A vanilla 3D extention to raghakot/keras-resnet
A keras re-implementation of VoxResNet (Hao Chen et.al) for volumetric image segmention. (Non-official)
keras-voxresnet enables volumetric image classification with keras and tensorflow/theano.
keras, tensorflow/theano and their corresponding dependencies.
$ pip install git+https://github.com/JihongJu/keras-resnet3d.git
$ git clone https://github.com/JihongJu/keras-resnet3d.git
$ cd keras-resnet3d
$ python setup.py build
from resnet3d import Resnet3DBuilder
model = Resnet3DBuilder.build_resnet_50((96, 96, 96, 1), 20)
model.compile(optimizer='adam',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=32)
More details see example: