{"id":13454832,"url":"https://github.com/trigeorgis/mdm","last_synced_at":"2025-03-24T07:32:14.438Z","repository":{"id":141722433,"uuid":"62345795","full_name":"trigeorgis/mdm","owner":"trigeorgis","description":"A TensorFlow implementation of the Mnemonic Descent Method.","archived":false,"fork":false,"pushed_at":"2022-05-21T17:31:33.000Z","size":1760,"stargazers_count":124,"open_issues_count":5,"forks_count":48,"subscribers_count":12,"default_branch":"master","last_synced_at":"2024-10-28T22:34:35.542Z","etag":null,"topics":["deep-learning","face","face-alignment","mdm","menpo","pretrained-models","snapchat","tensorflow"],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"bsd-3-clause","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/trigeorgis.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}},"created_at":"2016-06-30T22:20:13.000Z","updated_at":"2024-04-27T09:25:35.000Z","dependencies_parsed_at":null,"dependency_job_id":"757a54b8-0d69-4745-a719-9f76e74c41e4","html_url":"https://github.com/trigeorgis/mdm","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/trigeorgis%2Fmdm","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trigeorgis%2Fmdm/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trigeorgis%2Fmdm/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/trigeorgis%2Fmdm/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/trigeorgis","download_url":"https://codeload.github.com/trigeorgis/mdm/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":245227543,"owners_count":20580896,"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":["deep-learning","face","face-alignment","mdm","menpo","pretrained-models","snapchat","tensorflow"],"created_at":"2024-07-31T08:00:58.340Z","updated_at":"2025-03-24T07:32:12.304Z","avatar_url":"https://github.com/trigeorgis.png","language":"Jupyter Notebook","funding_links":[],"categories":["Models/Projects","Jupyter Notebook","模型项目"],"sub_categories":["微信群"],"readme":"# MDM\n\nA Tensorflow implementation of the Mnemonic Descent Method.\n\n    Mnemonic Descent Method: A recurrent process applied for end-to-end face alignment\n    G. Trigeorgis, P. Snape, M. A. Nicolaou, E. Antonakos, S. Zafeiriou.\n    Proceedings of IEEE International Conference on Computer Vision \u0026 Pattern Recognition (CVPR'16).\n    Las Vegas, NV, USA, June 2016.\n\n# Installation Instructions\n\n\n## Menpo\n\nWe are an avid supporter of the Menpo project (http://www.menpo.org/) which we use\nin various ways throughout the implementation.\n\nPlease look at the installation instructions at:\n\n    http://www.menpo.org/installation/\n\n## TensorFlow\n\nFollow the installation instructions of Tensorflow at and install it inside the conda enviroment you have created\n\n    https://www.tensorflow.org/versions/r0.9/get_started/os_setup.html#installing-from-sources\n\nbut use \n\n    git clone https://github.com/trigeorgis/tensorflow.git\n\nas the TensorFlow repo. This is a fork of Tensorflow (#ff75787c) but it includes some\nextra C++ ops, such as for the extraction of patches around the landmarks.\n\n# Pretrained models\n\nDisclaimer:\nThe pretrained models can only be used for non-commercial academic purposes.\n\nA pretrained model on 300W train set can be found at: https://www.doc.ic.ac.uk/~gt108/theano_mdm.pb\n\n# Training a model\nCurrently the TensorFlow implementation does not contain the same data augmnetation steps\nas we did in the paper, but this will be updated shortly.\n\n```\n    # Activate the conda environment where tf/menpo resides.\n    source activate menpo\n    \n    # Start training\n    python mdm_train.py --datasets='databases/lfpw/trainset/*.png:databases/afw/*.jpg:databases/helen/trainset/*.jpg'\n    \n    # Track the train process and evaluate the current checkpoint against the validation set\n    python mdm_eval.py --dataset_path=\"./databases/ibug/*.jpg\" --num_examples=135 --eval_dir=ckpt/eval_ibug  --device='/cpu:0' --checkpoint_dir=$PWD/ckpt/train\n    \n    python mdm_eval.py --dataset_path=\"./databases/lfpw/testset/*.png\" --num_examples=300 --eval_dir=ckpt/eval_lfpw  --device='/cpu:0' --checkpoint_dir=$PWD/ckpt/train\n    \n    python mdm_eval.py --dataset_path=\"./databases/helen/testset/*.jpg\" --num_examples=330 --eval_dir=ckpt/eval_helen  --device='/cpu:0' --checkpoint_dir=$PWD/ckpt/train\n    \n    # Run tensorboard to visualise the results\n    tensorboard --logdir==$PWD/ckpt\n```\n\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrigeorgis%2Fmdm","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Ftrigeorgis%2Fmdm","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Ftrigeorgis%2Fmdm/lists"}