Pytorch_CNN-RNN/main.py

import torch
import torchvision

# FOR DATA
from utils.preprocess import prepare_datasets
from utils.show_image import show_image
from torch.utils.data import DataLoader
from torchvision import datasets

from torch import nn
import torch.nn.functional as F
from torchvision.transforms import ToTensor

# import nonechucks as nc     # Used to load data in pytorch even when images are corrupted / unavailable (skips them)

# FOR IMAGE VISUALIZATION
import nibabel as nib

# GENERAL PURPOSE
import os
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import glob
from datetime import datetime

# FOR TRAINING
import torch.optim as optim
import utils.models as models
import utils.layers as ly
from tqdm import tqdm

#Set Default GPU
cuda_device = torch.device('cuda:1')
torch.set_default_device(cuda_device)

print("--- RUNNING ---")
print("Pytorch Version: " + torch. __version__)

# data & training properties:
val_split = 0.2     # % of val and test, rest will be train
runs = 1
epochs = 5
time_stamp = timestamp = datetime.now().strftime('%Y%m%d_%H%M%S')
seeds = [np.random.randint(0, 1000) for _ in range(runs)]

#Data Path
mri_datapath = '/data/data_wnx1/_Data/AlzheimersDL/CNN+RNN-2class-1cnn+data/PET_volumes_customtemplate_float32/'

#Local Path
local_path = '/export/home/nschense/alzheimers/Pytorch_CNN-RNN'

xls_path = local_path + '/LP_ADNIMERGE.csv'
saved_model_path = local_path + 'saved_models/'

DEBUG = False

# TODO: Datasets include multiple labels, such as medical info


def evaluate_model(seed):
    training_data, val_data, test_data = prepare_datasets(mri_datapath, xls_path, val_split, seed)
    

    batch_size = 64

    # Create data loaders
    train_dataloader = DataLoader(training_data, batch_size=batch_size, shuffle=True, generator=torch.Generator(device=cuda_device))
    test_dataloader = DataLoader(test_data, batch_size=batch_size, shuffle=True, generator=torch.Generator(device=cuda_device))
    val_dataloader = DataLoader(val_data, batch_size=batch_size, shuffle=True, generator=torch.Generator(device=cuda_device))

    #Print Shape of Image Data
    print("Shape of MRI Data: ", training_data[0][0].shape)
    print("Shape of XLS Data: ", training_data[0][1].shape)

    #Print Training Data Length
    print("Length of Training Data: ", len(train_dataloader))


    print("--- INITIALIZING MODEL ---")
    model_CNN = models.CNN_Net(1, 2, 0.5).to(cuda_device)
    criterion = nn.BCELoss()
    optimizer = optim.Adam(model_CNN.parameters(), lr=0.001)
    print("Seed: ", seed)
    epoch_number = 0

    print("--- TRAINING MODEL ---")
    for epoch in range(epochs):
        running_loss = 0.0
        length = len(train_dataloader)
        for i, data in tqdm(enumerate(train_dataloader, 0), total=length, desc="Epoch " + str(epoch), unit="batch"):
            mri, xls, label = data

            optimizer.zero_grad()

            mri = mri.to(cuda_device).float()
            xls = xls.to(cuda_device).float()
            label = label.to(cuda_device).float()


            outputs = model_CNN((mri, xls))

            if DEBUG:
                print(outputs.shape, label.shape)

            loss = criterion(outputs, label)
            loss.backward()
            optimizer.step()

            running_loss += loss.item()
            if i % 1000 == 999:
                print("Epoch: ", epoch_number, "Batch: ", i+1, "Loss: ", running_loss / 1000, "Accuracy: ", )
                print('[%d, %5d] loss: %.3f' % (epoch + 1, i + 1, running_loss / 1000))
                running_loss = 0.0
        epoch_number += 1


    print("--- TESTING MODEL ---")
    #Test model
    correct = 0
    total = 0

    with torch.no_grad():
        length = len(test_dataloader)
        for i, data in tqdm(enumerate(test_dataloader, 0), total=length, desc="Testing", unit="batch"):
            mri, xls, label = data

            mri = mri.to(cuda_device).float()
            xls = xls.to(cuda_device).float()
            label = label.to(cuda_device).float()


            outputs = model_CNN((mri, xls))

            if DEBUG:
                print(outputs.shape, label.shape)

            _, predicted = torch.max(outputs.data, 1)
            _, labels = torch.max(label.data, 1)

            if DEBUG:
                print("Predicted: ", predicted)
                print("Labels: ", labels)


            total += labels.size(0)
            correct += (predicted == labels).sum().item()

    print("Model Accuracy: ", 100 * correct / total)

        
for seed in seeds:
    evaluate_model(seed)


print("--- END ---")