Neural Network FHE models.#
The list below contains pretrained network architecture classes. Note that these are not HE-Friendly models as they still include ReLU activations, which still need to be replaced.
Class name |
Description |
---|---|
alexnet_fhe.alexnet_fhe |
An AlexNet-based model with weights pretrained on Imagenet. To make the model HE-Friendly, the following changes were applied: - Batch normalizations were added after max-pooling layers (layers 2,5,12) - Adaptive average-pooling were removed - max-pooling was replaced by average-pooling |
lenet5.Lenet5 |
|
resnet_clip.ClipResnet50_FHE |
|
resnet50.resnet_fhe |
|
squeezenetchet.SqueezeNetCHET |
A Squeezenet-CHET-based model. To make the model HE-Friendly, the following changes were applied:
|
squeezenet.SqueezeNet1_0_FHE |
A Squeezenet-based model with weights pretrained on ImageNet. To make the model HE-Friendly, the following changes were applied:
|
squeezenet.SqueezeNet1_1_FHE |
A Squeezenet-based model with weights pretrained on ImageNet. To make the model HE-Friendly, the following changes were applied:
|
To generate a new model use the base class nn_module.
This class serves as a wrapper for all the mltoolbox models. |