Deep Learning

Welcome to my Deep Learning repository! This collection showcases my work in the field of deep learning, including various projects and implementations. Feel free to explore the following notebooks

List:

1. Alziemer's detetction

2. Anti-cancer cell detetction

File: Anti-cancer cell detetction

Description: This project focuses on asteroid hazard classification using deep learning techniques. The notebook explores the application of neural networks for identifying potential asteroid threats.It also includes asteroid Hazard Classification and Orbit Clustering.

• Code:

Notebook	Description
Asteroid_Hazard_Classification.ipynb	Sequential Classification model to predict whether an asteroid is hazardous
Hazard_Classification.ipynb	Using KMeans to perform Asteroid orbit clustering

• Result:

Folder	Result
Hazard Classification	Folder Containing Accuracy plot and Confusion matrix of Hazard Classification model
Orbit Clustering	Folder containing 2D & 3D plot graph of Asteroid orbit clustering

---

2. Asteroid Hazard Classification

File: Asteroid Risk Prediction

Description: This project focuses on asteroid hazard classification using deep learning techniques. The notebook explores the application of neural networks for identifying potential asteroid threats.It also includes asteroid Hazard Classification and Orbit Clustering.

• Code:

Notebook	Description
Asteroid_Hazard_Classification.ipynb	Sequential Classification model to predict whether an asteroid is hazardous
Hazard_Classification.ipynb	Using KMeans to perform Asteroid orbit clustering

• Result:

Folder	Result
Hazard Classification	Folder Containing Accuracy plot and Confusion matrix of Hazard Classification model
Orbit Clustering	Folder containing 2D & 3D plot graph of Asteroid orbit clustering

---

3. Brain Tumour Detection

• File: Brain Tumour Detection

• Description: Predicting the adoption cost of blockchain technology is the goal of this project. The notebook delves into the use of deep learning models to estimate the costs associated with blockchain adoption.

• Code:

Notebook	Description
Brain_Tumor_Detection.ipynb	Classification of MRI Scans using Transfer Learning with ResNet50
Brain_Tumor_Detection.ipynb	Classification of MRI Scans using a self made CNN Model

• Result:

Folder	Result
CNN	Folder Containing Accuracy plot and Loss Plot of CNN Model
ResNet50	Folder Containing Accuracy plot and Loss Plot of ResNet50 Model

---

4. CCTV Fire Detection

• File: CCTV Fire Detection

• Description: CNN model for fire detection using CCTV footage, built using TensorFlow and Keras, and is designed to classify whether a given image footage contains fire or not.

• Code:

Notebook	Description
Fire_Detection_for_CCTV.ipynb	Classification of CCTV Images using a self made CNN Model

• Dataset:

Folder	Description
Dataset.md	Link for kaggle dataset used

---

5. Cat vs Dog Image Classification

• File: Cat vs Dog Classifier

• Description: Using deep learning, this project tackles the classic problem of classifying images as either a cat or a dog. The notebook demonstrates image classification techniques and model training for this binary classification task.

• Code:

Notebook	Description
Cat_vs_Dog.ipynb	Classification of images fo cats and dogs using a simple neural network

---

6. Customer Churn Prediction

• File: ``

• Description: Addressing the challenge of predicting customer churn, this project employs deep learning algorithms. The notebook explores how neural networks can be applied to forecast customer attrition.

• Code:

Notebook	Description
Customer_Churn_Prediction.ipynb	Customer Churn Prediction using a simple neural network

• Result:

Folder	Result
Result	Confusion matrix of the predicted values

---

7. Emotion Detection

• File: Emotion-Detection.ipynb

• Description: CNN models that performs classification of facial images into emtions of various classes.

• Code:

Notebook	Description
Emotion-Detection.ipynb	Various CNN models with multiple layers that are performing classification of grascale facial images into classes that represent emotions

---

8. Fracture Detection

• File: Fracture_Detection_InceptionV3.ipynb

• Description: Fracture detection is the key focus of this project, leveraging the InceptionV3 architecture. The notebook explores the use of a pre-trained deep learning model for accurate identification of fractures in medical images.

• Code:

Notebook	Description
Fracture-DenseNet121.ipynb	Fracture Detection using DenseNet21 model through transfer learning
Fracture-Resnet50.ipynb	Fracture Detection using Resnet50 model through transfer learning
Fracture-Xception.ipynb	Fracture Detection using Xception model through transfer learning
Fracture-own_model1.ipynb	Fracture Detection using own CNN Model
Fracture-own_model2.ipynbb	Fracture Detection using own CNN Model
Fracture_InceptionV3.ipynb	Fracture Detection using InceptionV3 model through transfer learning (Highest Accuracy)
Haar_Cascade.ipynb	Frcature Detection using red box with Haar Cascades
InceptionV3_Final.ipynb	Final Notebook

---

9. Gender Classification

• File: Gender_Classification.ipynb

• Description: This project involves the classification of instagram profile pictures based on the user's gender. Here, there are 2 classes male and female.

  • Code:

Notebook	Description
Gender_Classification.ipynb	Classification using transfer learining using the pre-trained model InceptionV3, and adding additional layers on top of the base model
Cnn.ipynb	Classification using a CNN model I made myself
link.ipynb	Performing Classification using the link of images
Face Detection.ipynb	Detecting faces in pfps using the Dlib library, and then classifying the faces using my model

• Test_Images:

Images used to test the model.

---

10. Handwritten Digits Classification

• File: Handwritten_Digits_Classification.ipynb

• Description: This project involves the classification of handwritten digits using deep learning. The notebook showcases the implementation of neural networks for recognizing and distinguishing digits in images.

  • Code:

Notebook	Description
Handwritten_Digits_Classification.ipynb	Simple classification using a neural network

• Result:

Folder	Result
Result	Confusion matrix of the predicted values

---

11. Plant Disease Diagnosis

• File: Plant_disease_diagnosis.ipynb

• Description: Addressing the issue of plant disease, this project utilizes deep learning to diagnose diseases in plants. The notebook demonstrates the application of neural networks for image-based classification of plant health.

  • Code:

Notebook	Description
Plant_disease_diagnosis.ipynb	Plant disease detection using transfer learning using ResNet50

• Dataset:

Folder	Dataset
Dataset.md	Dataset

• Model:

Folder	Model
Model.md	Model for classification

• Result:

Folder	Result
Accuracy.png	Accuracy plot the model
Loss.png	Loss plot the model

---

12. Speech Emotion Recognition

• File: Speech Emotion Recognition.ipynb

• Description: Focused on speech emotion recognition, this project employs deep learning techniques to identify and classify emotions in spoken language. The notebook showcases the application of neural networks for audio-based emotion analysis.

  • Code:

Notebook	Description
Speech Emotion Recognition.ipynb	LSTM Model to detect the emotion of speech classifying it to 6 catogeries of emotions

• Dataset:

Folder	Dataset
Dataset.md	Dataset

• Model:

Folder	Model
Model.md	Model for classification

• Result:

Folder	Result
Accuracy.png	Accuracy plot the model
Loss.png	Loss plot the model

---

Feel free to explore the notebooks and delve into the exciting world of deep learning. If you have any questions or feedback, please don't hesitate to reach out. Happy coding!