PulseFocusPlatform/static/configs/retinanet_x101_vd_64x4d_fpn...

90 lines
1.6 KiB
YAML

architecture: RetinaNet
max_iters: 180000
use_gpu: true
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNeXt101_vd_64x4d_pretrained.tar
weights: output/retinanet_x101_vd_64x4d_fpn_1x/model_final
log_iter: 20
snapshot_iter: 30000
metric: COCO
save_dir: output
num_classes: 81
RetinaNet:
backbone: ResNeXt
fpn: FPN
retina_head: RetinaHead
ResNeXt:
depth: 101
feature_maps: [3, 4, 5]
freeze_at: 2
group_width: 4
groups: 64
norm_type: bn
variant: d
FPN:
max_level: 7
min_level: 3
num_chan: 256
spatial_scale: [0.03125, 0.0625, 0.125]
has_extra_convs: true
RetinaHead:
num_convs_per_octave: 4
num_chan: 256
max_level: 7
min_level: 3
prior_prob: 0.01
base_scale: 4
num_scales_per_octave: 3
anchor_generator:
aspect_ratios: [1.0, 2.0, 0.5]
variance: [1.0, 1.0, 1.0, 1.0]
target_assign:
positive_overlap: 0.5
negative_overlap: 0.4
gamma: 2.0
alpha: 0.25
sigma: 3.0151134457776365
output_decoder:
score_thresh: 0.05
nms_thresh: 0.5
pre_nms_top_n: 1000
detections_per_im: 100
nms_eta: 1.0
LearningRate:
base_lr: 0.005
schedulers:
- !PiecewiseDecay
gamma: 0.1
milestones: [120000, 160000]
- !LinearWarmup
start_factor: 0.1
steps: 1000
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.0001
type: L2
_READER_: 'faster_fpn_reader.yml'
TrainReader:
batch_transforms:
- !PadBatch
pad_to_stride: 128
EvalReader:
batch_transforms:
- !PadBatch
pad_to_stride: 128
TestReader:
batch_transforms:
- !PadBatch
pad_to_stride: 128