deepvision
awesome-modular-pytorch-lightning
deepvision | awesome-modular-pytorch-lightning | |
---|---|---|
1 | 1 | |
30 | 20 | |
- | - | |
5.1 | 0.0 | |
11 months ago | over 1 year ago | |
Python | Python | |
Apache License 2.0 | GNU General Public License v3.0 only |
Stars - the number of stars that a project has on GitHub. Growth - month over month growth in stars.
Activity is a relative number indicating how actively a project is being developed. Recent commits have higher weight than older ones.
For example, an activity of 9.0 indicates that a project is amongst the top 10% of the most actively developed projects that we are tracking.
deepvision
-
PyTorch/TensorFlow image models with automatic weight conversions
Link: https://github.com/DavidLandup0/deepvision
awesome-modular-pytorch-lightning
-
[D] What do you think about these experiments on the HUGE effect of learning rate on overfitting?
More detail can be found in https://github.com/kuangliu/pytorch-cifar or the actual personal repo used for running experiments.
What are some alternatives?
pytorch2keras - PyTorch to Keras model convertor
open-metric-learning - Library for metric learning pipelines and models.
SHREC2023-ANIMAR - Source codes of team TikTorch (1st place solution) for track 2 and 3 of the SHREC2023 Challenge
so-vits-svc-fork - so-vits-svc fork with realtime support, improved interface and more features.
Open3D-ML - An extension of Open3D to address 3D Machine Learning tasks
lightning-flash - Your PyTorch AI Factory - Flash enables you to easily configure and run complex AI recipes for over 15 tasks across 7 data domains
datasets - 🤗 The largest hub of ready-to-use datasets for ML models with fast, easy-to-use and efficient data manipulation tools
lightning-hydra-template - PyTorch Lightning + Hydra. A very user-friendly template for ML experimentation. ⚡🔥⚡
Efficient-AI-Backbones - Efficient AI Backbones including GhostNet, TNT and MLP, developed by Huawei Noah's Ark Lab.
pytorch-forecasting - Time series forecasting with PyTorch
dream-creator - Quickly and easily create / train a custom DeepDream model
pytorch-cifar - 95.47% on CIFAR10 with PyTorch