OpenMMLab Detection Toolbox and Benchmark
https://mmdetection.readthedocs.io/
You can not select more than 25 topics
Topics must start with a letter or number, can include dashes ('-') and can be up to 35 characters long.
138 lines
4.8 KiB
138 lines
4.8 KiB
_base_ = [ |
|
'../_base_/datasets/coco_instance.py', |
|
'../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py' |
|
] |
|
num_stages = 6 |
|
num_proposals = 100 |
|
model = dict( |
|
type='QueryInst', |
|
backbone=dict( |
|
type='ResNet', |
|
depth=50, |
|
num_stages=4, |
|
out_indices=(0, 1, 2, 3), |
|
frozen_stages=1, |
|
norm_cfg=dict(type='BN', requires_grad=True), |
|
norm_eval=True, |
|
style='pytorch', |
|
init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')), |
|
neck=dict( |
|
type='FPN', |
|
in_channels=[256, 512, 1024, 2048], |
|
out_channels=256, |
|
start_level=0, |
|
add_extra_convs='on_input', |
|
num_outs=4), |
|
rpn_head=dict( |
|
type='EmbeddingRPNHead', |
|
num_proposals=num_proposals, |
|
proposal_feature_channel=256), |
|
roi_head=dict( |
|
type='SparseRoIHead', |
|
num_stages=num_stages, |
|
stage_loss_weights=[1] * num_stages, |
|
proposal_feature_channel=256, |
|
bbox_roi_extractor=dict( |
|
type='SingleRoIExtractor', |
|
roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=2), |
|
out_channels=256, |
|
featmap_strides=[4, 8, 16, 32]), |
|
mask_roi_extractor=dict( |
|
type='SingleRoIExtractor', |
|
roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=2), |
|
out_channels=256, |
|
featmap_strides=[4, 8, 16, 32]), |
|
bbox_head=[ |
|
dict( |
|
type='DIIHead', |
|
num_classes=80, |
|
num_ffn_fcs=2, |
|
num_heads=8, |
|
num_cls_fcs=1, |
|
num_reg_fcs=3, |
|
feedforward_channels=2048, |
|
in_channels=256, |
|
dropout=0.0, |
|
ffn_act_cfg=dict(type='ReLU', inplace=True), |
|
dynamic_conv_cfg=dict( |
|
type='DynamicConv', |
|
in_channels=256, |
|
feat_channels=64, |
|
out_channels=256, |
|
input_feat_shape=7, |
|
act_cfg=dict(type='ReLU', inplace=True), |
|
norm_cfg=dict(type='LN')), |
|
loss_bbox=dict(type='L1Loss', loss_weight=5.0), |
|
loss_iou=dict(type='GIoULoss', loss_weight=2.0), |
|
loss_cls=dict( |
|
type='FocalLoss', |
|
use_sigmoid=True, |
|
gamma=2.0, |
|
alpha=0.25, |
|
loss_weight=2.0), |
|
bbox_coder=dict( |
|
type='DeltaXYWHBBoxCoder', |
|
clip_border=False, |
|
target_means=[0., 0., 0., 0.], |
|
target_stds=[0.5, 0.5, 1., 1.])) for _ in range(num_stages) |
|
], |
|
mask_head=[ |
|
dict( |
|
type='DynamicMaskHead', |
|
dynamic_conv_cfg=dict( |
|
type='DynamicConv', |
|
in_channels=256, |
|
feat_channels=64, |
|
out_channels=256, |
|
input_feat_shape=14, |
|
with_proj=False, |
|
act_cfg=dict(type='ReLU', inplace=True), |
|
norm_cfg=dict(type='LN')), |
|
num_convs=4, |
|
num_classes=80, |
|
roi_feat_size=14, |
|
in_channels=256, |
|
conv_kernel_size=3, |
|
conv_out_channels=256, |
|
class_agnostic=False, |
|
norm_cfg=dict(type='BN'), |
|
upsample_cfg=dict(type='deconv', scale_factor=2), |
|
loss_mask=dict( |
|
type='DiceLoss', |
|
loss_weight=8.0, |
|
use_sigmoid=True, |
|
activate=False, |
|
eps=1e-5)) for _ in range(num_stages) |
|
]), |
|
# training and testing settings |
|
train_cfg=dict( |
|
rpn=None, |
|
rcnn=[ |
|
dict( |
|
assigner=dict( |
|
type='HungarianAssigner', |
|
cls_cost=dict(type='FocalLossCost', weight=2.0), |
|
reg_cost=dict(type='BBoxL1Cost', weight=5.0), |
|
iou_cost=dict(type='IoUCost', iou_mode='giou', |
|
weight=2.0)), |
|
sampler=dict(type='PseudoSampler'), |
|
pos_weight=1, |
|
mask_size=28, |
|
) for _ in range(num_stages) |
|
]), |
|
test_cfg=dict( |
|
rpn=None, rcnn=dict(max_per_img=num_proposals, mask_thr_binary=0.5))) |
|
|
|
# optimizer |
|
optimizer = dict( |
|
_delete_=True, |
|
type='AdamW', |
|
lr=0.0001, |
|
weight_decay=0.0001, |
|
paramwise_cfg=dict( |
|
custom_keys={'backbone': dict(lr_mult=0.1, decay_mult=1.0)})) |
|
optimizer_config = dict( |
|
_delete_=True, grad_clip=dict(max_norm=0.1, norm_type=2)) |
|
# learning policy |
|
lr_config = dict(policy='step', step=[8, 11], warmup_iters=1000) |
|
runner = dict(type='EpochBasedRunner', max_epochs=12)
|
|
|