deepcontext | Unsupervised Visual Representation Learning by Context

by cdoersch Python Version: Current License: MIT

X-Ray Key Features Code Snippets Community Discussions Vulnerabilities Install Support

kandi X-RAY | deepcontext Summary

deepcontext is a Python library. deepcontext has no bugs, it has no vulnerabilities, it has a Permissive License and it has low support. However deepcontext build file is not available. You can download it from GitHub.

This code is designed to train a visual representation from a raw, unlabeled image collection. The resulting representation seems to be useful for standard vision tasks like object detection, surface normal estimation, and visual data mining. This algorithm was originally described in Unsupervised Visual Representation Learning by Context Prediction, which was presented at ICCV 2015. This code is significantly refactored from what was used to produce the results in the paper, and minor modifications have been made. While I do not expect these modifications to significantly impact results, I have not yet fully tested the new codebase, and will need a few more weeks to do so. Qualitative behavior early in the training on appears to be equivalent, but you should still use this code with caution.

Support

Quality

Security

License

Reuse

Support

deepcontext has a low active ecosystem.

It has 104 star(s) with 38 fork(s). There are 12 watchers for this library.

It had no major release in the last 6 months.

There are 1 open issues and 0 have been closed. On average issues are closed in 307 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of deepcontext is current.

Quality

deepcontext has 0 bugs and 0 code smells.

Security

deepcontext has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

deepcontext code analysis shows 0 unresolved vulnerabilities.

There are 0 security hotspots that need review.

License

deepcontext is licensed under the MIT License. This license is Permissive.

Permissive licenses have the least restrictions, and you can use them in most projects.

Reuse

deepcontext releases are not available. You will need to build from source code and install.

deepcontext has no build file. You will be need to create the build yourself to build the component from source.

Installation instructions, examples and code snippets are available.

deepcontext saves you 200 person hours of effort in developing the same functionality from scratch.

It has 492 lines of code, 20 functions and 3 files.

It has low code complexity. Code complexity directly impacts maintainability of the code.

Top functions reviewed by kandi - BETA

kandi has reviewed deepcontext and discovered the below as its top functions. This is intended to give you an instant insight into deepcontext implemented functionality, and help decide if they suit your requirements.

Generate network
R Convolutional convolution layer
Stack 2d tensorstack
Create a layer - wise inner product
Set the value of an attribute
Construct a max pooling
Generate an image loader
Get a resized image
Sample a single patch
Convert a position to a label
Retrieve an image
Wrapper for mkorender
Render a template file
Return the filename of the file
Loads the imageset
Creates a mkorender

Get all kandi verified functions for this library.

deepcontext Key Features

No Key Features are available at this moment for deepcontext.

deepcontext Examples and Code Snippets

No Code Snippets are available at this moment for deepcontext.

Community Discussions

No Community Discussions are available at this moment for deepcontext.Refer to stack overflow page for discussions.

Community Discussions, Code Snippets contain sources that include Stack Exchange Network

Vulnerabilities

No vulnerabilities reported

Install deepcontext

Build Caffe and pycaffe. External caffe installations should work as well, but need to be downloaded from Github later than November 22, 2015 to support all required features. Copy deepcontext_config.py.example to deepcontext_config.pyand edit it to supply your path to ImageNet, and provide an output directory that the code can use for temporary files, including snapshots.
Clone the deepcontext repository
Build Caffe and pycaffe cd $DEEPCONTEXT_ROOT/caffe_ext # Now follow the Caffe installation instructions here: # http://caffe.berkeleyvision.org/installation.html # If you're experienced with Caffe and have all of the requirements installed # and your Makefile.config in place, then simply do: make -j8 && make pycaffe External caffe installations should work as well, but need to be downloaded from Github later than November 22, 2015 to support all required features.
Copy deepcontext_config.py.example to deepcontext_config.pyand edit it to supply your path to ImageNet, and provide an output directory that the code can use for temporary files, including snapshots.

Support

For any new features, suggestions and bugs create an issue on GitHub. If you have any questions check and ask questions on community page Stack Overflow .

Find more information at: