Result of auto-encoder dimensions are incorrect - deep-learning

Question

Using below code I'm attempting to encode image from mnist into a lower dimension representation :
import warnings
warnings.filterwarnings('ignore')
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
from matplotlib import pyplot as plt
from sklearn import metrics
import datetime
from sklearn.preprocessing import MultiLabelBinarizer
import seaborn as sns
sns.set_style("darkgrid")
from ast import literal_eval
import numpy as np
from sklearn.preprocessing import scale
import seaborn as sns
sns.set_style("darkgrid")
import torch
import torch
import torchvision
import torch.nn as nn
from torch.autograd import Variable
%matplotlib inline
low_dim_rep = 32
epochs = 2
cuda = torch.cuda.is_available() # True if cuda is available, False otherwise
FloatTensor = torch.cuda.FloatTensor if cuda else torch.FloatTensor
print('Training on %s' % ('GPU' if cuda else 'CPU'))
# Loading the MNIST data set
transform = torchvision.transforms.Compose([torchvision.transforms.ToTensor(),
torchvision.transforms.Normalize((0.1307,), (0.3081,))])
mnist = torchvision.datasets.MNIST(root='../data/', train=True, transform=transform, download=True)
# Loader to feed the data batch by batch during training.
batch = 100
data_loader = torch.utils.data.DataLoader(mnist, batch_size=batch, shuffle=True)
encoder = nn.Sequential(
# Encoder
nn.Linear(28 * 28, 64),
nn.PReLU(64),
nn.BatchNorm1d(64),
# Low-dimensional representation
nn.Linear(64, low_dim_rep),
nn.PReLU(low_dim_rep),
nn.BatchNorm1d(low_dim_rep))
decoder = nn.Sequential(
# Decoder
nn.Linear(low_dim_rep, 64),
nn.PReLU(64),
nn.BatchNorm1d(64),
nn.Linear(64, 28 * 28))
autoencoder = nn.Sequential(encoder, decoder)
encoder = encoder.type(FloatTensor)
decoder = decoder.type(FloatTensor)
autoencoder = autoencoder.type(FloatTensor)
optimizer = torch.optim.Adam(params=autoencoder.parameters(), lr=0.00001)
data_size = int(mnist.train_labels.size()[0])
print('data_size' , data_size)
for i in range(epochs):
for j, (images, _) in enumerate(data_loader):
images = images.view(images.size(0), -1) # from (batch 1, 28, 28) to (batch, 28, 28)
images = Variable(images).type(FloatTensor)
autoencoder.zero_grad()
reconstructions = autoencoder(images)
loss = torch.dist(images, reconstructions)
loss.backward()
optimizer.step()
print('Epoch %i/%i loss %.2f' % (i + 1, epochs, loss.data[0]))
print('Optimization finished.')
# Get the encoded images here
encoded_images = []
for j, (images, _) in enumerate(data_loader):
images = images.view(images.size(0), -1)
images = Variable(images).type(FloatTensor)
encoded_images.append(encoder(images))
Upon completion of this code
len(encoded_images) is 600 when I expect the length to match the number of images in mnist : len(mnist) - 60'000.
How to encode the images to a lower dimension representation of 32 ( low_dim_rep = 32 ) ? I've defined the network parameters incorrectly ?

Answer 1

You have 60000 images in mnist and your batch = 100. That is why your len(encoded_images)=600 because you do 60000/100=600 iterations when generating encoded image. You end up with a list of 600 elements where each element has shape [100, 32]. You can do the following
encoded_images = torch.zeros(len(mnist), 32)
for j, (images, _) in enumerate(data_loader):
images = images.view(images.size(0), -1)
images = Variable(images).type(FloatTensor)
encoded_images[j * batch : (j+1) * batch] = encoder(images)