Sign-Langugage-project

Contributors

_김영민

_곽민지

_이다인

_김영은

Survey

STMC-Transformer : Paper Review(KYM), Paper Review(LDI), Paper Review(KYE)
STMC : Paper Review(KYM), Paper Review(KYE)
NSLT : Paper Review(LDI), Paper Review(KYE), Paper Review(KYM), Paper Review(KMJ)

Environment

OS : Ubuntu 18.04.5(Docker) LTS or Colab
Cuda : 10.0
GPU : Tesla V100-32GB

Data

sample video downlaod - $ sh download_sh/sample_data_dowonload.sh

DataSet Download

Enviorment Setting

$ pip install -r requirements.txt
$ python -m pip install cython
$ sudo apt-get install libyaml-dev

Setting(Alphapose)

$ git clone https://github.com/winston1214/Sign-Langugage-project.git && cd Sign-Langugage-project
$ python setup.py build develop

If you don't run in the COLAB environment or the cuda version is 10.0, refer to this link.

Download pretrained File(Please Download)

If you run this command, you can download weight file at once. $ sh downlaod_sh/weight_download.sh

PreProcessing

1. Split frame

$ python frame_split.py # You have to add the main code.

2. Extract KeyPoint(Alphapose)

python scripts/demo_inference.py --cfg configs/halpe_136/resnet/256x192_res50_lr1e-3_2x-regression.yaml --checkpoint pretrained_models/halpe136_fast_res50_256x192.pt --indir ${img_folder_path} --outdir ${save_dir_path} --form boaz --vis_fast --sp

If you use multi-gpu, you don't have to sp option

Extract KeyPoint

Train

$ python train.py --X_path ${X_train.pickle path} --save_path ${model save directory} \
--pt_name ${save pt model name} --model ${LSTM or GRU} --batch ${BATCH SIZE}

## Example

$ python train.py --X_path /sign_data/ --save_path pt_file/ \
--pt_name model1.pt --model GRU --batch 128 --epochs 100 --dropout 0.5

X_train.pickle : For convenience, we stored and used the values extracted from the keypoint in pickle file format.
- (shape : [video_len, max_frame_len, keypoint_len] # [7129, 376, 246] )

Inference

$ python inference.py --video ${VIDEO_NAME} --outdir ${SAVE_PATH} --pt ${WEIGHT_PATH} --model ${MODEL NAME}

You can simply enjoy demo video at the COLAB

Result

Model	Hyperparameter	Metrics	Final Model
GRU-Attention	Adam CrossEntropy	BLEU	93.4
	Adam CrossEntropy	Accuracy	93.5
	AdamW Scheduler	BLEU	95.1
	AdamW Scheduler	Accuracy	95.0
LSTM	Adam CrossEntropy	BLEU	49.6
	Adam CrossEntropy	Accuracy	50.0
	AdamW Scheduler	BLEU	51.5
	AdamW Scheduler	Accuracy	51.5

We selected a method that applied the (HAND+BODY Keypoint) + (All Frame Random Argumentation) + (Frame Noramlization) technique as the final model.

More experimental results are shown here.

manypeople-AI/Sign-Langugage-project