forked from PulseFocusPlatform/PulseFocusPlatform
124 lines
2.8 KiB
YAML
124 lines
2.8 KiB
YAML
architecture: BlazeFace
|
|
max_iters: 320000
|
|
pretrain_weights:
|
|
use_gpu: true
|
|
snapshot_iter: 10000
|
|
log_iter: 20
|
|
metric: WIDERFACE
|
|
save_dir: output
|
|
weights: output/blazeface_nas/model_final
|
|
# 1(label_class) + 1(background)
|
|
num_classes: 2
|
|
|
|
BlazeFace:
|
|
backbone: BlazeNet
|
|
output_decoder:
|
|
keep_top_k: 750
|
|
nms_threshold: 0.3
|
|
nms_top_k: 5000
|
|
score_threshold: 0.01
|
|
min_sizes: [[16.,24.], [32., 48., 64., 80., 96., 128.]]
|
|
use_density_prior_box: false
|
|
|
|
BlazeNet:
|
|
blaze_filters: [[12, 12], [12, 12, 2], [12, 12]]
|
|
double_blaze_filters: [[12, 16, 24, 2], [24, 12, 24], [24, 16, 72, 2], [72, 12, 72]]
|
|
with_extra_blocks: true
|
|
lite_edition: false
|
|
|
|
LearningRate:
|
|
base_lr: 0.001
|
|
schedulers:
|
|
- !PiecewiseDecay
|
|
gamma: 0.1
|
|
milestones: [240000, 300000]
|
|
|
|
OptimizerBuilder:
|
|
optimizer:
|
|
momentum: 0.0
|
|
type: RMSPropOptimizer
|
|
regularizer:
|
|
factor: 0.0005
|
|
type: L2
|
|
|
|
TrainReader:
|
|
inputs_def:
|
|
image_shape: [3, 640, 640]
|
|
fields: ['image', 'gt_bbox', 'gt_class']
|
|
dataset:
|
|
!WIDERFaceDataSet
|
|
dataset_dir: dataset/wider_face
|
|
anno_path: wider_face_split/wider_face_train_bbx_gt.txt
|
|
image_dir: WIDER_train/images
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
- !NormalizeBox {}
|
|
- !RandomDistort
|
|
brightness_lower: 0.875
|
|
brightness_upper: 1.125
|
|
is_order: true
|
|
- !ExpandImage
|
|
max_ratio: 4
|
|
prob: 0.5
|
|
- !CropImageWithDataAchorSampling
|
|
anchor_sampler:
|
|
- [1, 10, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0, 0.2, 0.0]
|
|
batch_sampler:
|
|
- [1, 50, 1.0, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
|
|
- [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
|
|
- [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
|
|
- [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
|
|
- [1, 50, 0.3, 1.0, 1.0, 1.0, 0.0, 0.0, 1.0, 0.0]
|
|
target_size: 640
|
|
- !RandomInterpImage
|
|
target_size: 640
|
|
- !RandomFlipImage
|
|
is_normalized: true
|
|
- !Permute {}
|
|
- !NormalizeImage
|
|
is_scale: false
|
|
mean: [104, 117, 123]
|
|
std: [127.502231, 127.502231, 127.502231]
|
|
batch_size: 8
|
|
use_process: true
|
|
worker_num: 8
|
|
shuffle: true
|
|
|
|
EvalReader:
|
|
inputs_def:
|
|
fields: ['image', 'im_id']
|
|
dataset:
|
|
!WIDERFaceDataSet
|
|
dataset_dir: dataset/wider_face
|
|
anno_path: wider_face_split/wider_face_val_bbx_gt.txt
|
|
image_dir: WIDER_val/images
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
- !NormalizeBox {}
|
|
- !NormalizeImage
|
|
is_channel_first: false
|
|
is_scale: false
|
|
mean: [123, 117, 104]
|
|
std: [127.502231, 127.502231, 127.502231]
|
|
- !Permute {}
|
|
batch_size: 1
|
|
|
|
TestReader:
|
|
inputs_def:
|
|
fields: ['image', 'im_id', 'im_shape']
|
|
dataset:
|
|
!ImageFolder
|
|
use_default_label: true
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
- !NormalizeImage
|
|
is_channel_first: false
|
|
is_scale: false
|
|
mean: [123, 117, 104]
|
|
std: [127.502231, 127.502231, 127.502231]
|
|
- !Permute {}
|
|
batch_size: 1
|