Versions
Description
ProjektDepth: A DNN for segmentation and depth estimation. The entire dataset was created from scraping images, augmenting them to finally create a dataset of 1.2B images. The DNN was custom made inspired from Resnet and Unet architecture, various loss functions and their combinations were tried on the model. LRFinder was used to find the best or for the model. The model was trained on Colab with a P100, experiments were done on TPU. The vathos package contains the runner, trainer, model, loss, and the notebooks. Everything is documented and added to readthedocs.
Repository
https://github.com/satyajitghana/ProjektDepth.git
Project Slug
projektdepth
Last Built
3 years, 5 months ago passed
Maintainers
Home Page
https://github.com/satyajitghana/ProjektDepth
Badge
Tags
deep-learning, depth-estimation, pytorch
Short URLs
projektdepth.readthedocs.io
projektdepth.rtfd.io
Default Version
latest
'latest' Version
master