Light

servicenow / tadam Goto Github PK

The implementation of https://papers.nips.cc/paper/7352-tadam-task-dependent-adaptive-metric-for-improved-few-shot-learning . TADAM is a ServiceNow Research project that was started at Element AI.

License: Apache License 2.0

Python 34.10% Dockerfile 0.54% TeX 29.65% Jupyter Notebook 35.71%

tadam's Introduction

ServiceNow completed its acquisition of Element AI on January 8, 2021. All references to Element AI in the materials that are part of this project should refer to ServiceNow.

TADAM

Set up docker

go to folder docker in this project, execute docker build -f Dockerfile -t boris_tadam .

launch docker

NV_GPU=0 nvidia-docker run -p 1250:8888 -p 1251:6006 -p 1252:6007 -p 1253:6008 -v /mnt/datasets/public/:/mnt/datasets/public/ -v /mnt/home/boris:/mnt/home/boris -t -d --name boris_tadam_explore boris_tadam

iPython session should be available at http://machine_ip:1250/, password is "default". Datasets are mapped inside docker in /mnt/datasets/public/ folder.

tadam's People

Contributors

Stargazers

Watchers

tadam's Issues

question about alpha

Alpha is learnable in the paper, but inside the code
"Flags.metric_multiplier_trainable=False" means that alpha is a fixed value. Could you tell me why?

paper detail

how do you get the post-multipliers γ0 and β0, by training or set by hand.

BatchNorm's scale/center not turned off before FiLM layers

I might be missing something, but shouldn't the slim.conv2d() layers before FiLM layers have their scaling/centering turned off, such that only FiLM gammas/betas are used for CBN?

_get_scope_film() creates a scope that turns it off, but is not used in the code.

See:
https://github.com/ElementAI/TADAM/blob/476b024e08977143a01ed6b2fe7e479efa587197/model/tadam.py#L346

Some questions about ResNet.

It is a really nice job! We tried to use resnet as a backbone just like what you did in our own experiment. However, it didn't improve performance as we expected and even performed worse than 4-conv. I wonder if there are some tricks when you trained your model with a resnet. Thank you very much.

Recommend Projects

React

A declarative, efficient, and flexible JavaScript library for building user interfaces.
Vue.js

🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
Typescript

TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
TensorFlow

An Open Source Machine Learning Framework for Everyone
Django

The Web framework for perfectionists with deadlines.
Laravel

A PHP framework for web artisans
D3

Bring data to life with SVG, Canvas and HTML. 📊📈🎉

Recommend Topics

javascript

JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
web

Some thing interesting about web. New door for the world.
server

A server is a program made to process requests and deliver data to clients.
Machine learning

Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Visualization

Some thing interesting about visualization, use data art
Game

Some thing interesting about game, make everyone happy.

Recommend Org

Facebook

We are working to build community through open source technology. NB: members must have two-factor auth.
Microsoft

Open source projects and samples from Microsoft.
Google

Google ❤️ Open Source for everyone.
Alibaba

Alibaba Open Source for everyone
D3

Data-Driven Documents codes.
Tencent

China tencent open source team.