Pre-trained 3D ResNet-50

Pre-trained Neural Network Toolbox Model for 3D ResNet-50 Network

To transfer the learnable parameters from pre-trained 2D ResNet-50 (ImageNet) to 3D one, we duplicated 2D filters (copying them repeatedly) through the third dimension. This is possible since a video or a 3D image can be converted into a sequence of image slices. In the training process, we expect that the 3D ResNet-50 learns patterns in each frame. This model has 48 million learnable parameters.

simply, call "resnet50TL3Dfun()" function.