Giter Site home page Giter Site logo

lucasdmarten / im2txt_demo Goto Github PK

View Code? Open in Web Editor NEW

This project forked from siavashcsr/im2txt_demo

0.0 1.0 0.0 3.93 MB

im2txt + pretrained models + docker = easy tryout

Shell 3.48% Python 93.07% Makefile 0.28% Dockerfile 0.36% Starlark 2.81%

im2txt_demo's Introduction

im2txt_demo

im2txt + pretrained models + docker = easy tryout

This repo contains a copy of im2txt (https://github.com/tensorflow/models/tree/master/im2txt), a suitable docker image, pretrained models (tensorflow/models#466) and some trivial shell scripts for convenience.

Limitations:

  • The command "git lfs pull" might respond with errors, due to the limited GitHub data quota:
batch response: This repository is over its data quota. Purchase more data packs to restore access. 

In this case you can

  • wait until next month and hope you can perform "git lfs pull" before the data limit is reached OR
  • use the following links to the pretrained models and download them manually: https://drive.google.com/file/d/0Bw6m_66JSYLlRFVKQ2tGcUJaWjA/view
  • Copy the file model.ckpt-2000000 to the folder im2txt_pretrained. It should have a size of 143 mb.

The tensorflow version is fixed to an old one (0.12). Feel free to update and create a pull request! Thanks in Advance for your help!

Getting started:

Install docker (skip if already installed)

https://docs.docker.com/engine/installation/

Install git lfs (skip if already installed)

https://help.github.com/articles/installing-git-large-file-storage/

Clone this repo and pull large files (pretrained models):

git clone https://github.com/siavash9000/im2txt_demo.git
cd im2txt_demo
git lfs pull

build docker image

cd im2txt_demo
make build
start container
make run
run build_inference to prepare inference step (must be performed only once)
./build_inference.sh
get caption for image
./process_image.sh imgs/bikes.jpg

im2txt_demo's People

Contributors

andrewb-ms avatar mmattozzi avatar siavash9000 avatar valentinvieriu avatar

Watchers

 avatar

Recommend Projects

  • React photo React

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

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

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

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

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.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

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

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.