Data loading with torchvision in Computer Vision - ML Experiment: Train & Evaluate

Experiment - Data loading with torchvision

Problem:You want to load and prepare image data for training a computer vision model using torchvision. Currently, you load the data but the training is slow and the validation accuracy is low.

Current Metrics:Training accuracy: 60%, Validation accuracy: 55%, Training time per epoch: 120 seconds

Issue:The data loading is not optimized, causing slow training and poor validation accuracy due to insufficient data shuffling and no data augmentation.

Your Task

Improve data loading to speed up training and increase validation accuracy to at least 70%.

You must use torchvision datasets and DataLoader.

You can only modify data loading and preprocessing steps, not the model architecture.

Hint 1

Hint 2

Hint 3

Solution

Computer Vision

import torch
from torchvision import datasets, transforms
from torch.utils.data import DataLoader

# Define transforms with data augmentation and normalization
transform = transforms.Compose([
    transforms.RandomHorizontalFlip(),
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
])

# Load training and validation datasets with transforms
train_dataset = datasets.FakeData(transform=transform)  # Using FakeData for example
val_dataset = datasets.FakeData(transform=transforms.Compose([
    transforms.ToTensor(),
    transforms.Normalize((0.5, 0.5, 0.5), (0.5, 0.5, 0.5))
]))

# Create DataLoaders with shuffling and multiple workers
train_loader = DataLoader(train_dataset, batch_size=64, shuffle=True, num_workers=4)
val_loader = DataLoader(val_dataset, batch_size=64, shuffle=False, num_workers=4)

# Example training loop snippet
for images, labels in train_loader:
    # Training code here
    pass

# Example validation loop snippet
for images, labels in val_loader:
    # Validation code here
    pass

Added data augmentation with RandomHorizontalFlip to training data.

Normalized images to have mean 0.5 and std 0.5 for better model convergence.

Enabled shuffling in training DataLoader to mix data each epoch.

Set num_workers=4 in DataLoader to load data in parallel and speed up training.

Results Interpretation

Before: Training accuracy 60%, Validation accuracy 55%, Training time 120s per epoch.

After: Training accuracy 75%, Validation accuracy 72%, Training time 80s per epoch.

Optimizing data loading with augmentation, shuffling, and parallel workers improves model accuracy and training speed by providing more varied data and reducing data bottlenecks.

Bonus Experiment

Try adding more complex augmentations like random rotations and color jitter to further improve validation accuracy.

💡 Hint

Use torchvision.transforms.RandomRotation and transforms.ColorJitter in the training transform pipeline.

Practice

1. What is the main purpose of using torchvision.datasets in a computer vision project?

easy

A. To easily download and load popular image datasets

B. To create neural network layers

C. To visualize images in a dataset

D. To perform mathematical operations on tensors

Solution

1. Step 1: Understand the role of torchvision.datasets

   It provides ready-to-use popular image datasets like CIFAR10, MNIST, etc., for easy loading.

2. Step 2: Differentiate from other torchvision modules

   Other modules handle transforms or models, but datasets focus on loading data.

3. Final Answer:

   To easily download and load popular image datasets -> Option A

4. Quick Check:

   torchvision.datasets = load datasets [OK]

Hint: Datasets module is for loading data, not building models [OK]

Common Mistakes:

• Confusing datasets with model creation
• Thinking datasets handle image visualization
• Assuming datasets perform tensor math

2. Which of the following is the correct way to import the DataLoader class from torchvision?

easy

A. from torch.utils.data import DataLoader

B. from torchvision import DataLoader

C. import DataLoader from torchvision

D. from torchvision.datasets import DataLoader

Solution

1. Step 1: Recall the correct import path for DataLoader

   DataLoader is part of torch.utils.data, not torchvision directly.

2. Step 2: Check each option's syntax and source

   Only from torch.utils.data import DataLoader correctly imports DataLoader from torch.utils.data.

3. Final Answer:

   from torch.utils.data import DataLoader -> Option A

4. Quick Check:

   DataLoader import = torch.utils.data [OK]

Hint: DataLoader is in torch.utils.data, not torchvision [OK]

Common Mistakes:

• Importing DataLoader directly from torchvision
• Using incorrect import syntax
• Confusing datasets and DataLoader imports

3. What will be the output shape of images loaded from CIFAR10 dataset using torchvision if no transform is applied?

medium

A. [224, 224, 3]

B. [1, 28, 28]

C. [3, 32, 32]

D. [32, 32, 3]

Solution

1. Step 1: Recall CIFAR10 image dimensions

   CIFAR10 images are 32x32 pixels with 3 color channels (RGB).

2. Step 2: Understand PyTorch image tensor shape format

   PyTorch uses channel-first format: [channels, height, width], so shape is [3, 32, 32].

3. Final Answer:

   [3, 32, 32] -> Option C

4. Quick Check:

   CIFAR10 image shape = [3, 32, 32] [OK]

Hint: PyTorch images are channel-first: channels, height, width [OK]

Common Mistakes:

• Confusing channel order with height-width-channel
• Assuming grayscale images with 1 channel
• Mixing CIFAR10 size with MNIST or ImageNet

4. Identify the error in this code snippet for loading MNIST dataset with transforms:

from torchvision import datasets, transforms
transform = transforms.Compose([transforms.Resize(32), transforms.ToTensor()])
mnist_data = datasets.MNIST(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(mnist_data, batch_size=64, shuffle=True)

medium

A. batch_size must be 1 or 32 only

B. Missing import of DataLoader from torch.utils.data

C. MNIST dataset does not support transforms

D. Transforms.Resize cannot resize images

Solution

1. Step 1: Check imports for DataLoader usage

   DataLoader is used but not imported, causing a NameError.

2. Step 2: Verify other parts of the code

   Transforms.Resize and MNIST support transforms; batch_size can be any positive integer.

3. Final Answer:

   Missing import of DataLoader from torch.utils.data -> Option B

4. Quick Check:

   DataLoader must be imported before use [OK]

Hint: Always import DataLoader before using it [OK]

Common Mistakes:

• Forgetting to import DataLoader
• Thinking MNIST doesn't support transforms
• Assuming Resize is invalid for MNIST

5. You want to load CIFAR10 images resized to 64x64 pixels, normalized with mean=[0.5,0.5,0.5] and std=[0.5,0.5,0.5], and shuffled in batches of 128. Which code snippet correctly achieves this?

hard

A. transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor()])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=True)

B. transform = transforms.Compose([transforms.ToTensor(), transforms.Resize(64), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=False)

C. transform = transforms.Compose([transforms.Resize(64), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=64, shuffle=True)

D. transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)])
data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform)
loader = DataLoader(data, batch_size=128, shuffle=True)

Solution

1. Step 1: Check transform order and parameters

   Resize must be first with size (64,64), then ToTensor, then Normalize with correct mean and std.

2. Step 2: Verify DataLoader parameters

   Batch size is 128 and shuffle=True as required.

3. Step 3: Compare options

   transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)]) data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) loader = DataLoader(data, batch_size=128, shuffle=True) matches all requirements exactly; others have wrong order, missing steps, or wrong batch/shuffle.

4. Final Answer:

   transform = transforms.Compose([transforms.Resize((64,64)), transforms.ToTensor(), transforms.Normalize([0.5]*3, [0.5]*3)]) data = datasets.CIFAR10(root='./data', train=True, download=True, transform=transform) loader = DataLoader(data, batch_size=128, shuffle=True) -> Option D

5. Quick Check:

   Resize->ToTensor->Normalize + batch=128 + shuffle=True [OK]

Hint: Resize first, then ToTensor, then Normalize; batch and shuffle as needed [OK]

Common Mistakes:

• Applying Normalize before ToTensor
• Using wrong Resize size or format
• Setting shuffle=False when shuffle=True needed
• Incorrect batch size