tinypose3d_medical_multi_frames.yml

use_gpu: true
log_iter: 5
save_dir: output
snapshot_epoch: 1
weights: output/tinypose_3D_multi_frames/model_final
epoch: 420
num_joints: &num_joints 24
pixel_std: &pixel_std 200
metric: Pose3DEval
num_classes: 1
train_height: &train_height 128
train_width: &train_width 96
trainsize: &trainsize [*train_width, *train_height]
hmsize: &hmsize [24, 32]
flip_perm: &flip_perm [[1, 2], [4, 5], [7, 8], [10, 11], [13, 14], [16, 17], [18, 19], [20, 21], [22, 23]]


#####model
architecture: TinyPose3DHRNet
pretrain_weights: medical_multi_frames_best_model.pdparams

TinyPose3DHRNet:
  backbone: LiteHRNet
  post_process: TinyPose3DPostProcess
  num_joints: *num_joints
  width: &width 40
  loss: KeyPointRegressionMSELoss

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

KeyPointRegressionMSELoss:
  reduction: 'mean'

#####optimizer
LearningRate:
  base_lr: 0.001
  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:
  !Keypoint3DMultiFramesDataset
    dataset_dir: "data/medical/multi_frames/train"
    image_dir: "images"
    p3d_dir: "joint_pc/player_0"
    json_path: "json_results/player_0/player_0.json"
    img_size: *trainsize # w,h
    num_frames: 6


EvalDataset:
  !Keypoint3DMultiFramesDataset
    dataset_dir: "data/medical/multi_frames/val"
    image_dir: "images"
    p3d_dir: "joint_pc/player_0"
    json_path: "json_results/player_0/player_0.json"
    img_size: *trainsize # w,h
    num_frames: 6

TestDataset:
  !Keypoint3DMultiFramesDataset
    dataset_dir: "data/medical/multi_frames/val"
    image_dir: "images"
    p3d_dir: "joint_pc/player_0"
    json_path: "json_results/player_0/player_0.json"
    img_size: *trainsize # w,h
    num_frames: 6

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:
    - CropAndFlipImages:
        crop_range: [556, 1366]
    - RandomFlipHalfBody3DTransformImages:
        scale: 0.25
        rot: 30
        num_joints_half_body: 9
        prob_half_body: 0.3
        pixel_std: *pixel_std
        trainsize: *trainsize
        upper_body_ids: [0, 3, 6, 9, 12, 13, 14, 15, 16, 17, 18, 19, 20, 21, 22, 23]
        flip_pairs: *flip_perm
        do_occlusion: true
    - Resize: {interp: 2, target_size: [*train_height,*train_width], keep_ratio: false}
  batch_transforms:
    - NormalizeImage:
        mean: *global_mean
        std: *global_std
        is_scale: true
    - PermuteImages: {}
  batch_size: 32
  shuffle: true
  drop_last: false

EvalReader:
  sample_transforms:
    - CropAndFlipImages:
        crop_range: [556, 1366]
    - Resize: {interp: 2, target_size: [*train_height,*train_width], keep_ratio: false}
  batch_transforms:
    - NormalizeImage:
        mean: *global_mean
        std: *global_std
        is_scale: true
    - PermuteImages: {}
  batch_size: 32

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