magic_init
Data initialization method
This code provides an initialization method for convolutional neural networks based on data-dependent parameters.
138 stars
8 watching
47 forks
Language: Python
last commit: about 8 years ago
Linked from 1 awesome list
michaelxin/awesome-caffeRelated projects:
| Repository | Description | Stars |
|---|---|---|
 alykhantejani/nninit | Provides weight initialization schemes for PyTorch neural networks | 70 |
 ducha-aiki/lsuvinit | Implementation of a method to initialize neural network layers in a deep learning framework. | 112 |
 nlprinceton/alacarte | Tools and code for inducing custom semantic vector representations from text data | 104 |
 kaixhin/nninit | Provides parameter initialisation schemes for neural network modules in Torch7 | 100 |
 aria42/infer | A Clojure-based library for building machine learning and statistical models in a flexible and composable way. | 176 |
 ujjwalkarn/datasciencepython | A curated list of tutorials and resources for learning Python for data science, machine learning, and other related topics. | 5,276 |
 nethermindeth/entro | Interacts with blockchains using Python | 24 |
 albermax/innvestigate | A toolbox to help understand neural networks' predictions by providing different analysis methods and a common interface. | 1,268 |
 fgxaos/pytorch-innvestigate | PyTorch implementation of an explainability technique for deep neural networks | 9 |
 sergioburdisso/pyss3 | A Python package implementing an interpretable machine learning model for text classification with visualization tools | 336 |
 ryuk17/machinelearning | This is a collection of machine learning algorithms implemented in Python 3.6. | 103 |
 claws-lab/jodie | A PyTorch implementation of a representation learning framework for dynamic temporal networks | 355 |
 nationalgenomicsinfrastructure/icing | An approach to analyzing OxfordNanopore reads for HLA typing using Python | 13 |
 ernw/binja-ipython | Creates an IPython kernel integrated with Binary Ninja for interactive Python debugging and analysis | 29 |
 pylons/colander | A library for serializing and deserializing data structures into strings, mappings, and lists while performing validation. | 451 |