mirror of
https://github.com/open-mmlab/mmdeploy.git
synced 2025-01-14 08:09:43 +08:00
308e28fcb0
* support cascade (mask) rcnn * fix docstring * support SwinTransformer * move dense_head support to this branch * fix function names * fix part of uts of mmdet * fix for mmdet ut * fix det model cfg for ut * fix test_object_detection.py * fix mmdet object_detection_model.py * fix mmdet yolov3 ort ut * fix part of uts * fix cascade bbox head ut * fix cascade bbox head ut * remove useless ssd ncnn test * fix ncnn wrapper * fix openvino ut for reppoint head * fix openvino cascade mask rcnn * sync codes * support roll * remove unused pad * fix yolox * fix isort * fix lint * fix flake8 * reply for comments and fix failed ut * fix sdk_export in dump_info * fix temp hidden xlsx bugs * fix mmdet regression test * fix lint * fix timer * fix timecount side-effect * adapt profile.py for mmdet 2.0 * hardcode report.txt for T4 benchmark test: temp version * fix no-visualizer case * fix backend_model * fix android build * adapt new mmdet 2.0 0825 * fix new 2.0 * fix test_mmdet_structures * fix test_object_detection * fix codebase import * fix ut * fix all mmdet uts * fix det * fix mmdet trt * fix ncnn onnx optimize
140 lines
4.0 KiB
Python
140 lines
4.0 KiB
Python
# Copyright (c) OpenMMLab. All rights reserved.
|
|
# model settings
|
|
data_preprocessor = dict(
|
|
type='DetDataPreprocessor',
|
|
mean=[123.675, 116.28, 103.53],
|
|
std=[58.395, 57.12, 57.375],
|
|
bgr_to_rgb=True,
|
|
pad_size_divisor=32)
|
|
model = dict(
|
|
type='YOLOV3',
|
|
data_preprocessor=data_preprocessor,
|
|
backbone=dict(
|
|
type='MobileNetV2',
|
|
out_indices=(2, 4, 6),
|
|
act_cfg=dict(type='LeakyReLU', negative_slope=0.1),
|
|
init_cfg=dict(
|
|
type='Pretrained', checkpoint='open-mmlab://mmdet/mobilenet_v2')),
|
|
neck=dict(
|
|
type='YOLOV3Neck',
|
|
num_scales=3,
|
|
in_channels=[320, 96, 32],
|
|
out_channels=[96, 96, 96]),
|
|
bbox_head=dict(
|
|
type='YOLOV3Head',
|
|
num_classes=80,
|
|
in_channels=[96, 96, 96],
|
|
out_channels=[96, 96, 96],
|
|
anchor_generator=dict(
|
|
type='YOLOAnchorGenerator',
|
|
base_sizes=[[(116, 90), (156, 198), (373, 326)],
|
|
[(30, 61), (62, 45), (59, 119)],
|
|
[(10, 13), (16, 30), (33, 23)]],
|
|
strides=[32, 16, 8]),
|
|
bbox_coder=dict(type='YOLOBBoxCoder'),
|
|
featmap_strides=[32, 16, 8],
|
|
loss_cls=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=1.0,
|
|
reduction='sum'),
|
|
loss_conf=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=1.0,
|
|
reduction='sum'),
|
|
loss_xy=dict(
|
|
type='CrossEntropyLoss',
|
|
use_sigmoid=True,
|
|
loss_weight=2.0,
|
|
reduction='sum'),
|
|
loss_wh=dict(type='MSELoss', loss_weight=2.0, reduction='sum')),
|
|
test_cfg=dict(
|
|
nms_pre=1000,
|
|
min_bbox_size=0,
|
|
score_thr=0.05,
|
|
conf_thr=0.005,
|
|
nms=dict(type='nms', iou_threshold=0.45),
|
|
max_per_img=100))
|
|
# dataset settings
|
|
dataset_type = 'CocoDataset'
|
|
data_root = 'data/coco/'
|
|
|
|
file_client_args = dict(backend='disk')
|
|
|
|
test_pipeline = [
|
|
dict(type='LoadImageFromFile', file_client_args=file_client_args),
|
|
dict(type='Resize', scale=(416, 416), keep_ratio=False),
|
|
dict(
|
|
type='PackDetInputs',
|
|
meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape',
|
|
'scale_factor'))
|
|
]
|
|
|
|
val_dataloader = dict(
|
|
batch_size=24,
|
|
num_workers=4,
|
|
persistent_workers=True,
|
|
drop_last=False,
|
|
sampler=dict(type='DefaultSampler', shuffle=False),
|
|
dataset=dict(
|
|
type=dataset_type,
|
|
data_root=data_root,
|
|
ann_file='annotations/instances_val2017.json',
|
|
data_prefix=dict(img='val2017/'),
|
|
test_mode=True,
|
|
pipeline=test_pipeline))
|
|
test_dataloader = val_dataloader
|
|
|
|
val_evaluator = dict(
|
|
type='CocoMetric',
|
|
ann_file=data_root + 'annotations/instances_val2017.json',
|
|
metric='bbox')
|
|
test_evaluator = val_evaluator
|
|
|
|
val_cfg = dict(type='ValLoop')
|
|
test_cfg = dict(type='TestLoop')
|
|
|
|
# learning rate
|
|
param_scheduler = [
|
|
dict(
|
|
type='LinearLR', start_factor=0.001, by_epoch=False, begin=0, end=500),
|
|
dict(
|
|
type='MultiStepLR',
|
|
begin=0,
|
|
end=12,
|
|
by_epoch=True,
|
|
milestones=[8, 11],
|
|
gamma=0.1)
|
|
]
|
|
|
|
# optimizer
|
|
optim_wrapper = dict(
|
|
type='OptimWrapper',
|
|
optimizer=dict(type='SGD', lr=0.02, momentum=0.9, weight_decay=0.0001))
|
|
|
|
default_scope = 'mmdet'
|
|
|
|
default_hooks = dict(
|
|
timer=dict(type='IterTimerHook'),
|
|
logger=dict(type='LoggerHook', interval=50),
|
|
param_scheduler=dict(type='ParamSchedulerHook'),
|
|
checkpoint=dict(type='CheckpointHook', interval=1),
|
|
sampler_seed=dict(type='DistSamplerSeedHook'),
|
|
visualization=dict(type='DetVisualizationHook'))
|
|
|
|
env_cfg = dict(
|
|
cudnn_benchmark=False,
|
|
mp_cfg=dict(mp_start_method='fork', opencv_num_threads=0),
|
|
dist_cfg=dict(backend='nccl'),
|
|
)
|
|
|
|
vis_backends = [dict(type='LocalVisBackend')]
|
|
visualizer = dict(
|
|
type='DetLocalVisualizer', vis_backends=vis_backends, name='visualizer')
|
|
log_processor = dict(type='LogProcessor', window_size=50, by_epoch=True)
|
|
|
|
log_level = 'INFO'
|
|
load_from = None
|
|
resume = False
|