latent-noise-icnm | Code for CVPR 2016 paper on Learning from Noisy Labels

by imisra HTML Version: Current License: No License

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

kandi X-RAY | latent-noise-icnm Summary

latent-noise-icnm is a HTML library. latent-noise-icnm has no bugs, it has no vulnerabilities and it has low support. You can download it from GitHub.

Our code base is a mix of Python and C++ and uses the Caffe framework. It is heavily derived from the visual concepts codebase by Saurabh Gupta, and the Fast-RCNN codebase by Ross Girshick. It also uses the MS COCO PythonAPI from Piotr Dollar.

Support

Quality

Security

License

Reuse

Support

latent-noise-icnm has a low active ecosystem.

It has 20 star(s) with 14 fork(s). There are 7 watchers for this library.

It had no major release in the last 6 months.

There are 0 open issues and 1 have been closed. On average issues are closed in 4 days. There are no pull requests.

It has a neutral sentiment in the developer community.

The latest version of latent-noise-icnm is current.

Quality

latent-noise-icnm has no bugs reported.

Security

latent-noise-icnm has no vulnerabilities reported, and its dependent libraries have no vulnerabilities reported.

License

latent-noise-icnm does not have a standard license declared.

Check the repository for any license declaration and review the terms closely.

Without a license, all rights are reserved, and you cannot use the library in your applications.

Reuse

latent-noise-icnm releases are not available. You will need to build from source code and install.

Installation instructions, examples and code snippets are available.

Top functions reviewed by kandi - BETA

kandi's functional review helps you automatically verify the functionalities of the libraries and avoid rework.
Currently covering the most popular Java, JavaScript and Python libraries. See a Sample of latent-noise-icnm

Get all kandi verified functions for this library.

latent-noise-icnm Key Features

No Key Features are available at this moment for latent-noise-icnm.

latent-noise-icnm Examples and Code Snippets

No Code Snippets are available at this moment for latent-noise-icnm.

Community Discussions

No Community Discussions are available at this moment for latent-noise-icnm.Refer to stack overflow page for discussions.

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

Vulnerabilities

No vulnerabilities reported

Install latent-noise-icnm

Build Caffe and pycaffe. Download pre-computed ICNM classifiers here and unzip. This will populate the folder $ICNM_ROOT/experiments/latentNoise/cache with caffe model files. Download COCO Dataset and annotations. Extract all of these zips into one directory named $ICNM_ROOT/data/coco. You can optionally extract them in another location, say $COCO_ROOT and create a symlink to that location. It should have this basic structure. [Optional] Download baseline models for COCO here. Unzipping this in $ICNM_ROOT will populate the folder $ICNM_ROOT/experiments/latentNoise/cache with caffe model files.
Clone the ICNM repository
We'll call the directory that you cloned ICNM into ICNM_ROOT The following subdirectories should exist as soon as you clone
caffe-ICNM : contains the caffe version used by this codebase
utils : utilities for loading/saving data, reading caffe logs, and simple MAP/REDUCE jobs
vocabs : vocabulary files (classes) for visual concepts
coco : PythonAPI for MS COCO dataset
experiments : prototxt (solver, train, deploy) files for the models baselines : baseline models [only prototxt] latentNoise : models that use our method [only prototxt]
Build Caffe and pycaffe cd $ICNM_ROOT/caffe-icnm # 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 pycaffe #makes caffe and pycaffe with 8 processes in parallel
Download pre-computed ICNM classifiers here and unzip. This will populate the folder $ICNM_ROOT/experiments/latentNoise/cache with caffe model files.
Download COCO Dataset and annotations wget http://msvocds.blob.core.windows.net/coco2014/train2014.zip wget http://msvocds.blob.core.windows.net/coco2014/val2014.zip wget http://msvocds.blob.core.windows.net/annotations-1-0-3/captions_train-val2014.zip
Extract all of these zips into one directory named $ICNM_ROOT/data/coco. You can optionally extract them in another location, say $COCO_ROOT and create a symlink to that location. unzip train2014.zip unzip val2014.zip unzip captions_train-val2014.zip
It should have this basic structure $ICNM_ROOT/data/coco/images # images $ICNM_ROOT/data/coco/images/train2014 # images $ICNM_ROOT/data/coco/images/val2014 # images $ICNM_ROOT/data/coco/annotations # json files with annotations
[Optional] Download baseline models for COCO here. Unzipping this in $ICNM_ROOT will populate the folder $ICNM_ROOT/experiments/latentNoise/cache with caffe model files.
Use these steps to train and test our model on the COCO dataset.
coco1k_coco-valid2_label_counts.h5: Ground truth for 1000 visual concepts
coco_instancesGT_eval_* : COCO detection ground truth converted to classification ground truth
labels_captions_coco_vocabS1k_train.h5 and ids_captions_coco_vocabS1k_train.txt : Label files used to train models
captions_*.json: COCO captions ground-truth files for valid2 split. Place them under the annotations directory of your COCO dataset.

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: