tinypose3d_human36M.yml

use_gpu: true
log_iter: 5
save_dir: output
snapshot_epoch: 1
weights: output/tinypose3d_human36M/model_final
epoch: 220
num_joints: &num_joints 24
pixel_std: &pixel_std 200
metric: Pose3DEval
num_classes: 1
train_height: &train_height 128
train_width: &train_width 128
trainsize: &trainsize [*train_width, *train_height]

#####model
architecture: TinyPose3DHRNet
pretrain_weights: https://bj.bcebos.com/v1/paddledet/models/keypoint/tinypose_128x96.pdparams

TinyPose3DHRNet:
  backbone: LiteHRNet
  post_process: HR3DNetPostProcess
  fc_channel: 1024
  num_joints: *num_joints
  width: &width 40
  loss: Pose3DLoss

LiteHRNet:
  network_type: wider_naive
  freeze_at: -1
  freeze_norm: false
  return_idx: [0]

Pose3DLoss:
  weight_3d: 1.0
  weight_2d: 0.0

#####optimizer
LearningRate:
  base_lr: 0.0001
  schedulers:
  - !PiecewiseDecay
    milestones: [17, 21]
    gamma: 0.1
  - !LinearWarmup
    start_factor: 0.01
    steps: 1000

OptimizerBuilder:
  optimizer:
    type: Adam
  regularizer:
    factor: 0.0
    type: L2


#####data
TrainDataset:
  !Pose3DDataset
    dataset_dir: Human3.6M
    image_dirs: ["Images"]
    anno_list:  ['Human3.6m_train.json']
    num_joints: *num_joints
    test_mode: False

EvalDataset:
  !Pose3DDataset
    dataset_dir: Human3.6M
    image_dirs: ["Images"]
    anno_list: ['Human3.6m_valid.json']
    num_joints: *num_joints
    test_mode: True

TestDataset:
  !ImageFolder
    anno_path: dataset/coco/keypoint_imagelist.txt

worker_num: 4
global_mean: &global_mean [0.485, 0.456, 0.406]
global_std: &global_std [0.229, 0.224, 0.225]
TrainReader:
  sample_transforms:
    - SinglePoseAffine:
        trainsize: *trainsize
        rotate: [0.5, 30] #[prob, rotate range]
        scale: [0.5, 0.25] #[prob, scale range]
  batch_transforms:
    - NormalizeImage:
        mean: *global_mean
        std: *global_std
        is_scale: true
    - Permute: {}
  batch_size: 128
  shuffle: true
  drop_last: true

EvalReader:
  sample_transforms:
    - SinglePoseAffine:
        trainsize: *trainsize
        rotate: [0., 30]
        scale: [0., 0.25]
  batch_transforms:
    - NormalizeImage:
        mean: *global_mean
        std: *global_std
        is_scale: true
    - Permute: {}
  batch_size: 128

TestReader:
  inputs_def:
    image_shape: [3, *train_height, *train_width]
  sample_transforms:
    - Decode: {}
    - TopDownEvalAffine:
        trainsize: *trainsize
    - NormalizeImage:
        mean: *global_mean
        std: *global_std
        is_scale: true
    - Permute: {}
  batch_size: 1
  fuse_normalize: false