DocumentAIKit/configs/mot/bytetrack/_base_/ppyoloe_mot_reader_640x640.yml

worker_num: 4
eval_height: &eval_height 640
eval_width: &eval_width 640
eval_size: &eval_size [*eval_height, *eval_width]

TrainReader:
  sample_transforms:
    - Decode: {}
    - RandomDistort: {}
    - RandomExpand: {fill_value: [123.675, 116.28, 103.53]}
    - RandomCrop: {}
    - RandomFlip: {}
  batch_transforms:
    - BatchRandomResize: {target_size: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608, 640, 672, 704, 736, 768], random_size: True, random_interp: True, keep_ratio: False}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
    - PadGT: {}
  batch_size: 8
  shuffle: true
  drop_last: true
  use_shared_memory: true
  collate_batch: true

EvalReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 8

TestReader:
  inputs_def:
    image_shape: [3, *eval_height, *eval_width]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 1


# add MOTReader for MOT evaluation and inference, note batch_size should be 1 in MOT
EvalMOTReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 1

TestMOTReader:
  inputs_def:
    image_shape: [3, *eval_height, *eval_width]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *eval_size, keep_ratio: False, interp: 2}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
  batch_size: 1