{"id":17929627,"url":"https://github.com/angrybayblade/image_search","last_synced_at":"2025-04-03T10:15:54.753Z","repository":{"id":125388230,"uuid":"260910976","full_name":"angrybayblade/image_search","owner":"angrybayblade","description":"🔍 Image Search engine based on mnist dataset.","archived":false,"fork":false,"pushed_at":"2020-05-24T11:18:36.000Z","size":1173,"stargazers_count":0,"open_issues_count":0,"forks_count":0,"subscribers_count":2,"default_branch":"master","last_synced_at":"2025-02-08T23:28:15.999Z","etag":null,"topics":["autoencoder","autoencoder-mnist","convolutional-autoencoder","image-search","neural-network"],"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/angrybayblade.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":"2020-05-03T12:26:43.000Z","updated_at":"2020-05-24T11:22:33.000Z","dependencies_parsed_at":null,"dependency_job_id":"544fe943-924c-4571-8230-373372831825","html_url":"https://github.com/angrybayblade/image_search","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angrybayblade%2Fimage_search","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angrybayblade%2Fimage_search/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angrybayblade%2Fimage_search/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/angrybayblade%2Fimage_search/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/angrybayblade","download_url":"https://codeload.github.com/angrybayblade/image_search/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246981166,"owners_count":20863828,"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","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":["autoencoder","autoencoder-mnist","convolutional-autoencoder","image-search","neural-network"],"created_at":"2024-10-28T21:09:52.261Z","updated_at":"2025-04-03T10:15:54.726Z","avatar_url":"https://github.com/angrybayblade.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"### Image Search Using Autoencoders In MNIST Dataset 🔍\n\n**example**\n___\n\n![](doc/search.gif)\n\n___\n\nRun Using\n\n```bash\npython3 app.py\n```\nThen open http://localhost:8080 on your browser.\n\n\u003e  Search engine architecture uses a auto encoder to encode images into a 128-D vectors and clusters them using KMeans.\n\n\u003e When querying an image image is fed into the autoencoder which returns a 128-D vector, the vector is used to find which cluster the image belongs to and then some of the images from the cluster are fetched as result.\n\n\n### Auto-Encoders Used In Search Engine\n\n1. **Dense Autoencoder**\n\n    ![](doc/dense_out.png)\n\n2. **Convolutional Autoencoder**\n\n    ![](doc/conv_out.png)\n\n3. **Convolutional Autoencoder With Perceptual Loss** \n\n    ![](doc/conv_per_out.png)\n\n### Using different auto encoders for search\n\n\u003e Just open the app.py and find below code.\n\n```python\nsearch = DenseAutoEncoderSearch()\n```\n\n\u003e and replace it with one of the following.\n\n```python\nsearch = ConvolutionalAutoEncoderSearch()\n#or\nsearch = ConvolutionalAutoEncoderWithPerceptLossSearch()\n```\n\n* UI is build in node using ReactJS⚛️ ","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangrybayblade%2Fimage_search","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fangrybayblade%2Fimage_search","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fangrybayblade%2Fimage_search/lists"}