DANet

Dependencies

cuda 10.0
Python 3.6
Pytorch >1.0.0

Get the data

Human3.6m in exponential map can be downloaded from here.

Directory structure:

H3.6m
|-- S1
|-- S5
|-- S6
|-- ...
`-- S11

3DPW from their official website.

Directory structure:

3dpw
|-- imageFiles
|   |-- courtyard_arguing_00
|   |-- courtyard_backpack_00
|   |-- ...
`-- sequenceFiles
    |-- test
    |-- train
    `-- validation

Put the all downloaded datasets in ./datasets directory.

Training

All the running args are defined in opt.py. We use following commands to train on different datasets and representations. To train,

python main_h36m_3d.py --kernel_size 10 --dct_n 20 --input_n 50 --output_n 10 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 66

python main_h36m_ang_60.py --kernel_size 10 --dct_n 20 --input_n 50 --output_n 10 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 60

python main_amass_3d.py --kernel_size 10 --dct_n 35 --input_n 50 --output_n 25 --skip_rate 5 --batch_size 128 --test_batch_size 128 --in_features 54

Evaluation

To evaluate the pretrained model,

python main_h36m_3d_eval.py --is_eval --kernel_size 10 --dct_n 20 --input_n 50 --output_n 25 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 66 --ckpt ./checkpoint/h36m_3d_in50_out10_dctn20/

python main_h36m_ang_60_eval.py --is_eval --kernel_size 10 --dct_n 20 --input_n 50 --output_n 25 --skip_rate 1 --batch_size 32 --test_batch_size 32 --in_features 60 --ckpt ./checkpoint/h36m_ang_in50_out10_dctn20/

python main_amass_3d_eval.py --is_eval --kernel_size 10 --dct_n 35 --input_n 50 --output_n 25 --skip_rate 5 --batch_size 128 --test_batch_size 128 --in_features 54 --ckpt ./checkpoint/amass_3d_in50_out25_dctn30/

Acknowledgments

The overall code framework (dataloading, training, testing etc.) is adapted from HisRepItself.