DocumentAIKit/configs/vitdet/_base_/mask_rcnn_reader.yml

worker_num: 2
TrainReader:
  sample_transforms:
  - Decode: {}
  # - RandomResizeCrop: {resizes: [400, 500, 600], cropsizes: [[384, 600], ], prob: 0.5}
  - RandomResize: {target_size: [[640, 1333], [672, 1333], [704, 1333], [736, 1333], [768, 1333], [800, 1333]], interp: 2, keep_ratio: True}
  - RandomFlip: {prob: 0.5}
  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
  - Permute: {}
  batch_transforms:
  - PadBatch: {pad_to_stride: 32}
  batch_size: 1
  shuffle: true
  drop_last: true
  collate_batch: false
  use_shared_memory: true

EvalReader:
  sample_transforms:
  - Decode: {}
  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
  - Permute: {}
  batch_transforms:
  - PadBatch: {pad_to_stride: 32}
  batch_size: 1
  shuffle: false
  drop_last: false


TestReader:
  sample_transforms:
  - Decode: {}
  - Resize: {interp: 2, target_size: [800, 1333], keep_ratio: True}
  - NormalizeImage: {is_scale: true, mean: [0.485,0.456,0.406], std: [0.229, 0.224,0.225]}
  - Permute: {}
  batch_transforms:
  - PadBatch: {pad_to_stride: 32}
  batch_size: 1
  shuffle: false
  drop_last: false