adnan-bashir-fuaad · August 26, 2018 18:02
diff --git a/ImageNet-200-Classifier.py b/ImageNet-200-Classifier.py
 #!/home/adnan/anaconda3/bin/python
 import torch
 import torch.nn as nn
 import torch.optim as optim
 from torch.optim import lr_scheduler
 import torchvision
 from torchvision import datasets, models, transforms
 import time
 import os
 import copy


 batch_size = 128
 num_workers = 4

 data_transforms = {
    'train': transforms.Compose([
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
    'val': transforms.Compose([
        transforms.Resize(256),
        transforms.CenterCrop(224),
        transforms.ToTensor(),
        transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
    ]),
 }

 save_dir = '/home/adnan/A-New-Start/ImageNet-200_Classifier_Pre-trained_Models/'
 data_dir = '/home/adnan/A-New-Start/Enlarged-ImageNet-200'
 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=batch_size, shuffle=True, num_workers=num_workers) 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")


 def train_model(model, criterion, optimizer, scheduler=None, num_epochs=25):
    since = time.time()

    best_model_wts = copy.deepcopy(model.state_dict())
    best_acc = 0.0

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

        # Each epoch has a training and validation phase
        for phase in ['train', 'val']:
            if phase == 'train':
                # scheduler.step()
                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.
            iter_count = 0
            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)

                print('Done with ' + str(iter_count))
                iter_count += 1

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

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

            # deep copy the model
            if phase == 'val' and epoch_acc > best_acc:
                torch.save(model.state_dict(), os.path.join(save_dir, 'ImageNet-200-Classifier-Pretrained-Model-' + str(epoch_acc.item()) + '.pkl'))
                best_acc = epoch_acc
                best_model_wts = copy.deepcopy(model.state_dict())

        print()

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

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


 model_ft = models.squeezenet1_1(pretrained=True)
 # print(model_ft.classifier[1])
 # '''
 for param in model_ft.parameters():
    param.requires_grad = False

 # num_ftrs = model_ft.fc.in_features
 # model_ft.fc = nn.Linear(num_ftrs, len(class_names))
 num_ftrs = model_ft.classifier[1].in_channels
 model_ft.classifier[1] = nn.Conv2d(in_channels=num_ftrs, out_channels=200, kernel_size=(1, 1), stride=(1, 1))
 model_ft.num_classes = 200

 for param in model_ft.parameters():
    print(param.requires_grad)

 print(model_ft)
 # '''
 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)
 optimizer_ft = optim.Adam(params=model_ft.parameters(), lr=0.001)

 # 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=model_ft, criterion=criterion, optimizer=optimizer_ft, num_epochs=50)
 # '''
	#!/home/adnan/anaconda3/bin/python
	import torch
	import torch.nn as nn
	import torch.optim as optim
	from torch.optim import lr_scheduler
	import torchvision
	from torchvision import datasets, models, transforms
	import time
	import os
	import copy


	batch_size = 128
	num_workers = 4

	data_transforms = {
	'train': transforms.Compose([
	transforms.RandomHorizontalFlip(),
	transforms.ToTensor(),
	transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
	]),
	'val': transforms.Compose([
	transforms.Resize(256),
	transforms.CenterCrop(224),
	transforms.ToTensor(),
	transforms.Normalize([0.485, 0.456, 0.406], [0.229, 0.224, 0.225])
	]),
	}

	save_dir = '/home/adnan/A-New-Start/ImageNet-200_Classifier_Pre-trained_Models/'
	data_dir = '/home/adnan/A-New-Start/Enlarged-ImageNet-200'
	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=batch_size, shuffle=True, num_workers=num_workers) 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")


	def train_model(model, criterion, optimizer, scheduler=None, num_epochs=25):
	since = time.time()

	best_model_wts = copy.deepcopy(model.state_dict())
	best_acc = 0.0

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

	# Each epoch has a training and validation phase
	for phase in ['train', 'val']:
	if phase == 'train':
	# scheduler.step()
	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.
	iter_count = 0
	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)

	print('Done with ' + str(iter_count))
	iter_count += 1

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

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

	# deep copy the model
	if phase == 'val' and epoch_acc > best_acc:
	torch.save(model.state_dict(), os.path.join(save_dir, 'ImageNet-200-Classifier-Pretrained-Model-' + str(epoch_acc.item()) + '.pkl'))
	best_acc = epoch_acc
	best_model_wts = copy.deepcopy(model.state_dict())

	print()

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

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


	model_ft = models.squeezenet1_1(pretrained=True)
	# print(model_ft.classifier[1])
	# '''
	for param in model_ft.parameters():
	param.requires_grad = False

	# num_ftrs = model_ft.fc.in_features
	# model_ft.fc = nn.Linear(num_ftrs, len(class_names))
	num_ftrs = model_ft.classifier[1].in_channels
	model_ft.classifier[1] = nn.Conv2d(in_channels=num_ftrs, out_channels=200, kernel_size=(1, 1), stride=(1, 1))
	model_ft.num_classes = 200

	for param in model_ft.parameters():
	print(param.requires_grad)

	print(model_ft)
	# '''
	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)
	optimizer_ft = optim.Adam(params=model_ft.parameters(), lr=0.001)

	# 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=model_ft, criterion=criterion, optimizer=optimizer_ft, num_epochs=50)
	# '''
No results found