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.
Ebrahimi, Amir, et al. “Introducing Transfer Learning to 3D ResNet-18 for Alzheimer’s Disease Detection on MRI Images.” 2020 35th International Conference on Image and Vision Computing New Zealand (IVCNZ), IEEE, 2020, doi:10.1109/ivcnz51579.2020.9290616.
Find the treasures in MATLAB Central and discover how the community can help you!Start Hunting!