{"id":25343846,"url":"https://github.com/pintamonas4575/tfg-diffusion-model-customdataset","last_synced_at":"2026-04-17T10:31:34.192Z","repository":{"id":227224372,"uuid":"770813344","full_name":"pintamonas4575/TFG-Diffusion-Model-CustomDataset","owner":"pintamonas4575","description":"Creación en Pytorch de un modelo de difusión para generación incondicional de imágenes con un dataset propio.","archived":false,"fork":false,"pushed_at":"2024-06-13T22:06:26.000Z","size":96448,"stargazers_count":1,"open_issues_count":0,"forks_count":0,"subscribers_count":1,"default_branch":"main","last_synced_at":"2025-04-08T14:47:12.751Z","etag":null,"topics":["attention-mechanism","cnn","cosine-scheduler","cuda","custom-dataset","ddim","deep-learning","diffusion-models","gpu","image-generation","pytorch"],"latest_commit_sha":null,"homepage":"https://oa.upm.es/82193/","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/pintamonas4575.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}},"created_at":"2024-03-12T07:58:04.000Z","updated_at":"2025-02-03T13:15:23.000Z","dependencies_parsed_at":"2025-02-14T11:09:03.684Z","dependency_job_id":null,"html_url":"https://github.com/pintamonas4575/TFG-Diffusion-Model-CustomDataset","commit_stats":null,"previous_names":["pintamonas4575/diffusion-model-on-own-dataset","pintamonas4575/tfg-diffusion-model-customdataset"],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/pintamonas4575/TFG-Diffusion-Model-CustomDataset","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pintamonas4575%2FTFG-Diffusion-Model-CustomDataset","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pintamonas4575%2FTFG-Diffusion-Model-CustomDataset/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pintamonas4575%2FTFG-Diffusion-Model-CustomDataset/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pintamonas4575%2FTFG-Diffusion-Model-CustomDataset/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/pintamonas4575","download_url":"https://codeload.github.com/pintamonas4575/TFG-Diffusion-Model-CustomDataset/tar.gz/refs/heads/main","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/pintamonas4575%2FTFG-Diffusion-Model-CustomDataset/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":31925311,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-04-17T10:19:20.377Z","status":"ssl_error","status_checked_at":"2026-04-17T10:19:18.682Z","response_time":62,"last_error":"SSL_connect returned=1 errno=0 peeraddr=140.82.121.6:443 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":["attention-mechanism","cnn","cosine-scheduler","cuda","custom-dataset","ddim","deep-learning","diffusion-models","gpu","image-generation","pytorch"],"created_at":"2025-02-14T10:59:01.335Z","updated_at":"2026-04-17T10:31:34.173Z","avatar_url":"https://github.com/pintamonas4575.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# TFG-Diffusion-Model-CustomDataset\nCreación en Pytorch de un modelo de difusión para generación incondicional de imágenes con un dataset propio.\n\nSe ha creado un modelo que sigue el estándar DDIM sobre un *dataset* local de imágenes.\n\n🙋‍♂️ Los archivos de este repositorio pertenecen al **TFG** de **Alejandro Mendoza Medina**.\n\n----------------------\n\n# 📓 Notebook *DDIM_50_steps*\n\nEste notebook es el corazón de la creación y entrenamiento del modelo de difusión. Se ha hecho uso del algoritmo DDIM (***D**enoising **D**iffusion **I**mplicit **M**odels*) con *noise scheduler* de tipo coseno. Se ha entrenado con 1000 *timesteps* pero la generación se ha hecho con 50 pasos, gracias a la ventaja de flexibilidad frente al algoritmo DDPM (***D**enoising **D**iffusion **P**robabilistic **M**odels*).\n\nSe ha entrenado durante 580 *epochs*, tardando 87 horas en completar el entrenmiento.\n\n# 📓 Notebook *DDIM_pruebas_generación*\n\nEste notebook presenta la evolución de una semilla a lo largo de los *epochs*, así como distintas pruebas de generación. \n\n# 📂 Carpeta \"generated-samples\"\n\nEn esta carpeta se encontrarán ejemplos generados por el modelo.\n\n# ⚖️ Licencia\n\nHay algún proceso \"difuminado\" en la burocracía de España que hace que vaya muy lenta. \n\n# 👤 Contacto\n\nCualquier duda o sugerencia contactar con el autor:\n\nAlejandro Mendoza: alejandro.embi@gmail.com\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpintamonas4575%2Ftfg-diffusion-model-customdataset","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fpintamonas4575%2Ftfg-diffusion-model-customdataset","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fpintamonas4575%2Ftfg-diffusion-model-customdataset/lists"}