A curated database for pre-trained machine learning models.

What are pre-trained models? About
Explore all pre-trained networks. Explorer
Suggest new models for this list. Form
Stay up to date with our newsletter. Subscribe

Newest pre-trained models

⌨ Create

With the many of the models featured on this site you can create a fully working machine learning application in minutes.
Explore models!

🖌 Contribute

Help me to curate the best models. You can suggest me pre-trained models you created or found on the web.
Let me know!

✉ Learn

I also have a regular newsletter about pre-trained models with a lot of different resources and other relevant news.
Sign up here!

TensorFlow Android Camera Demo

A couple of pre-trained tensorflow models for android demos.

VGG16 for tensorflow

A version of the VGG16 net for tensorflow. Converted from Caffee.

VGG16 for deeplearning4j

A version of the VGG16 net for deeplearning4j.

GoogLeNet for deeplearning4j

An implementation of GoogLeNet for deeplearning4j. The main hallmark of this architecture is the improved utilization of the computing resources inside the network.

AlexNet for Deeplearning4j

A version of the AlexNet implemented for the framework Deeplearning4j.

FaceNet for Deeplearning4j

A version of the FaceNet implemented for the framework Deeplearning4j.

Unsupervised Sentiment Neuron

An unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.

Fully Convolutional Networks for Semantic Segmentation

A general approach for learning many image-to-image tasks.


CNN trained on Places Database could be directly used for scene recognition, while the deep scene features from the higher level layer of CNN could be used as generic features for visual recognition.


VGG Face Descriptor

The VGG-Face CNN descriptors are computed using our CNN implementation based on the VGG-Very-Deep-16 CNN architecture as described in the paper and are evaluated on the Labeled Faces in the Wild and the YouTube Faces dataset.


Stay updated!

We send a regular newsletter about new additions to this site and other interesting machine learning resources.