Pytorch_CNN-RNN/main.py

import torch
import torchvision

# FOR DATA
from utils.preprocess import prepare_datasets, prepare_predict
from utils.show_image import show_image
from utils.newCNN import CNN_Net
from torch.utils.data import DataLoader
from torchvision import datasets

from torch import nn
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



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


# MAYBE??
'''
import sys
sys.path.append('//data/data_wnx3/data_wnx1/rschuurs/CNN+RNN-2class-1cnn-CLEAN/utils')

import os
os.environ["CUDA_DEVICE_ORDER"] = "PCI_BUS_ID" 
os.environ["CUDA_VISIBLE_DEVICES"] = "0"  # use id from $ nvidia-smi
'''

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

# 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
# }

properties = {
    "batch_size":4,
    "padding":0,
    "dilation":1,
    "groups":1,
    "bias":True,
    "padding_mode":"zeros",
    "drop_rate":0
}


# Might have to replace datapaths or separate between training and testing
model_filepath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN'
CNN_filepath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN/cnn_net.pth'
mri_datapath = '/data/data_wnx1/rschuurs/Pytorch_CNN-RNN/MRI_volumes_customtemplate_float32/'
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)
test_dataloader = DataLoader(test_data, batch_size=properties['batch_size'], shuffle=True)
val_dataloader = DataLoader(val_data, batch_size=properties['batch_size'], shuffle=True)

# for X, y in train_dataloader:
#     print(f"Shape of X [Channels (colors), Y, X, Z]: {X.shape}")   # X & Y are from TOP LOOKING DOWN
#     print(f"Shape of Y (Dataset?): {y.shape} {y.dtype}")
#     break


# Display 4 images and labels.
# x = 1
# while x < 1:
#     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.show()
#     x = x+1


train = False
predict = True
CNN = CNN_Net(train_dataloader, prps=properties, final_layer_size=2)
CNN.cuda()

# RUN CNN
if(train):
    CNN.train_model(train_dataloader, CNN_filepath, epochs=10)
    CNN.evaluate_model(val_dataloader)

else:
    CNN.load_state_dict(torch.load(CNN_filepath))
    CNN.evaluate_model(val_dataloader)


# 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 ---")




# EXTRA

# will I need these params?
'''
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]))
'''