yolox_nano_300e_coco.yml

_BASE_: [
  '../datasets/coco_detection.yml',
  '../runtime.yml',
  './_base_/optimizer_300e.yml',
  './_base_/yolox_cspdarknet.yml',
  './_base_/yolox_reader.yml'
]
depth_mult: 0.33
width_mult: 0.25

log_iter: 100
snapshot_epoch: 10
weights: output/yolox_nano_300e_coco/model_final


### model config:
# Note: YOLOX-nano use depthwise conv in backbone, neck and head.
YOLOX:
  backbone: CSPDarkNet
  neck: YOLOCSPPAN
  head: YOLOXHead
  size_stride: 32
  size_range: [10, 20] # multi-scale range [320*320 ~ 640*640]

CSPDarkNet:
  arch: "X"
  return_idx: [2, 3, 4]
  depthwise: True

YOLOCSPPAN:
  depthwise: True

YOLOXHead:
  depthwise: True


### reader config:
# Note: YOLOX-tiny/nano uses 416*416 for evaluation and inference.
#       And multi-scale training setting is in model config, TrainReader's operators use 640*640 as default.
worker_num: 4
TrainReader:
  sample_transforms:
    - Decode: {}
    - Mosaic:
        prob: 0.5 # 1.0 in YOLOX-tiny/s/m/l/x
        input_dim: [640, 640]
        degrees: [-10, 10]
        scale: [0.5, 1.5] # [0.1, 2.0] in YOLOX-s/m/l/x
        shear: [-2, 2]
        translate: [-0.1, 0.1]
        enable_mixup: False # True in YOLOX-s/m/l/x
    - AugmentHSV: {is_bgr: False, hgain: 5, sgain: 30, vgain: 30}
    - PadResize: {target_size: 640}
    - RandomFlip: {}
  batch_transforms:
    - Permute: {}
  batch_size: 8
  shuffle: True
  drop_last: True
  collate_batch: False
  mosaic_epoch: 285


EvalReader:
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
    - Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
    - Permute: {}
  batch_size: 8


TestReader:
  inputs_def:
    image_shape: [3, 416, 416]
  sample_transforms:
    - Decode: {}
    - Resize: {target_size: [416, 416], keep_ratio: True, interp: 1}
    - Pad: {size: [416, 416], fill_value: [114., 114., 114.]}
    - Permute: {}
  batch_size: 1