CODEWITHSUNDEEP
pytorch
JAEMTO
JAEMTO

Reputation: 219

I want to see data from torch.utils.data.DataLoader. How Can I?

import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
import torchvision
import torchvision.transforms as transforms

train_set = torchvision.datasets.MNIST(root = './data/MNIST',train = True,download = True,\transform = transfroms.Compose([transfroms.ToTensor()])

print(len(train_set))
# 60000

train_loader = torch.utils.data.DataLoader(train_set, batch_size=100)
print(len(train_loader))
# 600

It seems like because of the batch_size, length of train_loader decreased.

I think there are 100 tensors and one classification in a batch. I just want to see the elements or shape of it. How can I do? Also,

### Model Omitted ###
model = ConvNet().to(device) 
criterion = nn.CrossEntropyLoss().to(device)
optimizer = torch.optim.Adam(model.parameters(), lr = learning_rate)

for epoch in range(5): 
    avg_cost = 0
    for data, target in train_loader:
        data = data.to(device)
        target = target.to(device)
        optimizer.zero_grad() 
        hypothesis = model(data) 
        cost = criterion(hypothesis, target) 
        cost.backward() 
        optimizer.step() 
        avg_cost += cost / len(train_loader)

    print('[Epoch: {:>4}] cost = {:>.9}'.format(epoch + 1, avg_cost))

I think the training per epoch trains with 60,000 tensors right? Then I think the avg_cost should be divided by 60,000, not 600(which is len(train_loader))... Am I wrong with it?

Upvotes: 1

Views: 3049

Answers (1)

yakhyo
yakhyo

Reputation: 1656

You can get one batch of train data from trainloader using the code below and you can easily check it's shape. I hope this may help to get what you want.

batch= iter(trainloader)
images, labels = batch.next()

print(images.shape)
# torch.Size([num_samples, in_channels, H, W])

print(labels.shape)

Upvotes: 2

Related Questions