PulseFocusPlatform/static/configs/yolov3_mobilenet_v1_roadsig...

176 lines
3.9 KiB
YAML

architecture: YOLOv3
use_gpu: true
max_iters: 3600
log_smooth_window: 20
save_dir: output
snapshot_iter: 200
metric: VOC
map_type: integral
pretrain_weights: https://paddlemodels.bj.bcebos.com/object_detection/yolov3_mobilenet_v1.tar
weights: output/yolov3_mobilenet_v1_roadsign/best_model
num_classes: 4
finetune_exclude_pretrained_params: ['yolo_output']
use_fine_grained_loss: false
YOLOv3:
backbone: MobileNet
yolo_head: YOLOv3Head
MobileNet:
norm_decay: 0.
conv_group_scale: 1
with_extra_blocks: false
YOLOv3Head:
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]]
yolo_loss: YOLOv3Loss
nms:
background_label: -1
keep_top_k: 100
nms_threshold: 0.45
nms_top_k: 1000
normalized: false
score_threshold: 0.01
YOLOv3Loss:
ignore_thresh: 0.7
label_smooth: true
LearningRate:
base_lr: 0.0001
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones:
- 2400
- 3300
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 100
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
# _READER_: 'yolov3_reader.yml'
TrainReader:
inputs_def:
fields: ['image', 'gt_bbox', 'gt_class', 'gt_score']
num_max_boxes: 50
dataset:
!VOCDataSet
dataset_dir: dataset/roadsign_voc
anno_path: train.txt
with_background: false
use_default_label: false
sample_transforms:
- !DecodeImage
to_rgb: True
with_mixup: True
- !MixupImage
alpha: 1.5
beta: 1.5
- !ColorDistort {}
- !RandomExpand
fill_value: [123.675, 116.28, 103.53]
ratio: 1.5
- !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: 8
shuffle: true
mixup_epoch: 250
drop_last: true
worker_num: 4
bufsize: 2
use_process: true
EvalReader:
inputs_def:
fields: ['image', 'im_size', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
num_max_boxes: 50
dataset:
!VOCDataSet
dataset_dir: dataset/roadsign_voc
anno_path: valid.txt
with_background: false
use_default_label: 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: 1
drop_empty: false
worker_num: 4
bufsize: 2
TestReader:
inputs_def:
image_shape: [3, 608, 608]
fields: ['image', 'im_size', 'im_id']
dataset:
!ImageFolder
anno_path: dataset/roadsign_voc/label_list.txt
with_background: false
use_default_label: 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