Name: c3d-keras
Owner: axon-research
Description: C3D for Keras + TensorFlow
Created: 2016-12-01 19:21:28.0
Updated: 2018-01-31 11:03:08.0
Pushed: 2017-07-19 22:00:45.0
Homepage: null
Size: 3079
Language: Python
GitHub Committers
User | Most Recent Commit | # Commits |
---|
Other Committers
User | Most Recent Commit | # Commits |
---|
The scripts here are inspired by C3D Model for Keras
gist, but specifically for Keras + TensorFlow (not Theano-backend).
To reproduce results:
bash do_everything.sh
OR, build a docker image, which will do all the steps of replication during the build:
er build -t c3d-keras .
OR, run each of these steps:
bash models/get_weights_and_mean.sh
bash sports1m/get_labels.sh
caffe.proto
file for conversion from caffe to Keras: wget https://raw.githubusercontent.com/facebook/C3D/master/C3D-v1.0/src/caffe/proto/caffe.proto
sudo apt-get install protobuf-compiler
will do.protoc --python_out=. caffe.proto
~/.keras/keras.json
) has: tf
image_dim_ordering, and tensorflow
backend.python convert_caffe_model.py
bash download_test_video.sh
python test_model.py
Known to work with the following python packages:
Some basic command-line tools:
A following classification probability plot is expected (saved as probabilities.png
). A peak at 367th class (probability = 71%) corresponds to basketball label.
The top 5 labels will also be reported, and should look something like:
tion of maximum probability: 367
mum probability: 0.57953
esponding label: basketball
5 probabilities and labels:
etball: 0.57953
eyball: 0.14435
etball: 0.06718
style wrestling: 0.03323
o-roman wrestling: 0.03293
Feel free to contact Chuck Cho (cycho at axon.com) for any comment or feedback.