forked from PulseFocusPlatform/PulseFocusPlatform
226 lines
4.4 KiB
YAML
226 lines
4.4 KiB
YAML
architecture: HybridTaskCascade
|
|
use_gpu: true
|
|
max_iters: 180000
|
|
snapshot_iter: 10000
|
|
log_iter: 50
|
|
save_dir: output
|
|
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/ResNet50_cos_pretrained.tar
|
|
metric: COCO
|
|
weights: output/htc_r50_fpn_1x/model_final
|
|
num_classes: 81
|
|
|
|
HybridTaskCascade:
|
|
backbone: ResNet
|
|
fpn: FPN
|
|
rpn_head: FPNRPNHead
|
|
roi_extractor: FPNRoIAlign
|
|
bbox_head: HTCBBoxHead
|
|
bbox_assigner: CascadeBBoxAssigner
|
|
mask_assigner: MaskAssigner
|
|
mask_head: HTCMaskHead
|
|
fused_semantic_head: FusedSemanticHead
|
|
|
|
ResNet:
|
|
depth: 50
|
|
feature_maps: [2, 3, 4, 5]
|
|
freeze_at: 2
|
|
norm_type: affine_channel
|
|
|
|
FPN:
|
|
max_level: 6
|
|
min_level: 2
|
|
num_chan: 256
|
|
spatial_scale: [0.03125, 0.0625, 0.125, 0.25]
|
|
|
|
FPNRPNHead:
|
|
anchor_generator:
|
|
aspect_ratios: [0.5, 1.0, 2.0]
|
|
variance: [1.0, 1.0, 1.0, 1.0]
|
|
anchor_start_size: 32
|
|
max_level: 6
|
|
min_level: 2
|
|
num_chan: 256
|
|
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: 2000
|
|
post_nms_top_n: 2000
|
|
test_proposal:
|
|
min_size: 0.0
|
|
nms_thresh: 0.7
|
|
pre_nms_top_n: 2000
|
|
post_nms_top_n: 1000
|
|
|
|
# bbox roi extractor
|
|
FPNRoIAlign:
|
|
canconical_level: 4
|
|
canonical_size: 224
|
|
max_level: 5
|
|
min_level: 2
|
|
sampling_ratio: 2
|
|
box_resolution: 7
|
|
mask_resolution: 14
|
|
|
|
# semantic roi extractor
|
|
RoIAlign:
|
|
resolution: 14
|
|
sampling_ratio: 2
|
|
|
|
HTCMaskHead:
|
|
dilation: 1
|
|
conv_dim: 256
|
|
num_convs: 4
|
|
resolution: 28
|
|
lr_ratio: 2.0
|
|
|
|
FusedSemanticHead:
|
|
semantic_num_class: 183
|
|
|
|
CascadeBBoxAssigner:
|
|
batch_size_per_im: 512
|
|
bbox_reg_weights: [10, 20, 30]
|
|
bg_thresh_hi: [0.5, 0.6, 0.7]
|
|
bg_thresh_lo: [0.0, 0.0, 0.0]
|
|
fg_fraction: 0.25
|
|
fg_thresh: [0.5, 0.6, 0.7]
|
|
|
|
MaskAssigner:
|
|
resolution: 28
|
|
|
|
HTCBBoxHead:
|
|
head: CascadeTwoFCHead
|
|
nms: MultiClassSoftNMS
|
|
|
|
MultiClassSoftNMS:
|
|
score_threshold: 0.01
|
|
keep_top_k: 300
|
|
softnms_sigma: 0.5
|
|
|
|
CascadeTwoFCHead:
|
|
mlp_dim: 1024
|
|
|
|
LearningRate:
|
|
base_lr: 0.01
|
|
schedulers:
|
|
- !PiecewiseDecay
|
|
gamma: 0.1
|
|
milestones: [120000, 160000]
|
|
- !LinearWarmup
|
|
start_factor: 0.1
|
|
steps: 1000
|
|
|
|
OptimizerBuilder:
|
|
clip_grad_by_norm: 35.0
|
|
optimizer:
|
|
momentum: 0.9
|
|
type: Momentum
|
|
regularizer:
|
|
factor: 0.0001
|
|
type: L2
|
|
|
|
TrainReader:
|
|
batch_size: 1
|
|
worker_num: 2
|
|
shuffle: true
|
|
dataset:
|
|
!COCODataSet
|
|
dataset_dir: dataset/coco
|
|
anno_path: annotations/instances_train2017.json
|
|
image_dir: train2017
|
|
load_semantic: True
|
|
inputs_def:
|
|
fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd', 'gt_mask', 'semantic']
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
- !RandomFlipImage
|
|
prob: 0.5
|
|
is_mask_flip: true
|
|
- !NormalizeImage
|
|
is_channel_first: false
|
|
is_scale: true
|
|
mean: [0.485,0.456,0.406]
|
|
std: [0.229, 0.224,0.225]
|
|
- !ResizeImage
|
|
target_size: 800
|
|
max_size: 1333
|
|
interp: 1
|
|
use_cv2: true
|
|
- !Permute
|
|
to_bgr: false
|
|
channel_first: true
|
|
batch_transforms:
|
|
- !PadBatch
|
|
pad_to_stride: 32
|
|
use_padded_im_info: false
|
|
|
|
EvalReader:
|
|
inputs_def:
|
|
fields: ['image', 'im_info', 'im_id', 'im_shape']
|
|
dataset:
|
|
!COCODataSet
|
|
image_dir: val2017
|
|
anno_path: annotations/instances_val2017.json
|
|
dataset_dir: dataset/coco
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
- !NormalizeImage
|
|
is_channel_first: false
|
|
is_scale: true
|
|
mean: [0.485,0.456,0.406]
|
|
std: [0.229, 0.224,0.225]
|
|
- !ResizeImage
|
|
interp: 1
|
|
max_size: 1333
|
|
target_size: 800
|
|
use_cv2: true
|
|
- !Permute
|
|
channel_first: true
|
|
to_bgr: false
|
|
batch_transforms:
|
|
- !PadBatch
|
|
pad_to_stride: 32
|
|
use_padded_im_info: false
|
|
batch_size: 1
|
|
shuffle: false
|
|
drop_last: false
|
|
drop_empty: false
|
|
worker_num: 2
|
|
|
|
TestReader:
|
|
inputs_def:
|
|
fields: ['image', 'im_info', 'im_id', 'im_shape']
|
|
dataset:
|
|
!ImageFolder
|
|
anno_path: annotations/instances_val2017.json
|
|
sample_transforms:
|
|
- !DecodeImage
|
|
to_rgb: true
|
|
with_mixup: false
|
|
- !NormalizeImage
|
|
is_channel_first: false
|
|
is_scale: true
|
|
mean: [0.485,0.456,0.406]
|
|
std: [0.229, 0.224,0.225]
|
|
- !ResizeImage
|
|
interp: 1
|
|
max_size: 1333
|
|
target_size: 800
|
|
use_cv2: true
|
|
- !Permute
|
|
channel_first: true
|
|
to_bgr: false
|
|
batch_transforms:
|
|
- !PadBatch
|
|
pad_to_stride: 32
|
|
use_padded_im_info: false
|
|
batch_size: 1
|
|
shuffle: false
|