keras-models 0.0.5

Keras Models Hub

Keras Models Hub

This repo aims at providing both reusable Keras Models and pre-trained models, which could easily integrated into your projects.

Install

pip install keras-models

If you will using the NLP models, you need run one more command:

python -m spacy download xx_ent_wiki_sm

Usage Guide

import kearasmodels

Examples

Reusable Models

SkipGram

WideDeep

Pre-trained Models

VGG16_Places365

This model is forked from GKalliatakis/Keras-VGG16-places365 and CSAILVision/places365

from kerasmodels.models.pretrained import vgg16_places365
labels = vgg16_places365.predict('your_image_file_pathname.jpg', n_top=3)
# Example Result: labels = ['cafeteria', 'food_court', 'restaurant_patio'] 

Models

• TextCNN
• TextDNN
• SkipGram
• VGG16_Places365 [pre-trained]
• working on more models

Citation

TextCNN

Kim Y. 
Convolutional neural networks for sentence classification[J]. 
arXiv preprint arXiv:1408.5882, 2014.

SkipGram

Mikolov T, Chen K, Corrado G, et al. 
Efficient estimation of word representations in vector space[J]. 
arXiv preprint arXiv:1301.3781, 2013.

VGG16_Places365

Zhou, B., Lapedriza, A., Khosla, A., Oliva, A., & Torralba, A.
Places: A 10 million Image Database for Scene Recognition
IEEE Transactions on Pattern Analysis and Machine Intelligence

Contribution

Please submit PR if you want to contribute, or submit issues for new model requirements.