Python / Python Deep Learning and Neural Networks Interview Questions

What is the difference between model.eval(), torch.no_grad(), and torch.inference_mode()? When do you use each?

These three mechanisms serve different but complementary purposes that are often confused. Understanding the distinction prevents subtle bugs in training, validation, and inference code.

eval vs no_grad vs inference_mode
Mechanism	What it controls	Effect
model.eval()	Layer behaviour (Dropout, BatchNorm)	Disables Dropout; BatchNorm uses running stats instead of batch stats
model.train()	Layer behaviour (Dropout, BatchNorm)	Enables Dropout; BatchNorm uses current batch stats
torch.no_grad()	Gradient tracking	Stops building the computation graph; saves memory; tensors cannot call .backward()
torch.inference_mode()	Gradient tracking + view tracking	Stricter than no_grad; ~10% faster; returned tensors cannot be used in autograd at all

import torch
import torch.nn as nn

model = nn.Sequential(
    nn.Linear(10, 64), nn.ReLU(),
    nn.BatchNorm1d(64), nn.Dropout(0.5),
    nn.Linear(64, 1)
)

# âââ Training âââââââââââââââââââââââââââââââââââââââââââââââââââââââ
model.train()   # Dropout ACTIVE, BatchNorm uses batch stats
x = torch.randn(32, 10)
out1 = model(x)
out2 = model(x)  # DIFFERENT â Dropout randomly drops each call

# âââ Validation (compute val loss, need backward later? No) âââââââââ
model.eval()
with torch.no_grad():
    # Dropout OFF, BatchNorm uses running stats, no computation graph
    val_out = model(x)
    val_loss = nn.MSELoss()(val_out, torch.zeros(32, 1))

# âââ Inference / deployment âââââââââââââââââââââââââââââââââââââââââ
model.eval()
with torch.inference_mode():  # fastest; cannot go back to autograd
    pred = model(torch.randn(1, 10))

# COMMON BUG: forgetting model.eval() at inference
# model.eval() and torch.no_grad() are INDEPENDENT â you need BOTH:
# - model.eval() alone: still builds graph (memory waste)
# - torch.no_grad() alone: Dropout still active (wrong predictions)

Take quiz

What happens if you call model.eval() but forget torch.no_grad() during validation?Dropout and BatchNorm remain in training mode

✗ Try again.

The model still builds the computation graph (tracking all operations for potential gradients), wasting memory — but layer behaviours like Dropout and BatchNorm are correctly switched to eval mode

✓ Correct! Well done.

The model raises a RuntimeError

✗ Try again.

Gradients flow through the validation batch and corrupt the model weights

✗ Try again.

What does BatchNorm do differently in eval mode vs train mode?In eval mode, BatchNorm learns faster by using a larger batch

✗ Try again.

In train mode, BatchNorm normalises using the current mini-batch's mean and variance; in eval mode, it uses running statistics accumulated as exponential moving averages over all training batches — providing stable, batch-size-independent normalisation at inference

✓ Correct! Well done.

In eval mode, BatchNorm's learnable parameters gamma and beta are set to 1 and 0

✗ Try again.

In eval mode, BatchNorm is bypassed entirely for speed

✗ Try again.

More Related questions...

What is a neural network and how does forward propagation work mathematically? Explain backpropagation mathematically. How does the chain rule enable computing gradients through many layers? What are the most common activation functions and why did ReLU replace sigmoid/tanh as the default? What are vanishing and exploding gradients, and what techniques are used to address them? Why does weight initialization matter in neural networks, and what is the difference between Xavier and He initialization? How does Batch Normalization work mathematically and why does it stabilize training? Compare SGD, SGD with momentum, RMSProp, and Adam optimizers. When do you choose each? How does Dropout work mathematically, and why does it act as regularization? Explain how convolutional layers work and why they are well-suited to image data. How do RNNs work and why did LSTMs solve the long-range dependency problem? What is the self-attention mechanism in Transformers and why did it replace RNNs for sequence modeling? What loss functions does PyTorch provide for classification and regression, and which to use when? What is transfer learning and how do you fine-tune a pretrained model in PyTorch? How does PyTorch's Dataset and DataLoader pipeline work, and what are the key performance considerations? Why is learning rate scheduling important and what are the most common strategies? What are the most effective regularization strategies for deep learning and how do they differ from classical ML regularization? What are embedding layers in deep learning and how are they different from one-hot encoding? How do you save and load PyTorch models correctly, and what is included in a proper checkpoint? What is mixed precision training and how does it speed up deep learning with torch.cuda.amp? What is the difference between model.eval(), torch.no_grad(), and torch.inference_mode()? When do you use each? How do you use GPUs in PyTorch and what are the key patterns for writing device-agnostic code? What are the differences between Batch Norm, Layer Norm, Group Norm, and Instance Norm? What is an autoencoder and what can a well-trained latent space be used for? How do you diagnose a neural network that is not training correctly from its loss curves? What is the mathematical setup of a Generative Adversarial Network (GAN) and what training challenges do they have? What is torch.compile and how does it speed up PyTorch model execution? Why do Transformers need positional encodings and how does sinusoidal encoding work? What are the most impactful hyperparameters to tune in deep learning and what is the recommended search order? What is an encoder-decoder architecture and how is it used for sequence-to-sequence tasks? What is model quantization in deep learning and how does PyTorch support it? What does a production-quality PyTorch training loop look like, incorporating all best practices? How does batch size affect deep learning training mathematically and practically? How do you choose the right layer type (Linear, Conv, Attention) for a given input modality? What evaluation metrics are most commonly used in deep learning tasks and how do you implement them in PyTorch? How do you export a PyTorch model for production deployment using TorchScript or ONNX? What is knowledge distillation and how does it compress large neural networks into smaller ones? What is self-supervised learning and how do contrastive methods like SimCLR learn representations? How would you implement and train a simple feedforward neural network in PyTorch from scratch, without using nn.Sequential?

Show more question and Answers...

Python Modern Generative AI and Agents Interview Questions

	Interviews Questions Java Spring Hibernate DevOps Testing API BigData Web Erlang AI Database Integration Cloud Python Scala Tools Golang SAP	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. Privacy Policy · Terms of Service.

Python / Python Deep Learning and Neural Networks Interview Questions

What is the difference between model.eval(), torch.no_grad(), and torch.inference_mode()? When do you use each?

Comments & Discussions

Recently added questions