-
This code is the object-oriented implementation of the Residual Network proposed by "Deep Residual Learning for Image Recognition". They proposed several structures summarized in Table. 1 of the paper. I implemented the one with 50 convolutional layers which uses the powerful so-called bottleneck blocks.
-
This code is prepared for the 3D CT scans of size 32x32x32 by using 3D convolutions, max-pooling, etc. You can simply modify it by changing the parameters and number of layers.
ClarenceHoo/3D_ResNet_Tensorflow_Tensorboard
The object-oriented implementation of the Residual Network proposed in "Deep Residual Learning for Image Recognition" modified to be used for 3D images
Python