precise - [link](Working_with_Video_and_tfhub_activity_recognition.ipynb)

    * TFhub activity recognition - unfortunately only TF1.x

    * `tensorflow_io` and `VideoDataset`

![alt text](images/oly-clean.gif "Oly Squat CLean")