DL-Simplified
DL-Simplified copied to clipboard
abhisheks008
Tiger Identification using DL
Deep Learning Simplified Repository (Proposing new issue)
:red_circle: Project Title : Tiger Identification :red_circle: Aim : Aim is to identify the tigers from the given dataset using a DL method/approach. :red_circle: Dataset : https://www.kaggle.com/datasets/quadeer15sh/amur-tiger-reidentification :red_circle: Approach : Try to use 3-4 algorithms to implement the models and compare all the algorithms to find out the best fitted algorithm for the model by checking the accuracy scores. Also do not forget to do a exploratory data analysis before creating any model.
📍 Follow the Guidelines to Contribute in the Project :
- You need to create a separate folder named as the Project Title.
- Inside that folder, there will be four main components.
- Images - To store the required images.
- Dataset - To store the dataset or, information/source about the dataset.
- Model - To store the machine learning model you've created using the dataset.
-
requirements.txt- This file will contain the required packages/libraries to run the project in other machines.
- Inside the
Modelfolder, theREADME.mdfile must be filled up properly, with proper visualizations and conclusions.
:red_circle::yellow_circle: Points to Note :
- The issues will be assigned on a first come first serve basis, 1 Issue == 1 PR.
- "Issue Title" and "PR Title should be the same. Include issue number along with it.
- Follow Contributing Guidelines & Code of Conduct before start Contributing.
:white_check_mark: To be Mentioned while taking the issue :
- Full name :
- GitHub Profile Link :
- Email ID :
- Participant ID (if applicable):
- Approach for this Project :
- What is your participant role? (Mention the Open Source program)
Happy Contributing 🚀
All the best. Enjoy your open source journey ahead. 😎
please asigned this task to me. Tiger Identification using DL #248.
FullName: Nirmal Kumar Ahirwar Github Profile Link: https://github.com/NirmalKAhirwar Email ID: [email protected]
Approach for this Project: 1] Perform Exploratory Data Analysis on the dataset. 2] Apply Data Augmentation techniques to the dataset using the Albumentations python library. 3] Create a deep learning model based on CNN models such as VGG, EfficientNet, or Transformers models like ViT to identify tigers in images. 4] Compare the performance of all models using accuracy metrics and perform Hyperparameter tuning to achieve higher accuracy on the Test Dataset. 5] Implement the models using TensorFlow or PyTorch.
What is your participant role? -contributor at Social Summer of Code (SSOC), Season-2
According to the Code of Conduct and Contribution Guidelines, one contributor can be assigned one issue at a time.
Tiger Identification using DL https://github.com/World-of-ML/DL-Simplified/issues/248.
FullName: Manoj Kumar H S Github Profile Link: https://github.com/Manoj-2702 Email ID: [email protected]
Approach for this Project: Analyze the distribution of tiger images, the number of samples per tiger, and any class imbalances. Visualize the tiger images to gain insights into their characteristics, such as color variations, pose, and background. Preprocess the tiger images to ensure they are in a consistent format and size. Resize the images to a uniform size while maintaining the aspect ratio. Normalize the pixel values of the images to a suitable range (e.g., 0-1) to improve model convergence. Split the dataset into training and testing sets, ensuring a balanced distribution of tigers in both sets. Choose pre-trained CNN models like VGG16, ResNet50, or InceptionV3 as a starting point. Add custom fully connected layers on top of the pre-trained CNN models to adapt them to the tiger identification task. Set appropriate activation functions and regularization techniques (e.g., dropout) in the custom layers. Evaluate the trained models on the testing set to measure their accuracy and other relevant metrics. Compare the performance of the trained models based on accuracy, precision, recall, F Score etc.,
What is your participant role? -contributor at Social Summer of Code (SSOC), Season-2
FullName: Pawas Pandey Github Profile Link: https://github.com/pawaspy Email ID: [[email protected]
Approach for this Project: Analyze the distribution of tiger images, the number of samples per tiger, and any class imbalances. Visualize the tiger images to gain insights into their characteristics, such as color variations, pose, and background. Preprocess the tiger images to ensure they are in a consistent format and size. Resize the images to a uniform size while maintaining the aspect ratio. Normalize the pixel values of the images to a suitable range (e.g., 0-1) to improve model convergence. Split the dataset into training and testing sets, ensuring a balanced distribution of tigers in both sets. Choose pre-trained CNN models like VGG16, ResNet50, or InceptionV3 as a starting point. Add custom fully connected layers on top of the pre-trained CNN models to adapt them to the tiger identification task. Set appropriate activation functions and regularization techniques (e.g., dropout) in the custom layers. Evaluate the trained models on the testing set to measure their accuracy and other relevant metrics. Compare the performance of the trained models based on accuracy, precision, recall, F Score etc.,
What is your participant role? - DWOC'24
✅ To be Mentioned while taking the issue :
Full name : Gaurav Kumar SIngh GitHub Profile Link : https://github.com/Gaurav-576 Email ID : [email protected] Participant ID (if applicable): Approach for this Project : I would like to perform web scrapping to add more images to the dataset. Using data augmentation to create more data for the model to train onto. Then I would be using CNN to identify whether it is a tiger or not using Tensorflow and keras. Improving the overall accuracy of the model and focusing on False Negative recall of the confusion matrix. What is your participant role? GSSoC'24
Hi @Gaurav-576 need to be more specific with the models/algorithms you are planning to use. And also do not spam into every issue, if you want to work on an issue, stick to that, wait for that issue to be assigned.
Full name : Abhijeet Kaithwas GitHub Profile Link : https://github.com/jeet-Abhi123 Email ID : [email protected] Participant ID (if applicable): Approach for this Project :
I will do the image scaling(normalize o01), and then data augmentation to increase the dataset size and add variety to the images. Declaring the input shape of the image [batch_size, img_w, img_h, channels].
Splitting the dataset in training and validation parts.
Applying the pretrained Transfer learning models like VGG16, Resnet50, MobileNet and unfreezing the few last layers of the model so that we can train it for tiger images.
After adding customized ANN or CNN layers to do identify characteristics of tiger. Will experiment with different activation functions like relu and tanh in hidden layers and regularization techniques(eg. dropout, BatchNormalization).
Will apply Kerastuner for hyperparameter tuning and setting the learning rate value, activation functions etc.
Drawing appropriate graphs of the results comparing training and validation accuracy.
Finally ,check the performance of the model based on confusion matrix, F1 score and accuracy.
What is your participant role? GSSoC'24
