exp_loocv

from __future__ import print_function, division

import torch
from torch.autograd import Variable
from sklearn.metrics import accuracy_score
from sklearn.metrics import confusion_matrix
import torch
import torch.nn as nn
import torch.optim as optim
from torch.optim import lr_scheduler
import numpy as np
import torchvision
from torchvision import datasets, models, transforms
import matplotlib.pyplot as plt
import time
import os
import copy



import torch.utils.data as data_utils
from torch.utils import data


data_transforms = {
    'train': transforms.Compose([
        transforms.RandomResizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.RandomRotation(20),
        transforms.ColorJitter(.3, .3, .3),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
}


data_dir = "test_images"

device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")



def train_model(model, criterion, optimizer, scheduler, dataloader, num_epochs=25):
    since = time.time()

    for epoch in range(num_epochs):
        print('Epoch {}/{}'.format(epoch, num_epochs - 1))
        print('-' * 10)

        # Each epoch has a training and validation phase

        scheduler.step()
        model.train()  # Set model to training mode


        running_loss = 0.0
        running_corrects = 0

        # Iterate over data.
        for inputs, labels in dataloader:
            inputs = inputs.to(device)
            labels = labels.to(device)

            # zero the parameter gradients
            optimizer.zero_grad()

            # forward
            # track history if only in train
            with torch.set_grad_enabled(True):
                outputs = model(inputs)
                _, preds = torch.max(outputs, 1)
                loss = criterion(outputs, labels)
                # backward + optimize only if in training phase
                loss.backward()
                optimizer.step()
            # statistics
            running_loss += loss.item() * inputs.size(0)
            running_corrects += torch.sum(preds == labels.data)

        epoch_loss = running_loss / dataset_size['train']
        epoch_acc = running_corrects.double() / dataset_size['train']

        print('Loss: {:.4f} Acc: {:.4f}'.format(epoch_loss, epoch_acc))



    time_elapsed = time.time() - since
    print('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))



    return model


######################################################################
# Finetuning the convnet
# ----------------------
#
# Load a pretrained model and reset final fully connected layer.
#

'''model_ft = models.resnet50(pretrained=True)

num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

model_ft = model_ft.to(device)

criterion = nn.CrossEntropyLoss()

# Observe that all parameters are being optimized
optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

# Decay LR by a factor of 0.1 every 7 epochs
exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)'''



#model_ft = model_ft.cuda()
nb_samples = 50
nb_classes = 2



image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train']}

dataset_size = {x: len(image_datasets[x]) for x in ['train']}
class_names = image_datasets['train'].classes

# LOOCV
loocv_preds = []
loocv_targets = []
for idx in range(nb_samples):

    print('Using sample {} as test data'.format(idx))

    # Get all indices and remove test sample
    train_indices = list(range(len(image_datasets['train'])))
    del train_indices[idx]

    # Create new sampler
    sampler = data.SubsetRandomSampler(train_indices)
    print('sampler size: ', len(sampler))

    dataloader = data.DataLoader(
        image_datasets['train'],
        num_workers=2,
        batch_size=1,
        sampler=sampler
    )

    # Train model
    #for batch_idx, (sample, target) in enumerate(dataloader):
    #print('Batch {}'.format(batch_idx))
    model_ft = models.resnet50(pretrained=True)

    num_ftrs = model_ft.fc.in_features
    model_ft.fc = nn.Linear(num_ftrs, 2)

    model_ft = model_ft.to(device)

    criterion = nn.CrossEntropyLoss()

    # Observe that all parameters are being optimized
    optimizer_ft = optim.SGD(model_ft.parameters(), lr=0.001, momentum=0.9)

    # Decay LR by a factor of 0.1 every 7 epochs
    exp_lr_scheduler = lr_scheduler.StepLR(optimizer_ft, step_size=7, gamma=0.1)
    model_ft = train_model(model_ft, criterion, optimizer_ft, exp_lr_scheduler, dataloader, num_epochs=25) # do I add this line here?

    # Test on LOO sample
    model_ft.eval()
    test_data, test_target = image_datasets['train'][idx]
    test_data = test_data.cuda()
    test_target = torch.tensor(test_target)
    test_target = test_target.cuda()
    test_data.unsqueeze_(0)
    test_target.unsqueeze_(0)
    output = model_ft(test_data)
    pred = torch.argmax(output, 1)
    loocv_preds.append(pred)
    loocv_targets.append(test_target.item())


print("loocv preds: ", loocv_preds)
print("loocv targets: ", loocv_targets)
print(accuracy_score(loocv_targets, loocv_preds))
print(confusion_matrix(loocv_targets, loocv_preds))