DocumentAIKit/configs/mot/bytetrack/_base_/yolov3_mot_reader_608x608.yml

worker_num: 2
TrainReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}
    - Mixup: {alpha: 1.5, beta: 1.5}
    - 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], random_size: True, random_interp: True, keep_ratio: False}
    - NormalizeBox: {}
    - PadBox: {num_max_boxes: 50}
    - BboxXYXY2XYWH: {}
    - NormalizeImage: {mean: [0.485, 0.456, 0.406], std: [0.229, 0.224, 0.225], is_scale: True}
    - Permute: {}
    - Gt2YoloTarget: {anchor_masks: [[6, 7, 8], [3, 4, 5], [0, 1, 2]], anchors: [[10, 13], [16, 30], [33, 23], [30, 61], [62, 45], [59, 119], [116, 90], [156, 198], [373, 326]], downsample_ratios: [32, 16, 8]}
  batch_size: 8
  shuffle: true
  drop_last: true
  mixup_epoch: 250
  use_shared_memory: true

EvalReader:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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, 608, 608]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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:
  inputs_def:
    num_max_boxes: 50
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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, 608, 608]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [608, 608], 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