脚本宝典收集整理的这篇文章主要介绍了多层自编码器手写版,脚本宝典觉得挺不错的,现在分享给大家,也给大家做个参考。
#导入实验需要的包
import torch
import torch.nn as nn
import torch.utils.data as Data
import torchvision
import matplotlib.pyplot as plt
From mpl_toolkITs.mplot3d import Axes3D
from matplotlib import cm
import numpy as np
# torch.manual_seed(1) # rePRoducible
#超参数
# HyPEr Parameters
EPOCH = 10
BATCH_SIZE = 64
LR = 0.005 # learning rate
DOWNLOAD_MNIST = True
N_test_img = 5
#下载数据集
# Mnist digits dataset
train_dataset = torchvision.datasets.MNIST(
root='./mnist/',
train=True, # this is training data
transform=torchvision.transforms.ToTensor(),
download=DOWNLOAD_MNIST, # download it if you don't have it
)
# plot one example
print(train_dataset.train_data.size()) # (60000, 28, 28)
print(train_dataset.train_labels.size()) # (60000)
plt.imshow(train_dataset.train_data[2].numpy(), cmap='gray')
plt.title('%i' % train_dataset.train_labels[2])
plt.show()
# Data Loader for easy mini-batch return in training, the image batch Shape will be (50, 1, 28, 28)
train_loader = Data.DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, shuffle=True)
#模型
class AutoEncoder(nn.Module):
def __init__(self):
super(AutoEncoder, self).__init__()
self.encoder = nn.Sequential(
nn.Linear(28*28, 128),
nn.Tanh(),
nn.Linear(128, 64),
nn.Tanh(),
nn.Linear(64, 12),
nn.Tanh(),
nn.Linear(12, 3), # comPress to 3 features which can be Visualized in plt
)
self.decoder = nn.Sequential(
nn.Linear(3, 12),
nn.Tanh(),
nn.Linear(12, 64),
nn.Tanh(),
nn.Linear(64, 128),
nn.Tanh(),
nn.Linear(128, 28*28),
nn.Sigmoid(), # compress to a range (0, 1)
)
def forward(self, x):
encoded = self.encoder(x)
decoded = self.decoder(encoded)
return encoded, decoded
autoencoder = AutoEncoder().cuda()
optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)
loss_func = nn.MSELoss()
# initialize figure
f, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))
plt.ion() # continuously plot
# original data (First row) for viewing
view_data = train_dataset.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.
for i in range(N_TEST_IMG):
a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())
for epoch in range(EPOCH):
for step, (x, b_label) in enumerate(train_loader):
b_x = x.view(-1, 28*28).cuda() # batch x, shape (batch, 28*28)
b_y = x.view(-1, 28*28).cuda() # batch y, shape (batch, 28*28)
encoded, decoded = autoencoder(b_x)
loss = loss_func(decoded, b_y) # mean square error
optimizer.zero_grad() # clear gradients for this training step
loss.backward() # backpropagation, compute gradients
optimizer.step() # apply gradients
if step % 100 == 0:
print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy())
# plotting decoded image (second row)
_, decoded_data = autoencoder(view_data)
for i in range(N_TEST_IMG):
a[1][i].clear()
a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray')
a[1][i].set_xticks(()); a[1][i].set_yticks(())
plt.draw(); plt.pause(0.05)
plt.ioff()
plt.show()
# visualize in 3D plot
view_data = train_dataset.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.
encoded_data, _ = autoencoder(view_data)
fig = plt.figure(2); ax = Axes3D(fig)
X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()
values = train_dataset.train_labels[:200].numpy()
for x, y, z, s in zip(X, Y, Z, values):
c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)
ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())
plt.show()
#导入实验需要的包import torchimport torch.nn as nnimport torch.utils.data as Dataimport torchvisionimport matplotlib.pyplot as pltfrom mpl_toolkits.mplot3d import Axes3Dfrom matplotlib import cmimport numpy as np# torch.manual_seed(1) # reproducible#超参数# Hyper ParametersEPOCH = 10BATCH_SIZE = 64LR = 0.005 # learning rateDOWNLOAD_MNIST = TrueN_TEST_IMG = 5#下载数据集# Mnist digits datasettrain_dataset = torchvision.datasets.MNIST( root='./mnist/',train=True, # this is training datatransform=torchvision.transforms.ToTensor(),download=DOWNLOAD_MNIST, # download it if you don't have it)# plot one exampleprint(train_dataset.train_data.size()) # (60000, 28, 28)print(train_dataset.train_labels.size()) # (60000)plt.imshow(train_dataset.train_data[2].numpy(), cmap='gray')plt.title('%i' % train_dataset.train_labels[2])plt.show()# Data Loader for easy mini-batch return in training, the image batch shape will be (50, 1, 28, 28)train_loader = Data.DataLoader(dataset=train_dataset, batch_size=BATCH_SIZE, shuffle=True)#模型class AutoEncoder(nn.Module): def __init__(self): super(AutoEncoder, self).__init__() self.encoder = nn.Sequential( nn.Linear(28*28, 128),nn.Tanh(),nn.Linear(128, 64),nn.Tanh(),nn.Linear(64, 12),nn.Tanh(),nn.Linear(12, 3), # compress to 3 features which can be visualized in plt) self.decoder = nn.Sequential( nn.Linear(3, 12),nn.Tanh(),nn.Linear(12, 64),nn.Tanh(),nn.Linear(64, 128),nn.Tanh(),nn.Linear(128, 28*28),nn.Sigmoid(), # compress to a range (0, 1)) def forward(self, x): encoded = self.encoder(x) decoded = self.decoder(encoded) return encoded, decodedautoencoder = AutoEncoder().cuda()optimizer = torch.optim.Adam(autoencoder.parameters(), lr=LR)loss_func = nn.MSELoss()# initialize figuref, a = plt.subplots(2, N_TEST_IMG, figsize=(5, 2))plt.ion() # continuously plot# original data (first row) for viewingview_data = train_dataset.train_data[:N_TEST_IMG].view(-1, 28*28).type(torch.FloatTensor)/255.for i in range(N_TEST_IMG): a[0][i].imshow(np.reshape(view_data.data.numpy()[i], (28, 28)), cmap='gray'); a[0][i].set_xticks(()); a[0][i].set_yticks(())for epoch in range(EPOCH): for step, (x, b_label) in enumerate(train_loader): b_x = x.view(-1, 28*28).cuda() # batch x, shape (batch, 28*28)b_y = x.view(-1, 28*28).cuda() # batch y, shape (batch, 28*28)encoded, decoded = autoencoder(b_x) loss = loss_func(decoded, b_y) # mean square erroroptimizer.zero_grad() # clear gradients for this training steploss.backward() # backpropagation, compute gradientsoptimizer.step() # apply gradientsif step % 100 == 0: print('Epoch: ', epoch, '| train loss: %.4f' % loss.data.numpy()) # plotting decoded image (second row)_, decoded_data = autoencoder(view_data) for i in range(N_TEST_IMG): a[1][i].clear() a[1][i].imshow(np.reshape(decoded_data.data.numpy()[i], (28, 28)), cmap='gray') a[1][i].set_xticks(()); a[1][i].set_yticks(()) plt.draw(); plt.pause(0.05)plt.ioff()plt.show()# visualize in 3D plotview_data = train_dataset.train_data[:200].view(-1, 28*28).type(torch.FloatTensor)/255.encoded_data, _ = autoencoder(view_data)fig = plt.figure(2); ax = Axes3D(fig)X, Y, Z = encoded_data.data[:, 0].numpy(), encoded_data.data[:, 1].numpy(), encoded_data.data[:, 2].numpy()values = train_dataset.train_labels[:200].numpy()for x, y, z, s in zip(X, Y, Z, values): c = cm.rainbow(int(255*s/9)); ax.text(x, y, z, s, backgroundcolor=c)ax.set_xlim(X.min(), X.max()); ax.set_ylim(Y.min(), Y.max()); ax.set_zlim(Z.min(), Z.max())plt.show()
以上是脚本宝典为你收集整理的多层自编码器手写版全部内容,希望文章能够帮你解决多层自编码器手写版所遇到的问题。
本图文内容来源于网友网络收集整理提供,作为学习参考使用,版权属于原作者。
如您有任何意见或建议可联系处理。小编QQ:384754419,请注明来意。