Custom Dataset class in PyTorch - Model Metrics & Evaluation

Metrics & Evaluation - Custom Dataset class

Which metric matters for Custom Dataset class and WHY

When using a custom dataset class in PyTorch, the main goal is to ensure your data loads correctly and efficiently. While this is not a model metric, the key "metric" is data integrity and loading speed. You want to confirm that your dataset class returns the right data samples and labels without errors or delays. This ensures your model training uses the correct inputs and runs smoothly.

Confusion matrix or equivalent visualization

Since a custom dataset class is about data handling, not predictions, a confusion matrix does not apply here. Instead, you can check your dataset by printing sample outputs and their labels to verify correctness.

Sample output from dataset:
Index: 0
Image shape: (3, 224, 224)
Label: 2

Index: 1
Image shape: (3, 224, 224)
Label: 0

... (and so on)

Tradeoff: Data loading speed vs memory usage

When designing a custom dataset, you often trade off between loading all data into memory (fast access but high memory use) or loading data on demand (low memory but slower). For example, loading all images at once speeds up training but needs more RAM. Loading images one by one saves memory but can slow training if disk access is slow.

What "good" vs "bad" looks like for a custom dataset class

Good: Dataset returns correct data and labels, no crashes, consistent data shapes, and loads data quickly enough to keep training smooth.

Bad: Dataset returns wrong labels, crashes on some indexes, inconsistent data shapes, or is too slow causing training to stall.

Common pitfalls when creating a custom dataset class

• Not implementing __len__ or __getitem__ correctly, causing errors.
• Returning data in wrong format or shape, confusing the model.
• Mixing up labels and data order.
• Loading all data into memory unintentionally, causing crashes.
• Not handling file paths or corrupt files gracefully.

Self-check question

Your custom dataset class loads images and labels. You notice training is very slow and sometimes crashes with memory errors. What might be wrong?

Answer: Your dataset might be loading all data into memory at once, using too much RAM. Consider loading data on demand in __getitem__ to reduce memory use and speed up training.

Key Result

For a custom dataset class, the key metric is correct and efficient data loading to ensure smooth model training.

Practice

1. What is the main purpose of creating a Custom Dataset class in PyTorch?

easy

A. To visualize data samples

B. To organize and provide access to data samples for model training

C. To perform gradient descent optimization

D. To define the neural network architecture

Solution

1. Step 1: Understand Dataset role

   A Custom Dataset class is designed to organize data and provide easy access to samples during training.

2. Step 2: Differentiate from other components

   Neural network architecture and optimization are handled elsewhere, not by the Dataset class.

3. Final Answer:

   To organize and provide access to data samples for model training -> Option B

4. Quick Check:

   Dataset class = data access [OK]

Hint: Dataset class organizes data for training access [OK]

Common Mistakes:

• Confusing Dataset with model definition
• Thinking Dataset handles optimization
• Assuming Dataset visualizes data

2. Which method must be implemented in a PyTorch Custom Dataset class to return the number of samples?

easy

A. __getitem__

B. __init__

C. __len__

D. forward

Solution

1. Step 1: Recall Dataset methods

   __len__ returns the total number of samples in the dataset.

2. Step 2: Identify other methods' roles

   __getitem__ fetches a sample, __init__ initializes the dataset, forward is for models, not datasets.

3. Final Answer:

   __len__ -> Option C

4. Quick Check:

   Count samples = __len__ [OK]

Hint: Count samples with __len__ method [OK]

Common Mistakes:

• Using __getitem__ to get length
• Confusing __init__ with length method
• Using forward method in Dataset

3. Given this Custom Dataset code, what will print(len(dataset)) output?

import torch
from torch.utils.data import Dataset

class MyDataset(Dataset):
    def __init__(self):
        self.data = [10, 20, 30, 40]
    def __len__(self):
        return len(self.data)
    def __getitem__(self, idx):
        return self.data[idx]

dataset = MyDataset()

medium

A. 4

B. 3

C. 40

D. Error

Solution

1. Step 1: Check __len__ method

   __len__ returns length of self.data, which is a list of 4 elements.

2. Step 2: Evaluate print output

   Calling len(dataset) calls __len__, so output is 4.

3. Final Answer:

   4 -> Option A

4. Quick Check:

   len([10,20,30,40]) = 4 [OK]

Hint: len(dataset) calls __len__ returning data length [OK]

Common Mistakes:

• Confusing length with last element value
• Expecting __getitem__ output instead of length
• Assuming error without checking code

4. Identify the error in this Custom Dataset class:

from torch.utils.data import Dataset

class SampleDataset(Dataset):
    def __init__(self, data):
        self.data = data
    def __len__(self):
        return self.data
    def __getitem__(self, idx):
        return self.data[idx]

sample = SampleDataset([1,2,3])
print(len(sample))

medium

A. Missing __init__ method

B. __getitem__ returns wrong index

C. Dataset class not imported

D. __len__ returns data list instead of its length

Solution

1. Step 1: Analyze __len__ method

   __len__ returns self.data, which is a list, not an integer length.

2. Step 2: Understand len() requirement

   len() expects __len__ to return an integer. Returning a list causes a TypeError.

3. Final Answer:

   __len__ returns data list instead of its length -> Option D

4. Quick Check:

   __len__ must return int, not list [OK]

Hint: __len__ must return integer length [OK]

Common Mistakes:

• Returning data list instead of length in __len__
• Ignoring import statements
• Confusing __getitem__ with __len__

5. You want to create a Custom Dataset class that returns both input features and labels from two separate lists. Which implementation correctly achieves this?

hard

A. class MyDataset(Dataset):
def __init__(self, inputs, labels):
self.inputs = inputs
self.labels = labels
def __len__(self):
return len(self.inputs)
def __getitem__(self, idx):
return self.inputs[idx], self.labels[idx]

B. class MyDataset(Dataset):
def __init__(self, inputs, labels):
self.data = inputs + labels
def __len__(self):
return len(self.data)
def __getitem__(self, idx):
return self.data[idx]

C. class MyDataset(Dataset):
def __init__(self, inputs, labels):
self.inputs = inputs
self.labels = labels
def __len__(self):
return len(self.labels)
def __getitem__(self, idx):
return self.inputs[idx]

D. class MyDataset(Dataset):
def __init__(self, inputs, labels):
self.inputs = inputs
self.labels = labels
def __len__(self):
return len(self.inputs)
def __getitem__(self, idx):
return self.labels[idx]

Solution

1. Step 1: Check __init__ and __len__ consistency

   The correct implementation stores inputs and labels separately and returns length of inputs in __len__, assuming matching lengths with labels.

2. Step 2: Verify __getitem__ returns both features and labels

   The correct __getitem__ returns a tuple (self.inputs[idx], self.labels[idx]) for supervised learning.

3. Final Answer:

   return self.inputs[idx], self.labels[idx] -> Option A

4. Quick Check:

   Return (input, label) tuple in __getitem__ [OK]

Hint: Return (input, label) tuple in __getitem__ [OK]

Common Mistakes:

• Combining inputs and labels into one list
• Returning only inputs or only labels
• Mismatched lengths in __len__