機械学習のお勉強（pytorchのtutorialを眺めてみる）

Let’s create three transforms:

Rescale: to scale the image

RandomCrop: to crop from image randomly. This is data augmentation.

ToTensor: to convert the numpy images to torch images (we need to swap axes).

Iterating through the dataset

Batching the data
Shuffling the data
Load the data in parallel using multiprocessing workers

num_workersでいくつのコアでデータをロードするか指定(デフォルトはメインのみ)

dataloader = DataLoader(transformed_dataset, batch_size=4,
                        shuffle=True, num_workers=4)


# Helper function to show a batch
def show_landmarks_batch(sample_batched):
    """Show image with landmarks for a batch of samples."""
    images_batch, landmarks_batch = \
            sample_batched['image'], sample_batched['landmarks']
    batch_size = len(images_batch)
    im_size = images_batch.size(2)

    grid = utils.make_grid(images_batch)
    plt.imshow(grid.numpy().transpose((1, 2, 0)))

    for i in range(batch_size):
        plt.scatter(landmarks_batch[i, :, 0].numpy() + i * im_size,
                    landmarks_batch[i, :, 1].numpy(),
                    s=10, marker='.', c='r')

        plt.title('Batch from dataloader')

for i_batch, sample_batched in enumerate(dataloader):
    print(i_batch, sample_batched['image'].size(),
          sample_batched['landmarks'].size())

    # observe 4th batch and stop.
    if i_batch == 3:
        plt.figure()
        show_landmarks_batch(sample_batched)
        plt.axis('off')
        plt.ioff()
        plt.show()
        break

output

0 torch.Size([4, 3, 224, 224]) torch.Size([4, 68, 2])
1 torch.Size([4, 3, 224, 224]) torch.Size([4, 68, 2])
2 torch.Size([4, 3, 224, 224]) torch.Size([4, 68, 2])
3 torch.Size([4, 3, 224, 224]) torch.Size([4, 68, 2])

torchvision

これは便利すぎる

One of the more generic datasets available in torchvision is ImageFolder.

It assumes that images are organized in the following way:

root/ants/xxx.png
root/ants/xxy.jpeg
root/ants/xxz.png
.
.
.
root/bees/123.jpg
root/bees/nsdf3.png
root/bees/asd932_.png

where ‘ants’, ‘bees’ etc. are class labels. Similarly generic transforms which operate on PIL.Image like RandomHorizontalFlip, Scale, are also avaiable. You can use these to write a dataloader like this:

import torch
from torchvision import transforms, datasets

data_transform = transforms.Compose([
        transforms.RandomSizedCrop(224),
        transforms.RandomHorizontalFlip(),
        transforms.ToTensor(),
        transforms.Normalize(mean=[0.485, 0.456, 0.406],
                             std=[0.229, 0.224, 0.225])
    ])
hymenoptera_dataset = datasets.ImageFolder(root='hymenoptera_data/train',                                        transform=data_transform)
dataset_loader = torch.utils.data.DataLoader(hymenoptera_dataset,
                                             batch_size=4, shuffle=True,
                                             num_workers=4)

これを使えば自作データセットのCNNのデータの用意がすぐできるイエイ

Transfer Learning Tutorial

Transfer Learning tutorial — PyTorch Tutorials 0.2.0_4 documentation

These two major transfer learning scenarios looks as follows:

Finetuning the convnet: Instead of random initializaion, we initialize the network with a pretrained network, like the one that is trained on imagenet 1000 dataset. Rest of the training looks as usual.

ConvNet as fixed feature extractor: Here, we will freeze the weights for all of the network except that of the final fully connected layer. This last fully connected layer is replaced with a new one with random weights and only this layer is trained.

Finetuning the convnet

pretrainされたモデルを読み込んだ上で学習

model_ft = models.resnet18(pretrained=True)
num_ftrs = model_ft.fc.in_features
model_ft.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_ft = model_ft.cuda()

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)

ConvNet as fixed feature extractor

for param in model_conv.parameters(): param.requires_grad = False

ここでconv層の重みは固定をして全結合層だけ学習

model_conv = torchvision.models.resnet18(pretrained=True)
for param in model_conv.parameters():
    param.requires_grad = False

# Parameters of newly constructed modules have requires_grad=True by default
num_ftrs = model_conv.fc.in_features
model_conv.fc = nn.Linear(num_ftrs, 2)

if use_gpu:
    model_conv = model_conv.cuda()

criterion = nn.CrossEntropyLoss()

# Observe that only parameters of final layer are being optimized as
# opoosed to before.
optimizer_conv = optim.SGD(model_conv.fc.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_conv, step_size=7, gamma=0.1)

GPU化

Training a classifier — PyTorch Tutorials 0.2.0_4 documentation

Multi-GPU examples — PyTorch Tutorials 0.2.0_4 documentation

net.cuda()
inputs, labels = Variable(inputs.cuda()), Variable(labels.cuda())

上記のように基本的にinputとラベルをすべてcuda()とつけてgpu化する。

.cpu()とするとcpu化。

空飛ぶロボットのつくりかた

ロボットをつくるために必要な技術をまとめます。ロボットの未来についても考えたりします。

機械学習のお勉強（pytorchのtutorialを眺めてみる）

install

DOCS

Tutorial

Data Loading and Processing Tutorial

Transform