Pytorch_CNN-RNN/main.py

import torch

# FOR DATA
from utils.preprocess import prepare_datasets
from utils.train_methods import train, load, evaluate, predict
from utils.CNN import CNN_Net
from torch.utils.data import DataLoader
from torchvision import datasets
from sklearn.model_selection import KFold

# GENERAL PURPOSE
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import platform
import time
current_time = time.localtime()

print(time.strftime("%Y-%m-%d_%H:%M", current_time))
print("--- RUNNING ---")
print("Pytorch Version: " + torch. __version__)
print("Python Version: " + platform.python_version())

# LOADING DATA
val_split = 0.2     # % of val and test, rest will be train
seed = 12       # TODO Randomize seed

properties = {
    "batch_size":6,
    "padding":0,
    "dilation":1,
    "groups":1,
    "bias":True,
    "padding_mode":"zeros",
    "drop_rate":0
}


model_filepath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN'
CNN_filepath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN/cnn_net.pth'       # cnn_net.pth
# small dataset
mri_datapath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN/PET_volumes_customtemplate_float32/'   # Small Test
# big dataset
# mri_datapath = '/data/data_wnx1/_Data/AlzheimersDL/CNN+RNN-2class-1cnn+data/PET_volumes_customtemplate_float32/'   # Real data
annotations_datapath = './data/data_wnx1/rschuurs/Pytorch_CNN-RNN/LP_ADNIMERGE.csv'

# annotations_file = pd.read_csv(annotations_datapath)    # DataFrame
# show_image(17508)

# TODO: Datasets include multiple labels, such as medical info
training_data, val_data, test_data = prepare_datasets(mri_datapath, val_split, seed)

# Create data loaders
train_dataloader = DataLoader(training_data, batch_size=properties['batch_size'], shuffle=True, drop_last=True)
test_dataloader = DataLoader(test_data, batch_size=properties['batch_size'], shuffle=True)
val_dataloader = DataLoader(val_data, batch_size=properties['batch_size'], shuffle=True)

# loads a few images to test
x = 0
while x < 0:
    train_features, train_labels = next(iter(train_dataloader))
    print(f"Feature batch shape: {train_features.size()}")
    img = train_features[0].squeeze()
    print(f"Feature batch shape: {img.size()}")
    image = img[:, :, 40]
    print(f"Feature batch shape: {image.size()}")
    label = train_labels[0]
    print(f"Label: {label}")
    plt.imshow(image, cmap="gray")
    plt.savefig(f"./Image{x}_IS:{label}.png")
    plt.show()

    x = x+1



epochs = 20
roc = True
CNN = CNN_Net(prps=properties, final_layer_size=2)
CNN.cuda()

train(CNN, train_dataloader, test_dataloader, CNN_filepath, epochs, graphs=True)
# load(CNN, CNN_filepath)
evaluate(CNN, val_dataloader)
predict(CNN, val_dataloader)



# EXTRA


# # PREDICT MODE TO TEST INDIVIDUAL IMAGES
# if(predict):
#     on = True
#     print("---- Predict mode ----")
#     print("Integer for image")
#     print("x or X for exit")
#
#     while(on):
#         inp = input("Next image: ")
#         if(inp == None or inp.lower() == 'x' or not inp.isdigit()): on = False
#         else:
#             dataloader = DataLoader(prepare_predict(mri_datapath, [inp]), batch_size=properties['batch_size'], shuffle=True)
#             prediction = CNN.predict(dataloader)
#
#             features, labels = next(iter(dataloader), )
#             img = features[0].squeeze()
#             image = img[:, :, 40]
#             print(f"Expected class: {labels}")
#             print(f"Prediction: {prediction}")
#             plt.imshow(image, cmap="gray")
#             plt.show()
#
# print("--- END ---")


# params = {
#     "target_rows": 91,
#     "target_cols": 109,
#     "depth": 91,
#     "axis": 1,
#     "num_clinical": 2,
#     "CNN_drop_rate": 0.3,
#     "RNN_drop_rate": 0.1,
#     # "CNN_w_regularizer": regularizers.l2(2e-2),
#     # "RNN_w_regularizer": regularizers.l2(1e-6),
#     "CNN_batch_size": 10,
#     "RNN_batch_size": 5,
#     "val_split": 0.2,
#     "final_layer_size": 5
# }

'''
params_dict = { 'CNN_w_regularizer': CNN_w_regularizer, 'RNN_w_regularizer': RNN_w_regularizer,
               'CNN_batch_size': CNN_batch_size, 'RNN_batch_size': RNN_batch_size,
               'CNN_drop_rate': CNN_drop_rate, 'epochs': 30,
          'gpu': "/gpu:0", 'model_filepath': model_filepath,
          'image_shape': (target_rows, target_cols, depth, axis),
          'num_clinical': num_clinical,
          'final_layer_size': final_layer_size,
          'optimizer': optimizer, 'RNN_drop_rate': RNN_drop_rate,}

params = Parameters(params_dict)

# WHAT WAS THIS AGAIN?
seeds = [np.random.randint(1, 5000) for _ in range(1)]

# READ THIS TO UNDERSTAND TRAIN VS VALIDATION DATA
def evaluate_net (seed):
    n_classes = 2
    data_loader = DataLoader((target_rows, target_cols, depth, axis), seed = seed)
    train_data, val_data, test_data,rnn_HdataT1,rnn_HdataT2,rnn_HdataT3,rnn_AdataT1,rnn_AdataT2,rnn_AdataT3, test_mri_nonorm = data_loader.get_train_val_test(val_split, mri_datapath)

    print('Length Val Data[0]: ',len(val_data[0]))
'''