PulseFocusPlatform/static/configs/solov2/solov2_r101_vd_fpn_3x.yml

108 lines
2.0 KiB
YAML

architecture: SOLOv2
use_gpu: true
max_iters: 270000
snapshot_iter: 30000
log_smooth_window: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet101_vd_pretrained.tar
metric: COCO
weights: output/solov2_r101_vd_fpn_3x/model_final
num_classes: 81
use_ema: true
ema_decay: 0.9998
SOLOv2:
backbone: ResNet
fpn: FPN
bbox_head: SOLOv2Head
mask_head: SOLOv2MaskHead
ResNet:
depth: 101
feature_maps: [2, 3, 4, 5]
freeze_at: 2
norm_type: bn
dcn_v2_stages: [3, 4, 5]
variant: d
FPN:
max_level: 6
min_level: 2
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
reverse_out: True
SOLOv2Head:
seg_feat_channels: 512
stacked_convs: 4
num_grids: [40, 36, 24, 16, 12]
kernel_out_channels: 256
solov2_loss: SOLOv2Loss
mask_nms: MaskMatrixNMS
dcn_v2_stages: [0, 1, 2, 3]
SOLOv2MaskHead:
in_channels: 128
out_channels: 256
start_level: 0
end_level: 3
use_dcn_in_tower: True
SOLOv2Loss:
ins_loss_weight: 3.0
focal_loss_gamma: 2.0
focal_loss_alpha: 0.25
MaskMatrixNMS:
pre_nms_top_n: 500
post_nms_top_n: 100
LearningRate:
base_lr: 0.01
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [180000, 240000]
- !LinearWarmup
start_factor: 0.
steps: 1000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
_READER_: 'solov2_reader.yml'
TrainReader:
batch_size: 2
sample_transforms:
- !DecodeImage
to_rgb: true
- !Poly2Mask {}
- !ResizeImage
target_size: [640, 672, 704, 736, 768, 800]
max_size: 1333
interp: 1
use_cv2: true
resize_box: true
- !RandomFlipImage
prob: 0.5
- !NormalizeImage
is_channel_first: false
is_scale: true
mean: [0.485,0.456,0.406]
std: [0.229, 0.224,0.225]
- !Permute
to_bgr: false
channel_first: true
batch_transforms:
- !PadBatch
pad_to_stride: 32
- !Gt2Solov2Target
num_grids: [40, 36, 24, 16, 12]
scale_ranges: [[1, 96], [48, 192], [96, 384], [192, 768], [384, 2048]]
coord_sigma: 0.2