{"id":18462650,"url":"https://github.com/0eix/deepclassifier","last_synced_at":"2026-04-08T20:43:32.465Z","repository":{"id":127307045,"uuid":"420201735","full_name":"0eix/DeepClassifier","owner":"0eix","description":"DeepClassify - A Versatile Command Line Image Classifier","archived":false,"fork":false,"pushed_at":"2023-06-04T11:55:02.000Z","size":1416,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-10-10T07:03:17.522Z","etag":null,"topics":["classification","classifier","cli","cnn","command-line-app","deep-learning","numpy","pandas","pillow","python","pytorch","torchvision","transfer-learning"],"latest_commit_sha":null,"homepage":"","language":"Python","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/0eix.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}},"created_at":"2021-10-22T18:21:32.000Z","updated_at":"2023-06-04T11:55:06.000Z","dependencies_parsed_at":"2023-08-16T12:52:49.873Z","dependency_job_id":null,"html_url":"https://github.com/0eix/DeepClassifier","commit_stats":null,"previous_names":["eoamegassi/deepclassifier","0eix/deepclassifier"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/0eix/DeepClassifier","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0eix%2FDeepClassifier","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0eix%2FDeepClassifier/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0eix%2FDeepClassifier/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0eix%2FDeepClassifier/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/0eix","download_url":"https://codeload.github.com/0eix/DeepClassifier/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/0eix%2FDeepClassifier/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31573788,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-08T14:31:17.711Z","status":"ssl_error","status_checked_at":"2026-04-08T14:31:17.202Z","response_time":54,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.5:443 state=error: 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":["classification","classifier","cli","cnn","command-line-app","deep-learning","numpy","pandas","pillow","python","pytorch","torchvision","transfer-learning"],"created_at":"2024-11-06T09:03:49.711Z","updated_at":"2026-04-08T20:43:32.449Z","avatar_url":"https://github.com/0eix.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Flower Image Classifier: An AI Programming Project\n\nThis project is part of the Udacity AI Programming with Python Nanodegree, where a deep learning model is developed for identifying 102 different species of flowers based on their images. The project is divided into two parts: \n\n1. Designing and training the model using Jupyter notebook.\n2. Turning the trained model into a command-line application that can train on any set of images, and make predictions on new images.\n\nThe final command-line application allows customization of various aspects including CNN architecture selection, setting hyperparameters, choosing between GPU/CPU, and saving the training to a checkpoint to resume later.\n\n## File Structure:\n\nHere is an overview of the purpose and usage of each file in this project.\n\n1. **cli_utils.py**: Contains helper functions for parsing command-line arguments. This aids in customizing the application's functionality like selecting the CNN architecture, setting hyperparameters, deciding whether to use GPU, and more.\n\n2. **data_utils.py**: Responsible for data preprocessing and loading tasks. It includes functions to load image datasets from a directory, split them into training, validation and testing sets, and apply necessary transformations to prepare data for the model.\n\n3. **device_utils.py**: Includes utility functions for device selection. It helps to identify whether a GPU is available and should be used for training and inference.\n\n4. **model_utils.py**: Contains functions to build and load the deep learning model. This includes creating a classifier using one of the pre-trained models (AlexNet, VGG, DenseNet, etc.), and loading a checkpoint to resume training.\n\n5. **predict.py**: This script uses the trained model to make predictions on new images. It processes the input image, performs inference using the model, and outputs the top K most likely classes along with their probabilities.\n\n6. **train.py**: Contains the functionality required for training the model. It defines the training loop, validation loop, and handles saving the model's state to a checkpoint after each epoch.\n\n## How to Run:\n\nYou can train a new network on a data-set with `train.py` and predict the class for an input image with `predict.py`. Run `python train.py -h` and `python predict.py -h` to see the available command-line options for each script.\n\n## Requirements:\n\nThe application is built using Python and requires PyTorch, NumPy, and Pillow libraries.\n\nRemember to install these dependencies before running the application.\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F0eix%2Fdeepclassifier","html_url":"https://awesome.ecosyste.ms/projects/github.com%2F0eix%2Fdeepclassifier","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2F0eix%2Fdeepclassifier/lists"}