{"id":18421106,"url":"https://github.com/aitorzip/keras-icnet","last_synced_at":"2025-04-07T14:31:35.952Z","repository":{"id":113778377,"uuid":"110992259","full_name":"aitorzip/Keras-ICNet","owner":"aitorzip","description":"Keras implementation of Real-Time Semantic Segmentation on High-Resolution Images","archived":false,"fork":false,"pushed_at":"2018-01-24T12:25:26.000Z","size":26461,"stargazers_count":86,"open_issues_count":11,"forks_count":33,"subscribers_count":8,"default_branch":"master","last_synced_at":"2025-03-22T19:43:48.581Z","etag":null,"topics":["autonomous-driving","computer-vision","deep-learning","fully-convolutional-networks","image-processing","image-segmentation","keras","semantic-segmentation","tensorflow"],"latest_commit_sha":null,"homepage":"https://arxiv.org/abs/1704.08545","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/aitorzip.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":"2017-11-16T16:01:16.000Z","updated_at":"2024-03-05T09:10:26.000Z","dependencies_parsed_at":null,"dependency_job_id":"4a5e3a80-b1c9-4442-8469-4ba67c95e6aa","html_url":"https://github.com/aitorzip/Keras-ICNet","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/aitorzip%2FKeras-ICNet","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aitorzip%2FKeras-ICNet/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aitorzip%2FKeras-ICNet/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/aitorzip%2FKeras-ICNet/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/aitorzip","download_url":"https://codeload.github.com/aitorzip/Keras-ICNet/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":247669873,"owners_count":20976463,"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":["autonomous-driving","computer-vision","deep-learning","fully-convolutional-networks","image-processing","image-segmentation","keras","semantic-segmentation","tensorflow"],"created_at":"2024-11-06T04:24:24.637Z","updated_at":"2025-04-07T14:31:35.946Z","avatar_url":"https://github.com/aitorzip.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Keras-ICNet\n### [[paper]](https://arxiv.org/abs/1704.08545)\n\nKeras implementation of Real-Time Semantic Segmentation on High-Resolution Images. **Training in progress!**\n    \n## Requisites\n- Python 3.6.3\n- Keras 2.1.1 with Tensorflow backend\n- A dataset, such as Cityscapes or Mapillary ([Mapillary](https://research.mapillary.com/) was used in this case).\n\n## Train\nIssue ```./train --help``` for options to start a training session, default arguments should work out-of-the-box.\n\nYou need to place the dataset following the next directory convention:\n\n    .\n    ├── mapillary                   \n    |   ├── training\n    |   |   ├── images             # Contains the input images\n    |   |   └── instances          # Contains the target labels\n    |   ├── validation\n    |   |   ├── images\n    |   |   └── instances\n    |   └── testing\n    |   |   └── images\n    \n\nThese are the results of training for 300 epochs ```./train --epochs 300```\n\n### Training\n![conv6_cls_categorical_accuracy](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/conv6_cls_categorical_accuracy.png)\n![conv6_cls_loss](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/conv6_cls_loss.png)\n![loss](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/loss.png)\n\n### Validation\n![val_conv6_cls_categorical_accuracy](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/val_conv6_cls_categorical_accuracy.png)\n![val_conv6_cls_loss](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/val_conv6_cls_loss.png)\n![val_loss](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/val_loss.png)\n\n## Test\nIssue ```./test --help``` for options to start a testing session, default arguments should work out-of-the-box.\n\n### Output examples\n![10](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/10.png)\n![07](https://raw.githubusercontent.com/ai-tor/Keras-ICNet/master/output/7.png)\n\n## TODO\n* Perform class weighting\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faitorzip%2Fkeras-icnet","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Faitorzip%2Fkeras-icnet","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Faitorzip%2Fkeras-icnet/lists"}