Prev Next

Python / PyTorch Fundamentals Interview Questions

What is Batch Normalization in PyTorch and how does it differ from Layer Normalization?

Normalization layers stabilise training by re-centring and re-scaling activations. PyTorch provides several variants; Batch Normalization (BatchNorm) and Layer Normalization (LayerNorm) are the two most widely used, but they normalise over different dimensions and suit different architectures.

BatchNorm vs LayerNorm
FeatureBatchNorm (nn.BatchNorm1d/2d)LayerNorm (nn.LayerNorm)
Normalises overBatch dimension (per-feature statistics)Feature dimension (per-sample statistics)
Statistics at trainComputed from current mini-batchComputed from current sample's features
Statistics at evalUses running mean/var accumulated during trainingAlways computed fresh from current input
Batch size dependencyNoisy with very small batches (< 8)Independent of batch size — works with batch=1
Best forCNNs (image models)Transformers, RNNs, NLP models
Parametersgamma (scale), beta (shift) per featureSame, but normalised per sample
;
import torch
import torch.nn as nn

# ── BatchNorm — for feedforward / CNN models
class BNModel(nn.Module):
    def __init__(self):
        super().__init__()
        self.fc1 = nn.Linear(20, 64)
        self.bn1 = nn.BatchNorm1d(64)   # 64 features
        self.fc2 = nn.Linear(64, 10)

    def forward(self, x):
        x = torch.relu(self.bn1(self.fc1(x)))
        return self.fc2(x)

# BatchNorm behaves differently in train vs eval mode!
# train: normalise using batch mean/var, update running stats
# eval:  use accumulated running_mean / running_var
model = BNModel()
model.train()   # must be in train mode during training!

# ── LayerNorm — for transformers and sequence models
class LNModel(nn.Module):
    def __init__(self, d_model=64):
        super().__init__()
        self.fc1 = nn.Linear(20, d_model)
        self.ln1 = nn.LayerNorm(d_model)   # normalise over last dim
        self.fc2 = nn.Linear(d_model, 10)

    def forward(self, x):
        x = torch.relu(self.ln1(self.fc1(x)))
        return self.fc2(x)

# LayerNorm produces the SAME result at train and eval
ln_model = LNModel()
ln_model.train()
x = torch.randn(8, 20)
out_train = ln_model(x)
ln_model.eval()
out_eval  = ln_model(x)
print(torch.allclose(out_train, out_eval))  # True — LayerNorm is mode-independent!

Common bug: forgetting to call model.train() before training and model.eval() before validation when using BatchNorm — at eval, it uses accumulated running statistics, and if these were never updated (because the model was always in eval mode), predictions will be incorrect.

Why does BatchNorm produce different outputs depending on whether the model is in train() or eval() mode?
For which type of architecture is LayerNorm preferred over BatchNorm, and why?

More Related questions...

What is PyTorch and what are its key advantages over other deep learning frameworks? What is a PyTorch tensor and how does it differ from a NumPy array? What are the most important tensor operations in PyTorch? What are tensor data types (dtypes) in PyTorch and why do they matter? How does broadcasting work in PyTorch and what are the rules? What is autograd in PyTorch and how does it compute gradients? What is the computation graph in PyTorch and how does the dynamic graph differ from a static graph? How do torch.no_grad() and tensor.detach() differ, and when do you use each? What is nn.Module and how do you build a custom neural network in PyTorch? What are nn.Sequential and other container modules in PyTorch? What built-in layers does PyTorch's nn module provide and how do you use the most common ones? What are activation functions in PyTorch and how do you apply them? What are the most important loss functions in PyTorch and when do you use each? What optimizers does PyTorch provide and how do you configure them? What are learning rate schedulers in PyTorch and how do you use them? What are the most common built-in layers in torch.nn and what do they do? How do you initialise weights in a PyTorch model? What loss functions does PyTorch provide and when do you use each? What optimizers does PyTorch provide and how do you choose between them? What are learning rate schedulers in PyTorch and how do you use them? What activation functions are commonly used in PyTorch and how do you choose between them? What loss functions does PyTorch provide and how do you choose the right one? What optimizers does PyTorch provide and what is the difference between SGD, Adam, and AdamW? What is the standard PyTorch training loop and what does each step do? What are Dataset and DataLoader in PyTorch and how do they work together? How do you move tensors and models between CPU and GPU in PyTorch? What is the difference between model.parameters() and model.state_dict() in PyTorch? How do you save and load PyTorch models correctly, including full training checkpoints? What is overfitting and what regularization techniques does PyTorch support to address it? What is the vanishing/exploding gradient problem and how do you detect and fix it in PyTorch? What is weight initialization in PyTorch and why does it matter? What is the difference between nn.Parameter and a regular tensor attribute in nn.Module? How do you implement and use learning rate schedulers in PyTorch? How do you debug a PyTorch training loop where the loss is not decreasing or is NaN? What is the difference between torch.tensor() and torch.Tensor() (capital T) for creating tensors? How does gradient accumulation work in PyTorch and when would you use it? What is mixed precision training in PyTorch and how do you implement it with torch.cuda.amp? What is torch.compile() and how does it speed up PyTorch model execution? What is the difference between batch size, epoch, and iteration in PyTorch training? How do you compute and track evaluation metrics like accuracy during PyTorch training? What is the purpose of torch.manual_seed() and how do you ensure reproducibility in PyTorch? How does PyTorch handle multi-dimensional indexing and slicing of tensors? What is the difference between.view(),.reshape(), and.contiguous() in PyTorch, and why does it matter? How do you freeze layers and perform transfer learning / fine-tuning in PyTorch? What is the purpose of torch.utils.data.random_split() and how do you create train/validation/test splits in PyTorch? What is Batch Normalization in PyTorch and how does it differ from Layer Normalization? How do you implement and use a custom loss function in PyTorch? What is torch.compile() vs TorchScript and how do you export a PyTorch model for production deployment?
Show more question and Answers...

Uvicorn Fundamentals Interview Questions

Comments & Discussions

Interviews Questions

About Javapedia.net

Javapedia.net is for Java and J2EE developers, technologist and college students who prepare of interview. Also this site includes many practical examples.

This site is developed using J2EE technologies by Steve Antony, a senior Developer/lead at one of the logistics based company.

Follow Javapedia updates

contact: javatutorials2016[at]gmail[dot]com

Kindly consider donating for maintaining this website. Thanks.

Copyright © 2026, javapedia.net, all rights reserved. · .

DMCA.com Protection Status