Deep learning framework by the BVLC

Created by
Yangqing Jia
Lead Developer
Evan Shelhamer

Caffe Model Zoo

Lots of researchers and engineers have made Caffe models for different tasks with all kinds of architectures and data. These models are learned and applied for problems ranging from simple regression, to large-scale visual classification, to Siamese networks for image similarity, to speech and robotics applications.

To help share these models, we introduce the model zoo framework:

Where to get trained models

First of all, we bundle BVLC-trained models for unrestricted, out of the box use.
See the BVLC model license for details. Each one of these can be downloaded by running scripts/ <dirname> where <dirname> is specified below:

Community models made by Caffe users are posted to a publicly editable wiki page. These models are subject to conditions of their respective authors such as citation and license. Thank you for sharing your models!

Model info format

A caffe model is distributed as a directory containing:

Hosting model info

Github Gist is a good format for model info distribution because it can contain multiple files, is versionable, and has in-browser syntax highlighting and markdown rendering.

scripts/ <dirname> uploads non-binary files in the model directory as a Github Gist and prints the Gist ID. If gist_id is already part of the <dirname>/ frontmatter, then updates existing Gist.

Try doing scripts/ models/bvlc_alexnet to test the uploading (don’t forget to delete the uploaded gist afterward).

Downloading model info is done just as easily with scripts/ <gist_id> <dirname>.

Hosting trained models

It is up to the user where to host the .caffemodel file. We host our BVLC-provided models on our own server. Dropbox also works fine (tip: make sure that ?dl=1 is appended to the end of the URL).

scripts/ <dirname> downloads the .caffemodel from the URL specified in the <dirname>/ frontmatter and confirms SHA1.

BVLC model license

The Caffe models bundled by the BVLC are released for unrestricted use.

These models are trained on data from the ImageNet project and training data includes internet photos that may be subject to copyright.

Our present understanding as researchers is that there is no restriction placed on the open release of these learned model weights, since none of the original images are distributed in whole or in part. To the extent that the interpretation arises that weights are derivative works of the original copyright holder and they assert such a copyright, UC Berkeley makes no representations as to what use is allowed other than to consider our present release in the spirit of fair use in the academic mission of the university to disseminate knowledge and tools as broadly as possible without restriction.