DocumentAIKit/configs/mot/bytetrack/_base_/yolox_mot_reader_800x1440.yml

input_height: &input_height 800
input_width: &input_width 1440
input_size: &input_size [*input_height, *input_width]

worker_num: 4
TrainReader:
  sample_transforms:
    - Decode: {}
    - Mosaic:
        prob: 1.0
        input_dim: *input_size
        degrees: [-10, 10]
        scale: [0.1, 2.0]
        shear: [-2, 2]
        translate: [-0.1, 0.1]
        enable_mixup: True
        mixup_prob: 1.0
        mixup_scale: [0.5, 1.5]
    - AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30}
    - PadResize: {target_size: *input_size}
    - RandomFlip: {}
  batch_transforms:
    - Permute: {}
  batch_size: 6
  shuffle: True
  drop_last: True
  collate_batch: False
  mosaic_epoch: 20

EvalReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *input_size, keep_ratio: True}
    - Pad: {size: *input_size, fill_value: [114., 114., 114.]}
    - Permute: {}
  batch_size: 8

TestReader:
  inputs_def:
    image_shape: [3, 800, 1440]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *input_size, keep_ratio: True}
    - Pad: {size: *input_size, fill_value: [114., 114., 114.]}
    - 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: *input_size, keep_ratio: True}
    - Pad: {size: *input_size, fill_value: [114., 114., 114.]}
    - Permute: {}
  batch_size: 1

TestMOTReader:
  inputs_def:
    image_shape: [3, 800, 1440]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: *input_size, keep_ratio: True}
    - Pad: {size: *input_size, fill_value: [114., 114., 114.]}
    - Permute: {}
  batch_size: 1