{"id":18322803,"url":"https://github.com/justsecret123/one-piece-image-classifier","last_synced_at":"2026-04-04T22:34:24.678Z","repository":{"id":174787394,"uuid":"327053353","full_name":"Justsecret123/One-Piece-Image-Classifier","owner":"Justsecret123","description":"A quick image classifier trained with manually selected One Piece images.","archived":false,"fork":false,"pushed_at":"2022-05-01T06:42:39.000Z","size":87331,"stargazers_count":2,"open_issues_count":0,"forks_count":1,"subscribers_count":1,"default_branch":"master","last_synced_at":"2026-01-03T19:24:52.511Z","etag":null,"topics":["batch-normalization","classification","classification-model","computer-vision","convolutional-neural-networks","data-augmentation","deep-learning","deep-neural-networks","docker","early-stopping","image-classification","image-classifier","jupyterlab","keras","machine-learning","notebook","python","tensorflow","tensorflow-serving","transfer-learning"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"gpl-3.0","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/Justsecret123.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":"CODE_OF_CONDUCT.md","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":"2021-01-05T16:19:25.000Z","updated_at":"2023-09-24T14:14:49.000Z","dependencies_parsed_at":null,"dependency_job_id":"e4820008-cb43-44ef-b32a-953d6d7b9983","html_url":"https://github.com/Justsecret123/One-Piece-Image-Classifier","commit_stats":null,"previous_names":["justsecret123/one-piece-image-classifier"],"tags_count":2,"template":false,"template_full_name":null,"purl":"pkg:github/Justsecret123/One-Piece-Image-Classifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Justsecret123%2FOne-Piece-Image-Classifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Justsecret123%2FOne-Piece-Image-Classifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Justsecret123%2FOne-Piece-Image-Classifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Justsecret123%2FOne-Piece-Image-Classifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Justsecret123","download_url":"https://codeload.github.com/Justsecret123/One-Piece-Image-Classifier/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Justsecret123%2FOne-Piece-Image-Classifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31416791,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-04T20:09:54.854Z","status":"ssl_error","status_checked_at":"2026-04-04T20:09:44.350Z","response_time":60,"last_error":"SSL_read: unexpected eof while reading","robots_txt_status":"success","robots_txt_updated_at":"2025-07-24T06:49:26.215Z","robots_txt_url":"https://github.com/robots.txt","online":false,"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":["batch-normalization","classification","classification-model","computer-vision","convolutional-neural-networks","data-augmentation","deep-learning","deep-neural-networks","docker","early-stopping","image-classification","image-classifier","jupyterlab","keras","machine-learning","notebook","python","tensorflow","tensorflow-serving","transfer-learning"],"created_at":"2024-11-05T18:26:02.312Z","updated_at":"2026-04-04T22:34:24.653Z","avatar_url":"https://github.com/Justsecret123.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# One-Piece-Image-Classifier ![Language_support](https://img.shields.io/pypi/pyversions/Tensorflow) ![Last_commit](https://img.shields.io/github/last-commit/JustSecret123/Human-pose-estimation) ![Workflow](https://img.shields.io/github/workflow/status/JustSecret123/Human-pose-estimation/Pylint/main) ![Tensorflow_version](https://img.shields.io/badge/Tensorflow%20version-2.6.2-orange)\n\nI trained a custom Deep Learning model to recognize some One Piece characters (17, at the moment) with Tensorflow, Keras, and a fine-tuned MobilenetV2.\nAfterwards, the model was converted to a TFLite model for running inferences on small devices, and a Tensorflow Serving Docker container for HTTP-based inferences.\n\n96.84% validation accuracy.\n\n\u003e **Deployed on my personal Docker Hub repository: [Click here](https://hub.docker.com/repository/docker/ibrahimserouis/my-tensorflow-models)\n\n\u003e **Kaggle Notebook link:  [Kaggle notebook](https://www.kaggle.com/ibrahimserouis99/one-piece-image-classifier-notebook)\n\n\u003e **Tensorflow Lite model : [op_classifier_V16.tflite](https://drive.google.com/file/d/1-xTYqv10IQmV0FS3ftYH6LeTbE86dlkT/view?usp=sharing)\n\n\u003ca href=\"https://www.linkedin.com/in/ibrahim-serouis-b05378181/\"\u003e\n  \u003cimg src=\"https://img.shields.io/badge/LinkedIn-Ibrahim%20Serouis-blue?link=http://left\u0026link=http://right)\"/\u003e\n\u003c/a\u003e\n\n\n## Training \n\nA fine-tuned mobilenet has been used. The training session was runned on Kaggle with a GPU execution type. \n\n### Dataset \n\n\u003e Dataset link : [Click here](https://www.kaggle.com/datasets/ibrahimserouis99/one-piece-image-classifier)\n\n### Notebook \n\n\u003e Notebook link : [Click here](one-piece-image-classifier-notebook.ipynb)\n\n## Model description\n\n- **A data augmentation layer** which creates \"modified\" images of the training set\n- **A MobileNet layer** which detects the features\n- **A Global average pooling layer** which converts the feature vectors into a 1280 element vector\n- **1*3 Dense layers** followed by a dropout layer to prevent overfitting\n- **An activation layer** (sigmoid) which represents the final output: Probability of input(X) belonging to each class\n- Output classes (17 probabilities) : ['Ace', 'Akainu', 'Brook', 'Chopper', 'Crocodile', 'Franky', 'Jinbei', 'Kurohige', 'Law', 'Luffy', 'Mihawk', 'Nami', 'Robin', 'Sanji', 'Shanks', 'Usopp', 'Zoro']\n\n\n## Architecture\n\n![Model architecture](Screenshots/Model_summary_v16.PNG)\n\u003e **Best valdiation accuracy: 96.84%.**\n\n## Results (Amazon SageMaker endpoint)\n\n![Results](Screenshots/One%20Piece%20image%20classifier.gif)\n\n# Useful scripts \n- [JFIFF to PNG converter](/Scripts/convert_jfif_to_png.py)\n- [Image inverter](Scripts/invert_images.py)\n\n## How to use \n\n### 1-First option: Using the [command line runner](Scripts/op_classifier.py)\n\n#### Args \n\n![Args](Screenshots/command_line_args.PNG)\n\n\u003e **The image source can be a file path or a URL. Set the \"mode\" parameter to 'image' or 'url' accordingly.**\n\n#### Results \n![Results](Screenshots/command_line_results.PNG)\n\n### 2-Second option: Using the Tensorflow Serving image deployed [here](https://hub.docker.com/repository/docker/ibrahimserouis/my-tensorflow-models) (**TAG: OP_serving**)\n\nPull the Docker image with the OP_serving tag, then run inferences using the 8501 port. \n\n\u003e A test script example is available [here](/Scripts/Prediction_OP_Model_Test.py)\n\n\n## Prerequisites\n\n- Python 3.7 or higher \n- IDE: Jupyter Lab/Kaggle Notebooks/Google Colab \n- Frameworks: Tensorflow 2.6 or higher and its dependencies\n- Libraries : OpenCV, PIL, NumPy\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjustsecret123%2Fone-piece-image-classifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fjustsecret123%2Fone-piece-image-classifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fjustsecret123%2Fone-piece-image-classifier/lists"}