Scribd
Upload
16 views1 page

Lab in Sem - Deep Learning Using Python

The document outlines a lab exam for a Deep Learning course using Python, consisting of two main questions. The first question involves building a CNN model with data augmentation techniques for image classification using the CIFAR-10 dataset. The second question focuses on developing an RNN model with LSTM cells for sentiment analysis on movie reviews using PyTorch, including an evaluation of hyperparameter impacts on model accuracy.

Uploaded by

balajibk333
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views1 page

Lab in Sem - Deep Learning Using Python

The document outlines a lab exam for a Deep Learning course using Python, consisting of two main questions. The first question involves building a CNN model with data augmentation techniques for image classification using the CIFAR-10 dataset. The second question focuses on developing an RNN model with LSTM cells for sentiment analysis on movie reviews using PyTorch, including an evaluation of hyperparameter impacts on model accuracy.

Uploaded by

balajibk333
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 1

22DS6216OJ DEEP LEARNING USING PYTHON

LAB-IN SEM EXAM

Question 1: Image Classification with Data Augmentation (25 marks)

 Task: Build a CNN model using TensorFlow/Keras to classify images from the
CIFAR-10 dataset. Implement data augmentation techniques (e.g., random cropping,
flipping, rotation) to improve model performance. Evaluate the model's accuracy on a
test set and compare the results with and without data augmentation.

Question 2: Sentiment Analysis with RNN and LSTM (25 marks)

 Task: Develop an RNN model with LSTM cells using PyTorch to perform sentiment
analysis on movie reviews. Train the model on a labeled dataset (e.g., IMDB movie
reviews) and evaluate its performance in classifying reviews as positive or negative.
Analyze the impact of different hyperparameters (e.g., number of LSTM layers,
dropout rate) on the model's accuracy.

You might also like