`handbag_data/github_datasets/Pursearch/src/train.py`

131 lines
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 time
import os
import copy
import logging

logfile = "name_resnet50_gpu_correct_merged_adddata.log"
logging.basicConfig(filename=logfile, format='%(asctime)s %(message)s', filemode='w')
logger = logging.getLogger()
logger.setLevel(logging.INFO)

def train_model(model, criterion, optimizer, scheduler, num_epochs=25):
    since = time.time()
    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

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

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                model.train()  # Set model to training mode
            else:
                model.eval()   # Set model to evaluate mode

            running_loss = 0.0
            running_corrects = 0

            # Iterate over data.
            for inputs, labels in dataloaders[phase]:
                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(phase == 'train'):
                    outputs = model(inputs)
                    _, preds = torch.max(outputs, 1)
                    loss = criterion(outputs, labels)

                    # backward + optimize only if in training phase
                    if phase == 'train':
                        loss.backward()
                        optimizer.step()

                # statistics
                running_loss += loss.item() * inputs.size(0)
                running_corrects += torch.sum(preds == labels.data)
                logger.info(running_corrects)
            if phase == 'train':
                scheduler.step()

            epoch_loss = running_loss / dataset_sizes[phase]
            epoch_acc = running_corrects.double() / dataset_sizes[phase]

            logger.info('{} Loss: {:.4f} Acc: {:.4f}'.format(
                phase, epoch_loss, epoch_acc))

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

    time_elapsed = time.time() - since
    logger.info('Training complete in {:.0f}m {:.0f}s'.format(
        time_elapsed // 60, time_elapsed % 60))
    logger.info('Best val Acc: {:4f}'.format(best_acc))

    # load best model weights
    model.load_state_dict(best_model_wts)
    return model

# data transformation 
data_transforms = {
    'train': transforms.Compose([
        transforms.Resize((256,256)),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize((256,256)),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ])
}


if name == "__main__":
    data_dir = "../data/processed/name_correct_merged/"
    image_datasets = {x: datasets.ImageFolder(os.path.join(data_dir, x),
                                          data_transforms[x])
                  for x in ['train', 'val']}
    dataloaders = {x: torch.utils.data.DataLoader(image_datasets[x], batch_size=100,
                                             shuffle=True)
                for x in ['train', 'val']}
    dataset_sizes = {x: len(image_datasets[x]) for x in ['train', 'val']}
    class_names = image_datasets['train'].classes
    device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
    model_ft = models.resnet50(pretrained=True)
    num_ftrs = model_ft.fc.in_features
    # Here the size of each output sample is set to 19.
    # Alternatively, it can be generalized to nn.Linear(num_ftrs, len(class_names)).
    model_ft.fc = nn.Linear(num_ftrs, 19)

    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,
                       num_epochs=100)
    torch.save(model_ft.state_dict(), "../models/model_name_resnet50gpu_correct_merged_adddata")