Commit 11e183d7 authored by Andrei-Claudiu Roibu's avatar Andrei-Claudiu Roibu 🖥
Browse files

added autoencoder version inspired by cGAN

parent 8449e9c9
"""Brain Mapper U-Net Architecture
Description:
This folder contains the Pytorch implementation of the core U-net architecture.
This arcitecture predicts functional connectivity rsfMRI from structural connectivity information from dMRI.
Usage:
To use this module, import it and instantiate is as you wish:
from BrainMapperUNet import BrainMapperUNet
deep_learning_model = BrainMapperUnet(parameters)
"""
import numpy as np
import torch
import torch.nn as nn
import utils.modules as modules
class BrainMapperAE3D(nn.Module):
"""Architecture class for CycleGAN inspired BrainMapper 3D Autoencoder.
This class contains the pytorch implementation of the generator architecture underpinning the BrainMapper project.
Args:
parameters (dict): Contains information relevant parameters
parameters = {
'kernel_heigth': 5
'kernel_width': 5
'kernel_depth': 5
'kernel_classification': 1
'input_channels': 1
'output_channels': 64
'convolution_stride': 1
'dropout': 0.2
'pool_kernel_size': 2
'pool_stride': 2
'up_mode': 'upconv'
'number_of_classes': 1
}
Returns:
probability_map (torch.tensor): Output forward passed tensor through the U-net block
"""
def __init__(self, parameters):
super(BrainMapperAE3D, self).__init__()
original_input_channels = parameters['input_channels']
original_output_channels = parameters['output_channels']
original_kernel_height = parameters['kernel_heigth']
original_stride = parameters['convolution_stride']
# Encoder Path
parameters['kernel_heigth'] = 7
self.encoderBlock1 = modules.ResNetEncoderBlock3D(parameters)
parameters['input_channels'] = parameters['output_channels']
parameters['output_channels'] = parameters['output_channels'] * 2
parameters['kernel_heigth'] = original_kernel_height
parameters['convolution_stride'] = 2
self.encoderBlock2 = modules.ResNetEncoderBlock3D(parameters)
parameters['input_channels'] = parameters['output_channels']
parameters['output_channels'] = parameters['output_channels'] * 2
self.encoderBlock3 = modules.ResNetEncoderBlock3D(parameters)
# Transformer
parameters['input_channels'] = parameters['output_channels']
parameters['convolution_stride'] = original_stride
self.transformerBlock1 = modules.ResNetBlock3D(parameters)
self.transformerBlock2 = modules.ResNetBlock3D(parameters)
self.transformerBlock3 = modules.ResNetBlock3D(parameters)
self.transformerBlock4 = modules.ResNetBlock3D(parameters)
self.transformerBlock5 = modules.ResNetBlock3D(parameters)
self.transformerBlock6 = modules.ResNetBlock3D(parameters)
# Decoder
parameters['output_channels'] = parameters['output_channels'] // 2
self.decoderBlock1 = modules.ResNetDecoderBlock3D(parameters)
parameters['input_channels'] = parameters['output_channels']
parameters['output_channels'] = parameters['output_channels'] // 2
self.decoderBlock2 = modules.ResNetDecoderBlock3D(parameters)
parameters['input_channels'] = parameters['output_channels']
self.decoderBlock3 = modules.ResNetClassifierBlock3D(parameters)
parameters['input_channels'] = original_input_channels
parameters['output_channels'] = original_output_channels
def forward(self, X):
"""Forward pass for 3D CGAN Autoencoder
Function computing the forward pass through the 3D generator
The input to the function is the dMRI map
Args:
X (torch.tensor): Input dMRI map, shape = (N x C x D x H x W)
Returns:
probability_map (torch.tensor): Output forward passed tensor through the CGAN Autoencoder
"""
# Encoder
X = self.encoderBlock1.forward(X)
Y_encoder_1_size = X.size()
X = self.encoderBlock2.forward(X)
Y_encoder_2_size = X.size()
X = self.encoderBlock3.forward(X)
# Transformer
X = self.transformerBlock1.forward(X)
X = self.transformerBlock2.forward(X)
X = self.transformerBlock3.forward(X)
X = self.transformerBlock4.forward(X)
X = self.transformerBlock5.forward(X)
X = self.transformerBlock6.forward(X)
# Decoder
X = self.decoderBlock1.forward(X, Y_encoder_2_size)
del Y_encoder_2_size
X = self.decoderBlock2.forward(X, Y_encoder_1_size)
del Y_encoder_1_size
X = self.decoderBlock3.forward(X)
return X
def save(self, path):
"""Model Saver
Function saving the model with all its parameters to a given path.
The path must end with a *.model argument.
Args:
path (str): Path string
"""
print("Saving Model... {}".format(path))
torch.save(self, path)
@property
def test_if_cuda(self):
"""Cuda Test
This function tests if the model parameters are allocated to a CUDA enabled GPU.
Returns:
bool: Flag indicating True if the tensor is stored on the GPU and Flase otherwhise
"""
return next(self.parameters()).is_cuda
def predict(self, X, device=0):
"""Post-training Output Prediction
This function predicts the output of the of the U-net post-training
Args:
X (torch.tensor): input dMRI volume
device (int/str): Device type used for training (int - GPU id, str- CPU)
Returns:
prediction (ndarray): predicted output after training
"""
self.eval() # PyToch module setting network to evaluation mode
if type(X) is np.ndarray:
X = torch.tensor(X, requires_grad=False).type(torch.FloatTensor)
elif type(X) is torch.Tensor and not X.is_cuda:
X = X.type(torch.FloatTensor).cuda(device, non_blocking=True)
# .cuda() call transfers the densor from the CPU to the GPU if that is the case.
# Non-blocking argument lets the caller bypas synchronization when necessary
with torch.no_grad(): # Causes operations to have no gradients
output = self.forward(X)
_, idx = torch.max(output, 1)
# We retrieve the tensor held by idx (.data), and map it to a cpu as an ndarray
idx = idx.data.cpu().numpy()
prediction = np.squeeze(idx)
del X, output, idx
return prediction
def reset_parameters(self):
"""Parameter Initialization
This function (re)initializes the parameters of the defined network.
This function is a wrapper for the reset_parameters() function defined for each module.
More information can be found here: https://discuss.pytorch.org/t/what-is-the-default-initialization-of-a-conv2d-layer-and-linear-layer/16055 + https://discuss.pytorch.org/t/how-to-reset-model-weights-to-effectively-implement-crossvalidation/53859
An alternative (re)initialization method is described here: https://discuss.pytorch.org/t/how-to-reset-variables-values-in-nn-modules/32639
"""
print("Initializing network parameters...")
for _, module in self.named_children():
for _, submodule in module.named_children():
for _, subsubmodule in submodule.named_children():
if isinstance(subsubmodule, (torch.nn.PReLU, torch.nn.Dropout3d, torch.nn.MaxPool3d)) == False:
subsubmodule.reset_parameters()
print("Initialized network parameters!")
\ No newline at end of file
Markdown is supported
0% or .
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment