PulseFocusPlatform/static/configs/mask_rcnn_r50_2x.yml

105 lines
1.9 KiB
YAML

architecture: MaskRCNN
use_gpu: true
max_iters: 360000
snapshot_iter: 10000
log_iter: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
metric: COCO
weights: output/mask_rcnn_r50_2x/model_final
num_classes: 81
MaskRCNN:
backbone: ResNet
rpn_head: RPNHead
roi_extractor: RoIAlign
bbox_assigner: BBoxAssigner
bbox_head: BBoxHead
mask_assigner: MaskAssigner
mask_head: MaskHead
ResNet:
norm_type: affine_channel
norm_decay: 0.
depth: 50
feature_maps: 4
freeze_at: 2
ResNetC5:
depth: 50
norm_type: affine_channel
RPNHead:
anchor_generator:
anchor_sizes: [32, 64, 128, 256, 512]
aspect_ratios: [0.5, 1.0, 2.0]
stride: [16.0, 16.0]
variance: [1.0, 1.0, 1.0, 1.0]
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_negative_overlap: 0.3
rpn_positive_overlap: 0.7
rpn_straddle_thresh: 0.0
train_proposal:
min_size: 0.0
nms_thresh: 0.7
pre_nms_top_n: 12000
post_nms_top_n: 2000
test_proposal:
min_size: 0.0
nms_thresh: 0.7
pre_nms_top_n: 6000
post_nms_top_n: 1000
RoIAlign:
resolution: 14
spatial_scale: 0.0625
sampling_ratio: 0
BBoxHead:
head: ResNetC5
nms:
keep_top_k: 100
nms_threshold: 0.5
normalized: false
score_threshold: 0.05
MaskHead:
dilation: 1
conv_dim: 256
resolution: 14
BBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [0.1, 0.1, 0.2, 0.2]
bg_thresh_hi: 0.5
bg_thresh_lo: 0.0
fg_fraction: 0.25
fg_thresh: 0.5
MaskAssigner:
resolution: 14
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [240000, 320000]
#start the warm up from base_lr * start_factor
- !LinearWarmup
start_factor: 0.3333333333333333
steps: 500
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
_READER_: 'mask_reader.yml'