{"id":20812373,"url":"https://github.com/osmr/facedetver","last_synced_at":"2025-03-12T04:45:27.717Z","repository":{"id":131249439,"uuid":"207882431","full_name":"osmr/facedetver","owner":"osmr","description":"Face Detection Verifier","archived":false,"fork":false,"pushed_at":"2019-09-19T09:21:16.000Z","size":149,"stargazers_count":2,"open_issues_count":0,"forks_count":2,"subscribers_count":1,"default_branch":"master","last_synced_at":"2025-01-18T14:53:23.141Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":null,"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/osmr.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":"2019-09-11T18:41:55.000Z","updated_at":"2019-12-16T02:13:00.000Z","dependencies_parsed_at":"2023-03-10T15:30:57.392Z","dependency_job_id":null,"html_url":"https://github.com/osmr/facedetver","commit_stats":null,"previous_names":[],"tags_count":3,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osmr%2Ffacedetver","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osmr%2Ffacedetver/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osmr%2Ffacedetver/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/osmr%2Ffacedetver/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/osmr","download_url":"https://codeload.github.com/osmr/facedetver/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":243158972,"owners_count":20245669,"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":[],"created_at":"2024-11-17T20:53:41.513Z","updated_at":"2025-03-12T04:45:27.694Z","avatar_url":"https://github.com/osmr.png","language":"Python","funding_links":[],"categories":[],"sub_categories":[],"readme":"# Face Detection Verifier\nThis repo contains scripts for solving the binary classification problem, where the positive class is undistorted images\nof a person’s face, and the negative class is everything else, including images of parts of a person’s face, face\ndrawings, etc.  \n\nThe repository contains scripts for building and analyzing the corresponding dataset, for training and testing models.\nTwo deep learning frameworks are supported: MXNet/Gluon and PyTorch. All scripts are completely duplicated.\nIn addition, the releases contain two training datasets and four models that solve the problem.\n\n## Deployment Instructions \nRecommended repository deployment protocol on the machine with CUDA 10.0 and cuDNN 7:\n1. Install prerequesities for MXNet:\n    ```\n    apt update\n    apt upgrade\n    apt install -y htop mc wget unzip python3-pip ipython3\n    apt install -y build-essential git ninja-build ccache\n    apt install -y apt-transport-https build-essential ca-certificates curl git libatlas-base-dev libcurl4-openssl-dev libjemalloc-dev libhdf5-dev liblapack-dev libopenblas-dev libopencv-dev libturbojpeg libzmq3-dev ninja-build software-properties-common sudo vim-nox\n    apt install -y libopenblas-dev libopencv-dev\n    apt install -y libsm6 libxext6 libxrender-dev\n    ```\n2. Install pip-packages from `requirements.txt`: \n    ```\n    pip3 install --upgrade numpy opencv-python imgaug tqdm\n    pip3 install --upgrade mxnet-cu100 gluoncv2\n    pip3 install --upgrade torch torchvision pytorchcv\n    ```\n3. Clone the repo:\n    ```\n    mkdir projects\n    cd projects\n    git clone https://github.com/osmr/facedetver.git\n    ```\n4. Create directory for dataset and models:\n    ```\n    mkdir facedetver_data\n    cd facedetver_data\n    ```\n5. Download and extract dataset FDV1:\n    ```\n    mkdir fdv1\n    cd fdv1\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.1/fdv1_test.zip\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.1/fdv1_train.zip\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.1/fdv1_val.zip\n    unzip fdv1_test.zip\n    unzip fdv1_train.zip\n    unzip fdv1_val.zip\n    ```\n6. Or download and extract dataset FDV2:\n    ```\n    mkdir fdv2\n    cd fdv2\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.2/fdv2_test.zip\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.2/fdv2_train.zip\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.2/fdv2_val.zip\n    unzip fdv2_test.zip\n    unzip fdv2_train.zip\n    unzip fdv2_val.zip\n    ```\n7. Download and extract a model:\n    ```\n    cd ..\n    mkdir resnet18_fdv1-0014\n    cd resnet18_fdv1-0014\n    wget https://github.com/osmr/facedetver/releases/download/v0.0.3/resnet18_fdv1-0014-a03f116e.params.zip\n    unzip resnet18_fdv1-0014-a03f116e.params.zip\n    ```\n8. Run a testing script:\n    ```\n    cd ../../facedetver\n    python3 eval_gl.py --num-gpus=1 --model=resnet18 --save-dir=../facedetver_data/resnet18_fdv1-0014/ --batch-size=100 -j=4 --resume=../facedetver_data/resnet18_fdv1-0014/resnet18_fdv1-0014-a03f116e.params --calc-flops --show-bad-samples --data-subset=test\n    ```\n\n## Pretrainded Models  \n\n| Model | Dataset | Framework | Acc | F1 | MCC | Params | FLOPs/2 | Remarks |\n| --- | --- | --- | ---: | ---: | ---: | ---: | ---: | --- |\n| ResNet-18 | FDV1 | Gluon | 0.9976 | 0.9976 | 0.9952 | 11,177,538 | 1,819.90M | Training ([log](https://github.com/osmr/facedetver/releases/download/v0.0.3/resnet18_fdv1-0014-a03f116e.params.log)) |\n| ResNet-18 | FDV1 | PyTorch | 0.9976 | 0.9976 | 0.9952 | 11,177,538 | 1,819.90M | Training ([log](https://github.com/osmr/facedetver/releases/download/v0.0.3/resnet18_fdv1-0011-85475034.pth.log)) |\n| ResNet-18 | FDV2 | Gluon | 0.9971 | 0.9971 | 0.9942 | 11,177,538 | 1,819.90M | Training ([log](https://github.com/osmr/facedetver/releases/download/v0.0.3/resnet18_fdv2-0011-391f0c7e.params.log)) |\n| ResNet-18 | FDV2 | PyTorch | 0.9971 | 0.9971 | 0.9942 | 11,177,538 | 1,819.90M | Training ([log](https://github.com/osmr/facedetver/releases/download/v0.0.3/resnet18_fdv2-0009-e1a3e6f2.pth.log)) |\n\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fosmr%2Ffacedetver","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fosmr%2Ffacedetver","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fosmr%2Ffacedetver/lists"}