https://github.com/robmarkcole/gvision-analyzer

Perform analysis on images and videos using Google Vision
https://github.com/robmarkcole/gvision-analyzer

Last synced: 5 months ago
JSON representation

Perform analysis on images and videos using Google Vision

• Host: GitHub
• URL: https://github.com/robmarkcole/gvision-analyzer
• Owner: robmarkcole
• License: apache-2.0
• Created: 2019-10-31T06:02:52.000Z (over 6 years ago)
• Default Branch: master
• Last Pushed: 2019-10-31T07:16:15.000Z (over 6 years ago)
• Last Synced: 2025-03-25T00:07:48.502Z (about 1 year ago)
• Size: 7.81 KB
• Stars: 1
• Watchers: 2
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: README.md
  • License: LICENSE

Awesome Lists containing this project

README

          
# gvision-analyzer

Perform analysis on images and videos using Google Vision. Using Google Vision means we get fast processing without requiring a GPU. 5000 calls to the API for free per month, low cost after.

* Helper functions and example notebooks for analysis

* Docker environment -> https://github.com/jupyter/docker-stacks/tree/master/scipy-notebook + `requirements.txt`

* Use Jupyter as IDE [following fastai2 example](https://forums.fast.ai/t/fastai-v2-roadmap/46661?u=xyz)

* Strealit (most likely) or Voila/Bokeh/Plot.ly for UI for reviewing analysis (TBC)

* Make pragmatic choices that minimise moving parts, e.g. sqlite over a server solution