PulseFocusPlatform/static/configs/ppyolo/ppyolo_reader.yml

112 lines
2.7 KiB
YAML

TrainReader:
inputs_def:
fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
num_max_boxes: 50
dataset:
!COCODataSet
image_dir: train2017
anno_path: annotations/instances_train2017.json
dataset_dir: dataset/coco
with_background: false
sample_transforms:
- !DecodeImage
to_rgb: True
with_mixup: True
- !MixupImage
alpha: 1.5
beta: 1.5
- !ColorDistort {}
- !RandomExpand
ratio: 2.0
fill_value: [123.675, 116.28, 103.53]
- !RandomCrop {}
- !RandomFlipImage
is_normalized: false
- !NormalizeBox {}
- !PadBox
num_max_boxes: 50
- !BboxXYXY2XYWH {}
batch_transforms:
- !RandomShape
sizes: [320, 352, 384, 416, 448, 480, 512, 544, 576, 608]
random_inter: True
- !NormalizeImage
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
is_scale: True
is_channel_first: false
- !Permute
to_bgr: false
channel_first: True
# Gt2YoloTarget is only used when use_fine_grained_loss set as true,
# this operator will be deleted automatically if use_fine_grained_loss
# is set as false
- !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: 24
shuffle: true
mixup_epoch: 25000
drop_last: true
worker_num: 8
bufsize: 4
use_process: true
EvalReader:
inputs_def:
fields: ['image', 'im_size', 'im_id']
num_max_boxes: 50
dataset:
!COCODataSet
image_dir: val2017
anno_path: annotations/instances_val2017.json
dataset_dir: dataset/coco
with_background: false
sample_transforms:
- !DecodeImage
to_rgb: True
- !ResizeImage
target_size: 608
interp: 2
- !NormalizeImage
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
is_scale: True
is_channel_first: false
- !PadBox
num_max_boxes: 50
- !Permute
to_bgr: false
channel_first: True
batch_size: 8
drop_empty: false
worker_num: 8
bufsize: 4
TestReader:
inputs_def:
image_shape: [3, 608, 608]
fields: ['image', 'im_size', 'im_id']
dataset:
!ImageFolder
anno_path: annotations/instances_val2017.json
with_background: false
sample_transforms:
- !DecodeImage
to_rgb: True
- !ResizeImage
target_size: 608
interp: 2
- !NormalizeImage
mean: [0.485, 0.456, 0.406]
std: [0.229, 0.224, 0.225]
is_scale: True
is_channel_first: false
- !Permute
to_bgr: false
channel_first: True
batch_size: 1