PulseFocusPlatform/static/configs/mobile/cascade_rcnn_mobilenetv3_fp...

220 lines
4.4 KiB
YAML

architecture: CascadeRCNN
max_iters: 500000
snapshot_iter: 50000
use_gpu: true
log_iter: 20
save_dir: output
pretrain_weights: https://paddle-imagenet-models-name.bj.bcebos.com/MobileNetV3_large_x1_0_ssld_pretrained.tar
weights: output/cascade_rcnn_mobilenetv3_fpn_320/model_final
metric: COCO
num_classes: 81
CascadeRCNN:
backbone: MobileNetV3RCNN
fpn: FPN
rpn_head: FPNRPNHead
roi_extractor: FPNRoIAlign
bbox_head: CascadeBBoxHead
bbox_assigner: CascadeBBoxAssigner
MobileNetV3RCNN:
norm_type: bn
freeze_norm: true
norm_decay: 0.0
feature_maps: [2, 3, 4]
conv_decay: 0.00001
lr_mult_list: [0.25, 0.25, 0.5, 0.5, 0.75]
scale: 1.0
model_name: large
FPN:
min_level: 2
max_level: 6
num_chan: 48
has_extra_convs: true
spatial_scale: [0.0625, 0.125, 0.25]
FPNRPNHead:
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]
anchor_start_size: 16
min_level: 2
max_level: 6
num_chan: 48
rpn_target_assign:
rpn_batch_size_per_im: 256
rpn_fg_fraction: 0.5
rpn_positive_overlap: 0.7
rpn_negative_overlap: 0.3
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: 300
post_nms_top_n: 100
FPNRoIAlign:
canconical_level: 3
canonical_size: 112
min_level: 2
max_level: 4
box_resolution: 7
sampling_ratio: 2
CascadeBBoxAssigner:
batch_size_per_im: 512
bbox_reg_weights: [10, 20, 30]
bg_thresh_lo: [0.0, 0.0, 0.0]
bg_thresh_hi: [0.5, 0.6, 0.7]
fg_thresh: [0.5, 0.6, 0.7]
fg_fraction: 0.25
CascadeBBoxHead:
head: CascadeTwoFCHead
bbox_loss: BalancedL1Loss
nms:
keep_top_k: 100
nms_threshold: 0.5
score_threshold: 0.05
BalancedL1Loss:
alpha: 0.5
gamma: 1.5
beta: 1.0
loss_weight: 1.0
CascadeTwoFCHead:
mlp_dim: 128
LearningRate:
base_lr: 0.02
schedulers:
- !CosineDecay
max_iters: 500000
- !LinearWarmup
start_factor: 0.1
steps: 500
OptimizerBuilder:
optimizer:
momentum: 0.9
type: Momentum
regularizer:
factor: 0.00004
type: L2
TrainReader:
inputs_def:
fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_crowd']
dataset:
!COCODataSet
image_dir: train2017
anno_path: annotations/instances_train2017.json
dataset_dir: dataset/coco
sample_transforms:
- !DecodeImage
to_rgb: true
- !RandomFlipImage
prob: 0.5
- !AutoAugmentImage
autoaug_type: v1
- !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: [224, 256, 288, 320, 352, 384]
max_size: 512
interp: 1
use_cv2: true
- !Permute
to_bgr: false
channel_first: true
batch_transforms:
- !PadBatch
pad_to_stride: 32
use_padded_im_info: false
batch_size: 2
shuffle: true
worker_num: 2
use_process: false
TestReader:
inputs_def:
# set image_shape if needed
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: 320
target_size: 320
use_cv2: true
- !Permute
channel_first: true
to_bgr: false
batch_transforms:
- !PadBatch
pad_to_stride: 32
use_padded_im_info: true
batch_size: 1
shuffle: false
EvalReader:
inputs_def:
fields: ['image', 'im_info', 'im_id', 'im_shape']
# for voc
#fields: ['image', 'im_info', 'im_id', 'gt_bbox', 'gt_class', 'is_difficult']
dataset:
!COCODataSet
image_dir: val2017
anno_path: annotations/instances_val2017.json
dataset_dir: dataset/coco
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: 320
target_size: 320
use_cv2: true
- !Permute
channel_first: true
to_bgr: false
batch_transforms:
- !PadBatch
pad_to_stride: 32
use_padded_im_info: true
batch_size: 1
shuffle: false
drop_empty: false
worker_num: 2