- 前回に続いて，学習済みモデルの中間層の出力を取り出す例として，学習済みCNNを自己符号化(オートエンコーダ)として使う例をやってみる。
- コードはPyTorch公式exampleのmnistを少しいじって，モデルの中間層が取り出しやすくして，t-SNEによる埋め込みを行った。と言っても，t-SNEはsklearnを使っているだけ。t-SNEはアルゴリズム的に学習済みモデルを使って予測，という類の使い方ではない。つまり，他のsklearnのモデルみたいに学習データでfitして，評価したいデータをpredict，みたいな使い方は(基本的には)できない。
from __future__ import print_function
import numpy as np
from sklearn.manifold import TSNE
import matplotlib.pyplot as plt
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
class Net(nn.Module):
def __init__(self):
super(Net, self).__init__()
self.encoder = nn.Sequential(
nn.Conv2d(1, 10, kernel_size=5),
nn.MaxPool2d(kernel_size=2),
nn.ReLU(),
nn.Conv2d(10, 20, kernel_size=5),
nn.Dropout2d(),
nn.MaxPool2d(kernel_size=2),
nn.ReLU(),
)
self.fc1 = nn.Linear(320, 50)
self.fc2 = nn.Linear(50, 10)
def forward(self, x):
x = self.encoder(x)
x = x.view(-1, 320)
x = F.relu(self.fc1(x))
x = F.dropout(x, training=self.training)
x = self.fc2(x)
return F.log_softmax(x, dim=1)
def train(args, model, device, train_loader, optimizer, epoch):
model.train()
for batch_idx, (data, target) in enumerate(train_loader):
data, target = data.to(device), target.to(device)
optimizer.zero_grad()
output = model(data)
loss = F.nll_loss(output, target)
loss.backward()
optimizer.step()
if batch_idx % args.log_interval == 0:
print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'.format(
epoch, batch_idx * len(data), len(train_loader.dataset),
100. * batch_idx / len(train_loader), loss.item()))
def test(args, model, device, test_loader):
model.eval()
test_loss = 0
correct = 0
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
output = model(data)
test_loss += F.nll_loss(output, target, reduction='sum').item()
pred = output.max(1, keepdim=True)[1]
correct += pred.eq(target.view_as(pred)).sum().item()
test_loss /= len(test_loader.dataset)
print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'.format(
test_loss, correct, len(test_loader.dataset),
100. * correct / len(test_loader.dataset)))
def auto_encode(args, model, device, test_loader):
model.eval()
with torch.no_grad():
for data, target in test_loader:
data, target = data.to(device), target.to(device)
latent_vecs = model.encoder(data)
latent_vecs = latent_vecs.view(-1, 320)
latent_vecs = model.fc1(latent_vecs)
return latent_vecs, target
def main(train=False):
parser = argparse.ArgumentParser(description='PyTorch MNIST Example')
parser.add_argument('--batch-size', type=int, default=64, metavar='N',
help='input batch size for training (default: 64)')
parser.add_argument('--test-batch-size', type=int, default=10000, metavar='N',
help='input batch size for testing (default: 10000)')
parser.add_argument('--epochs', type=int, default=10, metavar='N',
help='number of epochs to train (default: 10)')
parser.add_argument('--lr', type=float, default=0.01, metavar='LR',
help='learning rate (default: 0.01)')
parser.add_argument('--momentum', type=float, default=0.5, metavar='M',
help='SGD momentum (default: 0.5)')
parser.add_argument('--no-cuda', action='store_true', default=False,
help='disables CUDA training')
parser.add_argument('--seed', type=int, default=1, metavar='S',
help='random seed (default: 1)')
parser.add_argument('--log-interval', type=int, default=10, metavar='N',
help='how many batches to wait before logging training\
status')
args = parser.parse_args()
use_cuda = not args.no_cuda and torch.cuda.is_available()
torch.manual_seed(args.seed)
device = torch.device("cuda" if use_cuda else "cpu")
kwargs = {'num_workers': 1, 'pin_memory': True} if use_cuda else {}
train_loader = torch.utils.data.DataLoader(
datasets.MNIST('/home/hoge/PyTorch_MLdata/MNIST',
train=True,
download=True,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))
])),
batch_size=args.batch_size, shuffle=True, **kwargs)
test_loader = torch.utils.data.DataLoader(
datasets.MNIST('/home/hoge/PyTorch_MLdata/MNIST',
train=False,
transform=transforms.Compose([
transforms.ToTensor(),
transforms.Normalize((0.1307,), (0.3081,))])),
batch_size=args.test_batch_size, shuffle=True, **kwargs)
model = Net().to(device)
if train:
optimizer = optim.SGD(model.parameters(), lr=args.lr,
momentum=args.momentum)
for epoch in range(1, args.epochs + 1):
train(args, model, device, train_loader, optimizer, epoch)
test(args, model, device, test_loader)
torch.save(model.state_dict(), './model_param_autoencoder.pkl')
model.load_state_dict(torch.load('./model_param_autoencoder.pkl'))
latent_vecs, target = auto_encode(args, model, device, test_loader)
latent_vecs, target = latent_vecs.numpy(), target.numpy()
print(latent_vecs.shape, target.shape)
latent_vecs_reduced = TSNE(n_components=2,\
random_state=0).fit_transform(latent_vecs[:1000])
plt.scatter(latent_vecs_reduced[:, 0], latent_vecs_reduced[:, 1],
c=target[:1000], cmap='jet')
plt.colorbar()
plt.show()
if __name__ == '__main__':
main(train=False)
