{"id":16272152,"url":"https://github.com/progamergov/neural-graph-legacy","last_synced_at":"2026-02-23T16:03:33.834Z","repository":{"id":103796474,"uuid":"79671243","full_name":"ProGamerGov/Neural-Graph-Legacy","owner":"ProGamerGov","description":"Graph Neural-Style's loss value outputs","archived":false,"fork":false,"pushed_at":"2017-01-23T00:30:40.000Z","size":28,"stargazers_count":5,"open_issues_count":0,"forks_count":0,"subscribers_count":3,"default_branch":"master","last_synced_at":"2025-10-27T19:33:37.181Z","etag":null,"topics":["neural-style"],"latest_commit_sha":null,"homepage":null,"language":"Lua","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/ProGamerGov.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":"2017-01-21T20:35:08.000Z","updated_at":"2021-12-16T17:34:51.000Z","dependencies_parsed_at":null,"dependency_job_id":"109d4f0d-c986-44fa-85bb-b9af6bd892d7","html_url":"https://github.com/ProGamerGov/Neural-Graph-Legacy","commit_stats":null,"previous_names":[],"tags_count":0,"template":false,"template_full_name":null,"purl":"pkg:github/ProGamerGov/Neural-Graph-Legacy","repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ProGamerGov%2FNeural-Graph-Legacy","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ProGamerGov%2FNeural-Graph-Legacy/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ProGamerGov%2FNeural-Graph-Legacy/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ProGamerGov%2FNeural-Graph-Legacy/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/ProGamerGov","download_url":"https://codeload.github.com/ProGamerGov/Neural-Graph-Legacy/tar.gz/refs/heads/master","sbom_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/ProGamerGov%2FNeural-Graph-Legacy/sbom","scorecard":null,"host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":286080680,"owners_count":29747981,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2026-02-23T07:44:07.782Z","status":"ssl_error","status_checked_at":"2026-02-23T07:44:07.432Z","response_time":90,"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":["neural-style"],"created_at":"2024-10-10T18:16:28.182Z","updated_at":"2026-02-23T16:03:33.809Z","avatar_url":"https://github.com/ProGamerGov.png","language":"Lua","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Neural-Graph\nGraph Neural-Style's loss value outputs. Special thanks to [htoyryla](https://github.com/htoyryla) for helping me [modify the neural_style.lua script](https://github.com/jcjohnson/neural-style/issues/370).\n\n![](https://i.imgur.com/4ViZZpH.png)\n\n![](https://i.imgur.com/bBHgBbY.png)\n\nThe Neural-Style issue: https://github.com/jcjohnson/neural-style/issues/370\n\nAlternate download of the modified neural_style.lua script: https://gist.github.com/ProGamerGov/a8134605c89f01e5bcd88539456675b8\n\n\nMore graphs can be found here along with observations: https://github.com/ProGamerGov/Neural-Graph/wiki/Graphs\n\n# Requirements\n\n[Neural-Style](https://github.com/jcjohnson/neural-style/) must be installed.\n\nMake sure you Neural-Style command is modified to use the modified Neural-Style script.\n\nMatplotlib is also required: \n\n`sudo apt-get install python-matplotlib`\n\n# Usage\n\nFirst run the modified neural_style.lua script with `2\u003e\u00261 | tee ~/neural-style/loss_values.log` at the end of your Neural-Style command paramters. Example: \n\n`th neural_style_csv.lua -style_image \u003cimage.jpg\u003e -content_image \u003cimage.jpg\u003e -print_iter 10 2\u003e\u00261 | tee ~/neural-style/loss_values.log`\n\nOr if you are using multires, then do:\n\n`./multires.sh 2\u003e\u00261 | tee ~/neural-style/loss_values.log`\n\nUsing `-print_iter 1` will create a less jagged looking graph.\n\nAfter running Neural-Style, you must manually convert the iteration section(s) from the saved terminal log file to their own CSV file.\n\nMake sure the first row of the CSV file is (If using different combinations of layers, or more than one style image, you may have to modify the CSV file headers):\n\nIteration | Content 1 loss | Style 1 loss | Style 2 loss |  Style 3 loss | Style 4 loss | Style 5 loss | Total loss\n--- | --- | --- | --- | --- | --- | --- | --- \n\nNote that the exact header names are not needed. After copying my text file data into Excel, I used this [guide](https://web.archive.org/web/20170123002416/https://help.xero.com/Q_ConvertTXT) to convert it into a \"Space\" deliminated CSV file. Though you can use whatever method of text to CSV conversion that works for you.\n\nThen first modify the graphing script's tile to match your CSV file(s), and run the graphing script: \n\n`python graph.py`\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprogamergov%2Fneural-graph-legacy","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fprogamergov%2Fneural-graph-legacy","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fprogamergov%2Fneural-graph-legacy/lists"}