{"id":13543205,"url":"https://github.com/Shun14/TextBoxes_plusplus_Tensorflow","last_synced_at":"2025-04-02T12:31:49.690Z","repository":{"id":56283170,"uuid":"159474140","full_name":"Shun14/TextBoxes_plusplus_Tensorflow","owner":"Shun14","description":"Textboxes_plusplus implementation with Tensorflow (python)","archived":false,"fork":false,"pushed_at":"2020-11-16T23:06:43.000Z","size":331,"stargazers_count":82,"open_issues_count":11,"forks_count":25,"subscribers_count":3,"default_branch":"master","last_synced_at":"2024-11-03T10:32:07.597Z","etag":null,"topics":["tensorflow","textboxes"],"latest_commit_sha":null,"homepage":null,"language":"Python","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/Shun14.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}},"created_at":"2018-11-28T09:11:27.000Z","updated_at":"2024-10-09T13:31:29.000Z","dependencies_parsed_at":"2022-08-15T16:00:40.398Z","dependency_job_id":null,"html_url":"https://github.com/Shun14/TextBoxes_plusplus_Tensorflow","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/Shun14%2FTextBoxes_plusplus_Tensorflow","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shun14%2FTextBoxes_plusplus_Tensorflow/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shun14%2FTextBoxes_plusplus_Tensorflow/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/Shun14%2FTextBoxes_plusplus_Tensorflow/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/Shun14","download_url":"https://codeload.github.com/Shun14/TextBoxes_plusplus_Tensorflow/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":246815714,"owners_count":20838492,"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":["tensorflow","textboxes"],"created_at":"2024-08-01T11:00:25.965Z","updated_at":"2025-04-02T12:31:44.682Z","avatar_url":"https://github.com/Shun14.png","language":"Python","funding_links":[],"categories":["Text detection and localization"],"sub_categories":["TextBoxes++ [paper:2018](https://arxiv.org/abs/1801.02765)"],"readme":"# TextBoxes++-TensorFlow\nTextBoxes++ re-implementation using tensorflow.\nThis project is greatly inspired by [slim project](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/contrib/slim)\nAnd many functions are modified based on [SSD-tensorflow project](https://github.com/balancap/SSD-Tensorflow)\n\nAuthor:\n\tZhisheng Zou zzsshun13@gmail.com\n\n# pretrained model \n1. [Google drive](https://drive.google.com/open?id=1kkRyVrx9iFtwEar6OJBKWNVyTLSYsF28)\n\n# environment\n` python2.7/python3.5 ` \n\n`tensorflow-gpu 1.8.0`\n\n`at least one gpu`\n\n# how to use\n\n1. Getting the  xml file like this [example xml](./demo/example/image0.xml) and put the image together because we need the format like this [standard xml](./demo/example/standard.xml)\n   1. picture format: *.png or *.PNG\n2. Getting the xml and flags\n   ensure the XML file is under the same directory as the corresponding image.execute the code: [convert_xml_format.py](./tools/convert_xml_format.py)\n   1. `python tools/convert_xml_format.py -i in_dir  -s split_flag -l save_logs -o output_dir` \n   2. in_dir means the absolute directory which contains the pic and xml\n   3. split_flag means whether or not to split the datasets\n   4. save_logs means whether to save train_xml.txt\n   5. output_dir means where to save xmls\n3. Getting the tfrecords\n   1. `python gene_tfrecords.py --xml_img_txt_path=./logs/train_xml.txt --output_dir=tfrecords` \n   2. xml_img_txt_path like this [train xml](./logs/train_xml.txt)\n   3. output_dir means where to save tfrecords\n4. Training\n   1. `python train.py --train_dir =some_path --dataset_dir=some_path --checkpoint_path=some_path`\n   2. train_dir  store the checkpoints when training\n   3. dataset_dir store the tfrecords for training\n   4. checkpoint_path store the model which needs to be fine tuned\n5. Testing\n   1. `python test.py -m /home/model.ckpt-858 -o test`\n   2. -m which means the model\n   3. -o which means output_result_dir\n   4. -i which means the test img dir\n   5. -c which means use which device to run the test\n   6. -n which means the nms threshold\n   7. -s which means the score threshold\n\n\n\n# Note:\n\n1. when you are training the model, you can run the eval_result.py to eval your model and save the result\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShun14%2FTextBoxes_plusplus_Tensorflow","html_url":"https://awesome.ecosyste.ms/projects/github.com%2FShun14%2FTextBoxes_plusplus_Tensorflow","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2FShun14%2FTextBoxes_plusplus_Tensorflow/lists"}