一，configs/_base_

1.default_runtime.py

2.schedule_1x.py

二，mmdet

1.datasets/coco.py/CocoDataset

    METAINFO = {'classes':('milk', 'red', 'spring', 'fanta', 'sprite', 'pepsi', 'king', 'ice', 'cola', 'scream'  ),# palette is a list of color tuples, which is used for visualization.'palette':[(220, 20, 60), (119, 11, 32), (0, 0, 142), (0, 0, 230), (106, 0, 228),(0, 60, 100), (0, 80, 100), (0, 0, 70), (0, 0, 192), (250, 170, 30)]}

2.evaluation/functional/class_names.py/coco_classes

    return ['milk', 'red', 'spring', 'fanta', 'sprite', 'pepsi', 'king', 'ice', 'cola', 'scream']

三，configs

1.yolov3_mobilenetv2_8xb24-ms-416-300e_coco.py

num_classes

data_root

ann_file

data_prefix

max_epochs

重新安裝：

pip install -v -e .

開始訓練：

python tools/train.py configs\yolo\yolov3_mobilenetv2_8xb24-ms-416-300e_coco.py

_base_ = ['../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py']
# 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=10, 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')),# training and testing settingstrain_cfg=dict(assigner=dict(type='GridAssigner',pos_iou_thr=0.5,neg_iou_thr=0.5,min_pos_iou=0)),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/drink/'# Example to use different file client
# Method 1: simply set the data root and let the file I/O module
# automatically infer from prefix (not support LMDB and Memcache yet)# data_root = 's3://openmmlab/datasets/detection/coco/'# Method 2: Use `backend_args`, `file_client_args` in versions before 3.0.0rc6
# backend_args = dict(
#     backend='petrel',
#     path_mapping=dict({
#         './data/': 's3://openmmlab/datasets/detection/',
#         'data/': 's3://openmmlab/datasets/detection/'
#     }))
backend_args = Nonetrain_pipeline = [dict(type='LoadImageFromFile', backend_args=backend_args),dict(type='LoadAnnotations', with_bbox=True),dict(type='Expand',mean=data_preprocessor['mean'],to_rgb=data_preprocessor['bgr_to_rgb'],ratio_range=(1, 2)),dict(type='MinIoURandomCrop',min_ious=(0.4, 0.5, 0.6, 0.7, 0.8, 0.9),min_crop_size=0.3),dict(type='RandomResize', scale=[(320, 320), (416, 416)], keep_ratio=True),dict(type='RandomFlip', prob=0.5),dict(type='PhotoMetricDistortion'),dict(type='PackDetInputs')
]
test_pipeline = [dict(type='LoadImageFromFile', backend_args=backend_args),dict(type='Resize', scale=(416, 416), keep_ratio=True),dict(type='LoadAnnotations', with_bbox=True),dict(type='PackDetInputs',meta_keys=('img_id', 'img_path', 'ori_shape', 'img_shape','scale_factor'))
]train_dataloader = dict(batch_size=24,num_workers=4,persistent_workers=True,sampler=dict(type='DefaultSampler', shuffle=True),batch_sampler=dict(type='AspectRatioBatchSampler'),dataset=dict(type='RepeatDataset',  # use RepeatDataset to speed up trainingtimes=10,dataset=dict(type=dataset_type,data_root=data_root,ann_file='annotations/annotations_all.json',data_prefix=dict(img='images/'),filter_cfg=dict(filter_empty_gt=True, min_size=32),pipeline=train_pipeline,backend_args=backend_args)))
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/annotations_all.json',data_prefix=dict(img='images/'),test_mode=True,pipeline=test_pipeline,backend_args=backend_args))
test_dataloader = val_dataloaderval_evaluator = dict(type='CocoMetric',ann_file=data_root + 'annotations/annotations_all.json',metric='bbox',backend_args=backend_args)
test_evaluator = val_evaluatortrain_cfg = dict(max_epochs=30)# optimizer
optim_wrapper = dict(type='OptimWrapper',optimizer=dict(type='SGD', lr=0.003, momentum=0.9, weight_decay=0.0005),clip_grad=dict(max_norm=35, norm_type=2))# learning policy
param_scheduler = [dict(type='LinearLR',start_factor=0.0001,by_epoch=False,begin=0,end=4000),dict(type='MultiStepLR', by_epoch=True, milestones=[24, 28], gamma=0.1)
]find_unused_parameters = True# NOTE: `auto_scale_lr` is for automatically scaling LR,
# USER SHOULD NOT CHANGE ITS VALUES.
# base_batch_size = (8 GPUs) x (24 samples per GPU)
auto_scale_lr = dict(base_batch_size=24)# my settings
load_from = './checkpoints/yolov3_mobilenetv2_mstrain-416_300e_coco_20210718_010823-f68a07b3.pth'
work_dir = './work_dirs/yolov3_mobilenetv2_drink'