{"id":26699896,"url":"https://github.com/khushirajurkar/vision-transformer-image-classification","last_synced_at":"2026-07-16T23:34:50.102Z","repository":{"id":271841864,"uuid":"914734554","full_name":"KhushiRajurkar/Vision-Transformer-Image-Classification","owner":"KhushiRajurkar","description":"A Vision Transformer (ViT) implementation for image classification using CIFAR-10 dataset, leveraging HuggingFace's Trainer API for computational efficiency","archived":false,"fork":false,"pushed_at":"2025-07-13T07:59:26.000Z","size":196,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-21T12:44:55.323Z","etag":null,"topics":["cifar-10","computer-vision","data-augmentation","deep-learning","huggingface","image-classification","machine-learning","model-evaluation","neural-networks","patch-encoding","positional-encoding","self-attention","trainer-api","transfer-learning","transformer","vision-transformer"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/KhushiRajurkar.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null,"roadmap":null,"authors":null,"dei":null,"publiccode":null,"codemeta":null,"zenodo":null,"notice":null,"maintainers":null,"copyright":null,"agents":null,"dco":null,"cla":null}},"created_at":"2025-01-10T07:43:47.000Z","updated_at":"2025-07-13T07:59:30.000Z","dependencies_parsed_at":null,"dependency_job_id":"7c51852c-89ec-4b23-ad25-6a99d3f79a87","html_url":"https://github.com/KhushiRajurkar/Vision-Transformer-Image-Classification","commit_stats":null,"previous_names":["khushirajurkar/vision-transformer-image-classification"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/KhushiRajurkar/Vision-Transformer-Image-Classification","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KhushiRajurkar%2FVision-Transformer-Image-Classification","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KhushiRajurkar%2FVision-Transformer-Image-Classification/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KhushiRajurkar%2FVision-Transformer-Image-Classification/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KhushiRajurkar%2FVision-Transformer-Image-Classification/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/KhushiRajurkar","download_url":"https://codeload.github.com/KhushiRajurkar/Vision-Transformer-Image-Classification/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/KhushiRajurkar%2FVision-Transformer-Image-Classification/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":35560452,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-05-26T15:22:16.424Z","status":"online","status_checked_at":"2026-07-16T02:00:06.687Z","response_time":83,"last_error":null,"robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":true,"can_crawl_api":true,"host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":["cifar-10","computer-vision","data-augmentation","deep-learning","huggingface","image-classification","machine-learning","model-evaluation","neural-networks","patch-encoding","positional-encoding","self-attention","trainer-api","transfer-learning","transformer","vision-transformer"],"created_at":"2025-03-26T23:17:45.074Z","updated_at":"2026-07-16T23:34:50.068Z","avatar_url":"https://github.com/KhushiRajurkar.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Vision-Transformer-Image-Classification\nA Vision Transformer (ViT) implementation for image classification using CIFAR-10 dataset, leveraging HuggingFace's Trainer API for computational efficiency\n# Vision Transformer for Image Classification\n\n## Overview\nThis repository contains an implementation of the Vision Transformer (ViT) model, a novel architecture leveraging self-attention mechanisms for image classification tasks. Unlike traditional CNNs, ViT splits images into patches and processes them as sequences, enabling the model to capture global context effectively.\n\n## Objective\n- To explore the capabilities of Vision Transformer on the CIFAR-10 dataset.\n- To compare its performance with traditional CNN models.\n- To implement and evaluate using HuggingFace's Trainer API for improved computational efficiency.\n\n## Methodology\n1. **Dataset**: CIFAR-10 (60,000 32x32 images across 10 classes).\n2. **Preprocessing**: Data augmentation and patch embedding for input preparation.\n3. **Model Architecture**: Implementation of Vision Transformer with patch encoding and positional encoding.\n4. **Training**: Leveraged HuggingFace's Trainer API to streamline training and overcome computational limitations.\n5. **Evaluation**: Achieved high accuracy through transfer learning and efficient training.\n\n## Results\n- **Accuracy**: Reached 98.77% validation accuracy by epoch 5.\n- **Efficiency**: Demonstrated the use of pre-trained weights and transfer learning for computationally constrained setups.\n\n## Challenges\nFaced computational resource constraints but overcame them using HuggingFace’s Trainer API, reducing the training burden while maintaining accuracy.\n\n## Usage\n1. Clone the repository:\n   ```bash\n   git clone https://github.com/KhushiRajurkar/Vision-Transformer-Image-Classification.git\n   ```\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhushirajurkar%2Fvision-transformer-image-classification","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fkhushirajurkar%2Fvision-transformer-image-classification","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fkhushirajurkar%2Fvision-transformer-image-classification/lists"}