PulseFocusPlatform/static/configs/mobile/ssdlite_mobilenet_v3_large.yml

163 lines
3.6 KiB
YAML

architecture: SSD
use_gpu: true
max_iters: 400000
snapshot_iter: 20000
log_iter: 20
metric: COCO
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar
save_dir: output
weights: output/ssdlite_mobilenet_v3_large/model_final
# 80(label_class) + 1(background)
num_classes: 81
SSD:
backbone: MobileNetV3
multi_box_head: SSDLiteMultiBoxHead
output_decoder:
background_label: 0
keep_top_k: 200
nms_eta: 1.0
nms_threshold: 0.45
nms_top_k: 400
score_threshold: 0.01
MobileNetV3:
scale: 1.0
model_name: large
extra_block_filters: [[256, 512], [128, 256], [128, 256], [64, 128]]
feature_maps: [5, 7, 8, 9, 10, 11]
lr_mult_list: [0.25, 0.25, 0.5, 0.5, 0.75]
conv_decay: 0.00004
multiplier: 0.5
SSDLiteMultiBoxHead:
aspect_ratios: [[2.], [2., 3.], [2., 3.], [2., 3.], [2., 3.], [2., 3.]]
base_size: 320
steps: [16, 32, 64, 107, 160, 320]
flip: true
clip: true
max_ratio: 95
min_ratio: 20
offset: 0.5
conv_decay: 0.00004
LearningRate:
base_lr: 0.4
schedulers:
- !CosineDecay
max_iters: 400000
- !LinearWarmup
start_factor: 0.33333
steps: 2000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0005
type: L2
TrainReader:
inputs_def:
image_shape: [3, 320, 320]
fields: ['image', 'gt_bbox', 'gt_class']
dataset:
!COCODataSet
dataset_dir: dataset/coco
anno_path: annotations/instances_train2017.json
image_dir: train2017
sample_transforms:
- !DecodeImage
to_rgb: true
- !RandomDistort
brightness_lower: 0.875
brightness_upper: 1.125
is_order: true
- !RandomExpand
fill_value: [123.675, 116.28, 103.53]
- !RandomCrop
allow_no_crop: false
- !NormalizeBox {}
- !ResizeImage
interp: 1
target_size: 320
use_cv2: false
- !RandomFlipImage
is_normalized: false
- !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: 64
shuffle: true
drop_last: true
# Number of working threads/processes. To speed up, can be set to 16 or 32 etc.
worker_num: 8
# Size of shared memory used in result queue. After increasing `worker_num`, need expand `memsize`.
memsize: 8G
# Buffer size for multi threads/processes.one instance in buffer is one batch data.
# To speed up, can be set to 64 or 128 etc.
bufsize: 32
use_process: true
EvalReader:
inputs_def:
image_shape: [3, 320, 320]
fields: ['image', 'gt_bbox', 'gt_class', 'im_shape', 'im_id']
dataset:
!COCODataSet
dataset_dir: dataset/coco
anno_path: annotations/instances_val2017.json
image_dir: val2017
sample_transforms:
- !DecodeImage
to_rgb: true
- !NormalizeBox {}
- !ResizeImage
interp: 1
target_size: 320
use_cv2: false
- !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: 8
worker_num: 8
bufsize: 32
use_process: false
TestReader:
inputs_def:
image_shape: [3,320,320]
fields: ['image', 'im_id', 'im_shape']
dataset:
!ImageFolder
anno_path: annotations/instances_val2017.json
sample_transforms:
- !DecodeImage
to_rgb: true
- !ResizeImage
interp: 1
max_size: 0
target_size: 320
use_cv2: 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
batch_size: 1