Skip to content

RanjeetKumbhar01/SPPU-BE-IT-DL-ASSIGNMENTS

Repository files navigation

SPPU-BE-IT-DL-ASSIGNMENTS 🚀

ViewCount

BE IT (2019 Course) || 414447: Lab Practice IV

Welcome to the repository for your deep learning assignments. Below, you'll find details for each assignment, including the task description.

Assignment 1: Study of Deep Learning Packages 📚

Document the distinct features and functionality of deep learning packages, including TensorFlow, Keras, Theano, and PyTorch.

Assignment 2: Implementing Feedforward Neural Networks with Keras and TensorFlow 🧠

Implement a feedforward neural network using Keras and TensorFlow.

a. Import the necessary packages. 📦
b. Load the training and testing data (MNIST/CIFAR10). 📂
c. Define the network architecture using Keras. 🧮
d. Train the model using SGD. 🚀
e. Evaluate the network. 📊
f. Plot the training loss and accuracy. 📈

Assignment 3: Building an Image Classification Model 🖼️

Build an image classification model divided into four stages.

a. Loading and preprocessing the image data. 🖼️
b. Defining the model's architecture. 🏗️
c. Training the model. 📈
d. Estimating the model's performance. 📊

Assignment 4: Anomaly Detection Using Autoencoder 🕵️

Implement anomaly detection using an autoencoder.

a. Import required libraries. 📚
b. Upload/access the dataset. 📂
c. Encoder converts data into a latent representation. 🧐
d. Decoder networks convert it back to the original input. 🔄
e. Compile the models with Optimizer, Loss, and Evaluation Metrics. 📈

Assignment 5: Implementing the Continuous Bag of Words (CBOW) Model 📝

Implement the Continuous Bag of Words (CBOW) model.

a. Data preparation. 📊
b. Generate training data. 📂
c. Train the model. 🚀
d. Output. 📄

Assignment 5: Object detection using Transfer Learning of CNN architectures 📷

Datasets: Caltech-101 and CIFAR10

a. Load in a pre-trained CNN model trained on a large dataset. 📸
b. Freeze parameters(weights) in model’s lower convolutional layers. ❄️
c. Add custom classifier with several layers of trainable parameters to model. 🏗️
d. Train classifier layers on training data available for task. 📈
e. Fine-tune hyper parameters and unfreeze more layers as needed. 🚀

Requirements 🛠️

To run the code in these assignments, you need to have Python installed on your system along with the required libraries and dependencies. Make sure to install the necessary packages mentioned in the assignment files. For Tableau, you will need to have Tableau software installed on your machine.

License 📜

This project is licensed under the MIT License. Feel free to use the code and materials for educational purposes or personal projects.

Contact ✉️

If you have any questions or suggestions, please feel free to contact:

  • Email: Ranjeet - contact [dot] ranjeetkumbhar [at] gmail [dot] com

Feel free to navigate to each assignment's directory for detailed instructions, code, and any additional resources. If you have any questions or need assistance, don't hesitate to reach out. Good luck with your assignments!

Copyright © 2023 Ranjeet Kumbhar

About

BE IT (2019 Course) || 414447: Lab Practice IV

Topics

Resources

License

Stars

Watchers

Forks