MMDetection的学习与应用

---

1. MMDetection

---

1.1 》》》》》》

---

1.2 》》》》》》

---

1.3 》》》》》》

---

1.4 训练基本流程

---

2. MMDetection的安装与配置

---

3. MMCV

MMCV是用于计算机视觉研究的基础python库，并支持以下许多研究项目：

• MMDetection: Detection toolbox and benchmark
• MMDetection3D: General 3D object detection toolbox and benchmark
• MMSegmentation: Semantic segmentation toolbox and benchmark
• MMEditing: Image and video editing toolbox
• MMPose: Pose estimation toolbox and benchmark
• MMAction2: Action understanding toolbox and benchmark
• MMClassification: Image classification toolbox and benchmark

它提供以下功能：

• 通用I/O API接口
• 图像/视频处理
• 图像和标签可视化
• 实用程序（进度条，计时器等）
• 带挂钩机构的PyTorch Runner训练器
• 各种CNN架构
• CUDA通用操作的高质量实现

GitHub传送门
文档传送门

---

---

4. SSD: Single Shot MultiBox Detector

SSD（Single Shot Detection）是一个流行且强大的目标检测网络，网络结构包含了基础网络（Base Network），辅助卷积层（Auxiliary Convolutions）和预测卷积层（Predicton Convolutions）。

---

4.1 配置文件分析

1.ssd300_coco.py

input_size = 300
model = dict(
    type='SingleStageDetector',
    pretrained='open-mmlab://vgg16_caffe',
    backbone=dict(
        type='SSDVGG',
        input_size=300,
        depth=16,
        with_last_pool=False,
        ceil_mode=True,
        out_indices=(3, 4),
        out_feature_indices=(22, 34),
        l2_norm_scale=20),
    neck=None,
    bbox_head=dict(
        type='SSDHead',
        in_channels=(512, 1024, 512, 256, 256, 256),
        num_classes=80,
        anchor_generator=dict(
            type='SSDAnchorGenerator',
            scale_major=False,
            input_size=300,
            basesize_ratio_range=(0.15, 0.9),
            strides=[8, 16, 32, 64, 100, 300],
            ratios=[[2], [2, 3], [2, 3], [2, 3], [2], [2]]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[0.0, 0.0, 0.0, 0.0],
            target_stds=[0.1, 0.1, 0.2, 0.2])))
cudnn_benchmark = True
train_cfg = dict(
    assigner=dict(
        type='MaxIoUAssigner',
        pos_iou_thr=0.5,
        neg_iou_thr=0.5,
        min_pos_iou=0.0,
        ignore_iof_thr=-1,
        gt_max_assign_all=False),
    smoothl1_beta=1.0,
    allowed_border=-1,
    pos_weight=-1,
    neg_pos_ratio=3,
    debug=False)
test_cfg = dict(
    nms=dict(type='nms', iou_threshold=0.45),
    min_bbox_size=0,
    score_thr=0.02,
    max_per_img=200)
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(mean=[123.675, 116.28, 103.53], std=[1, 1, 1], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile', to_float32=True),
    dict(type='LoadAnnotations', with_bbox=True),
    dict(
        type='PhotoMetricDistortion',
        brightness_delta=32,
        contrast_range=(0.5, 1.5),
        saturation_range=(0.5, 1.5),
        hue_delta=18),
    dict(
        type='Expand',
        mean=[123.675, 116.28, 103.53],
        to_rgb=True,
        ratio_range=(1, 4)),
    dict(
        type='MinIoURandomCrop',
        min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
        min_crop_size=0.3),
    dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[1, 1, 1],
        to_rgb=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(300, 300),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=False),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[1, 1, 1],
                to_rgb=True),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=8,
    workers_per_gpu=3,
    train=dict(
        type='RepeatDataset',
        times=5,
        dataset=dict(
            type='CocoDataset',
            ann_file='data/coco/annotations/instances_train2017.json',
            img_prefix='data/coco/train2017/',
            pipeline=[
                dict(type='LoadImageFromFile', to_float32=True),
                dict(type='LoadAnnotations', with_bbox=True),
                dict(
                    type='PhotoMetricDistortion',
                    brightness_delta=32,
                    contrast_range=(0.5, 1.5),
                    saturation_range=(0.5, 1.5),
                    hue_delta=18),
                dict(
                    type='Expand',
                    mean=[123.675, 116.28, 103.53],
                    to_rgb=True,
                    ratio_range=(1, 4)),
                dict(
                    type='MinIoURandomCrop',
                    min_ious=(0.1, 0.3, 0.5, 0.7, 0.9),
                    min_crop_size=0.3),
                dict(type='Resize', img_scale=(300, 300), keep_ratio=False),
                dict(
                    type='Normalize',
                    mean=[123.675, 116.28, 103.53],
                    std=[1, 1, 1],
                    to_rgb=True),
                dict(type='RandomFlip', flip_ratio=0.5),
                dict(type='DefaultFormatBundle'),
                dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
            ])),
    val=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        img_prefix='data/coco/val2017/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(300, 300),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=False),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[1, 1, 1],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]),
    test=dict(
        type='CocoDataset',
        ann_file='data/coco/annotations/instances_val2017.json',
        img_prefix='data/coco/val2017/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(300, 300),
                flip=False,
                transforms=[
                    dict(type='Resize', keep_ratio=False),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[1, 1, 1],
                        to_rgb=True),
                    dict(type='ImageToTensor', keys=['img']),
                    dict(type='Collect', keys=['img'])
                ])
        ]))
evaluation = dict(interval=1, metric='bbox')
optimizer = dict(type='SGD', lr=0.002, momentum=0.9, weight_decay=0.0005)
optimizer_config = dict()
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[16, 22])
total_epochs = 24
checkpoint_config = dict(interval=1)
log_config = dict(interval=50, hooks=[dict(type='TextLoggerHook')])
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
work_dir = './work_dirs/ssd300_coco'
gpu_ids = range(0, 1)

---

4.2 图示分析

---

4.2.1 Backbone

1.VGG网络结构（图片来自WIKI）

---

2.SSD_VGG网络结构

---

4.2.2 组件分析

1.MMdetection架构