{"id":26451035,"url":"https://github.com/yahiazakaria445/image-classification-using-vgg-16","last_synced_at":"2026-04-12T13:33:26.814Z","repository":{"id":282738079,"uuid":"949492182","full_name":"yahiazakaria445/Image-Classification-using-VGG-16","owner":"yahiazakaria445","description":"computer vision model for 10 classes classification","archived":false,"fork":false,"pushed_at":"2025-03-16T16:07:11.000Z","size":5463,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-03-16T17:20:53.964Z","etag":null,"topics":["matplotlib","numpy","opencv","pandas","sklearn","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":null,"status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/yahiazakaria445.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":null,"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}},"created_at":"2025-03-16T15:30:20.000Z","updated_at":"2025-03-16T17:07:02.000Z","dependencies_parsed_at":"2025-03-16T17:31:38.644Z","dependency_job_id":null,"html_url":"https://github.com/yahiazakaria445/Image-Classification-using-VGG-16","commit_stats":null,"previous_names":["yahiazakaria445/image-classification-using-vgg-16"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/yahiazakaria445/Image-Classification-using-VGG-16","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FImage-Classification-using-VGG-16","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FImage-Classification-using-VGG-16/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FImage-Classification-using-VGG-16/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FImage-Classification-using-VGG-16/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/yahiazakaria445","download_url":"https://codeload.github.com/yahiazakaria445/Image-Classification-using-VGG-16/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/yahiazakaria445%2FImage-Classification-using-VGG-16/sbom","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":266572568,"owners_count":23950046,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","status":"online","status_checked_at":"2025-07-22T02:00:09.085Z","response_time":66,"last_error":null,"robots_txt_status":null,"robots_txt_updated_at":null,"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":["matplotlib","numpy","opencv","pandas","sklearn","tensorflow"],"created_at":"2025-03-18T16:31:22.617Z","updated_at":"2025-10-24T09:35:35.010Z","avatar_url":"https://github.com/yahiazakaria445.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Overview\nThis project implements an image classification model using the VGG-16 architecture to classify images into 10 different animal categories.\nThe dataset can be downloaded from [kaggle](https://www.kaggle.com/datasets/alessiocorrado99/animals10)\n\n![image](https://github.com/user-attachments/assets/b9bff808-7008-4ac2-af3a-954594d7ae99)\n\n# Libraries used\n- Os\n- Numpy\n- Pandas\n- Matplotlib\n- Seaborn \n- Cv2\n- Datetime\n- Tensorflow\n- sklearn\n\n# Data loading workflow\n- A DataFrame consisting of two columns (filename, representing the image path, and class, representing the image label) was created, with each row corresponding to an image.\n- The data was then split into training, validation, and test sets using the sklearn library with shuffling enabled.\n- Each resulting DataFrame was passed to Keras’ ImageDataGenerator for reading images from disk in batches and applying real-time transformations.\n\n# Model architecture\nVGG-16 is a convolutional neural network that is 16 layers deep and a pretrained version of the network trained on more than a million images from the ImageNet database.\n\n![model](https://github.com/user-attachments/assets/a2f787d8-bda7-4b71-b3f6-9444f4344303)\n\n# Used Callbacks\n1. **ModelCheckpoint** : \nThis function of keras callbacks is used to save the model after every epoch.\n\n2. **EarlyStopping** : \nThis function of Keras callbacks is used to stop the model training in between, used to stop the model as soon as it gets overfitted.\n\n3. **Learning Rate Reduction** : \nThis is a very simple function of callback that can be used to tweak the learning rate over a while, This gives us the desired output based on the respective epoch.\n\n# Model explainability\n 1- __Saliency maps__ : is an image that highlights the region on which people's eyes focus first.\n \n![125](https://github.com/user-attachments/assets/6bb564e5-e8b7-4467-b057-b357a09cc705)\n\n 2- __Grad-CAM__ (Gradient-weighted Class Activation Mapping). \n \n ![648d6](https://github.com/user-attachments/assets/d55bc1a1-5be0-4cea-9044-06d06def7adc)\n\n # Results\n- __train loss and validation loss__\n  \n   ![image](https://github.com/user-attachments/assets/b178d3c0-c0dd-43a5-bbca-1e7f99281534)\n\n- __train and validation accuracy__\n  \n     ![image](https://github.com/user-attachments/assets/41187aea-33cc-46fe-b78b-e9d40530c7b9)\n\n- __Classification Accuracy__\n\n  ![image](https://github.com/user-attachments/assets/173195ec-f4a6-4523-9811-a9015709e886)\n\n- __Confusion Matrix__\n  \n  ![image](https://github.com/user-attachments/assets/fecd302f-abe2-4b09-83a3-ca6852b5c17b)\n\n- __Classification report__\n  \n  ![image](https://github.com/user-attachments/assets/ea6936d2-9a52-4494-8485-40b2291bc076)\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyahiazakaria445%2Fimage-classification-using-vgg-16","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fyahiazakaria445%2Fimage-classification-using-vgg-16","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fyahiazakaria445%2Fimage-classification-using-vgg-16/lists"}