Lots of researchers and engineers have made Caffe models for different tasks with all kinds of architectures and data: check out the model zoo! 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:
First of all, we bundle BAIR-trained models for unrestricted, out of the box use.
See the BAIR model license for details. Each one of these can be downloaded by running
scripts/download_model_binary.py <dirname> where
<dirname> is specified below:
models/bvlc_reference_caffenet: AlexNet trained on ILSVRC 2012, with a minor variation from the version as described in ImageNet classification with deep convolutional neural networks by Krizhevsky et al. in NIPS 2012. (Trained by Jeff Donahue @jeffdonahue)
models/bvlc_alexnet: AlexNet trained on ILSVRC 2012, almost exactly as described in ImageNet classification with deep convolutional neural networks by Krizhevsky et al. in NIPS 2012. (Trained by Evan Shelhamer @shelhamer)
models/bvlc_reference_rcnn_ilsvrc13: pure Caffe implementation of R-CNN as described by Girshick et al. in CVPR 2014. (Trained by Ross Girshick @rbgirshick)
models/bvlc_googlenet: GoogLeNet trained on ILSVRC 2012, almost exactly as described in Going Deeper with Convolutions by Szegedy et al. in ILSVRC 2014. (Trained by Sergio Guadarrama @sguada)
Community models made by Caffe users are posted to a publicly editable model zoo wiki page. These models are subject to conditions of their respective authors such as citation and license. Thank you for sharing your models!
A caffe model is distributed as a directory containing:
This simple format can be handled through bundled scripts or manually if need be.
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/upload_model_to_gist.sh <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>/readme.md frontmatter, then updates existing Gist.
scripts/upload_model_to_gist.sh 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/download_model_from_gist.sh <gist_id> <dirname>.
It is up to the user where to host the
We host our BAIR-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/download_model_binary.py <dirname> downloads the
.caffemodel from the URL specified in the
<dirname>/readme.md frontmatter and confirms SHA1.
The Caffe models bundled by the BAIR 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.