本文将快速引导使用 MMDetection ，记录了实践中需注意的一些问题。

环境准备

基础环境

开发环境

下载并安装 Anaconda ,之后于 Terminal 执行：

# 创建 Python 虚拟环境

conda create -n open-mmlab python=3.7 -y

conda activate open-mmlab

# 安装 PyTorch with CUDA

conda install pytorch==1.6.0 torchvision==0.7.0 cudatoolkit=10.2 -c pytorch -y

# 安装 MMCV

pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.6.0/index.html

# 安装 MMDetection

git clone https://github.com/open-mmlab/mmdetection.git

cd mmdetection

pip install -r requirements/build.txt

pip install -v -e .

pytorch==1.7.0 时多卡训练会发生问题，需参考此 Issue。命令参考：

conda install pytorch==1.7.0 torchvision==0.8.1 cudatoolkit=10.2 -c pytorch -y

pip install mmcv-full -f https://download.openmmlab.com/mmcv/dist/cu102/torch1.7.0/index.html

更多安装方式，可见官方文档：

现有模型进行推断

Faster RCNN

以 R-50-FPN 为例，下载其 model 文件到 mmdetection/checkpoints/。之后，进行推断，

conda activate open-mmlab

cd mmdetection/

python demo/image_demo.py \

demo/demo.jpg \

configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \

checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth

现有模型进行测试

准备数据集

下载 COCO 数据集，如下放进 mmdetection/data/coco/ 目录，

mmdetection

├── data

│   ├── coco

│   │   ├── annotations

│   │   ├── train2017

│   │   ├── val2017

│   │   ├── test2017

测试现有模型

cd mmdetection/

# single-gpu testing

python tools/test.py \

configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \

checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \

--out results.pkl \

--eval bbox \

--show

# multi-gpu testing

bash tools/dist_test.sh \

configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \

checkpoints/faster_rcnn_r50_fpn_1x_coco_20200130-047c8118.pth \

2 \

--out results.pkl \

--eval bbox

效果如下，

结果如下，

loading annotations into memory...

Done (t=0.33s)

creating index...

index created!

[>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>>] 5000/5000, 15.3 task/s, elapsed: 328s, ETA:     0s

writing results to results.pkl

Evaluating bbox...

Loading and preparing results...

DONE (t=0.89s)

creating index...

index created!

Running per image evaluation...

Evaluate annotation type *bbox*

DONE (t=26.17s).

Accumulating evaluation results...

DONE (t=4.10s).

Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.374

Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=1000 ] = 0.581

Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=1000 ] = 0.404

Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.212

Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.410

Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.481

Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.517

Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=300 ] = 0.517

Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=1000 ] = 0.517

Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=1000 ] = 0.326

Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=1000 ] = 0.557

Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=1000 ] = 0.648

OrderedDict([('bbox_mAP', 0.374), ('bbox_mAP_50', 0.581), ('bbox_mAP_75', 0.404), ('bbox_mAP_s', 0.212), ('bbox_mAP_m', 0.41), ('bbox_mAP_l', 0.481), ('bbox_mAP_copypaste', '0.374 0.581 0.404 0.212 0.410 0.481')])

标准数据集训练模型

准备数据集

同前一节的 COCO 数据集。

准备配置文件

配置文件为 configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py。

需要依照自己的 GPU 情况，修改 lr 学习速率参数，说明如下：

  • lr=0.005 for 2 GPUs * 2 imgs/gpu
  • lr=0.01 for 4 GPUs * 2 imgs/gpu
  • lr=0.02 for 8 GPUs and 2 img/gpu (batch size = 8*2 = 16), DEFAULT
  • lr=0.08 for 16 GPUs * 4 imgs/gpu
_base_ = [

    '../_base_/models/faster_rcnn_r50_fpn.py',

    '../_base_/datasets/coco_detection.py',

    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'

]

# optimizer

optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001)

训练模型

cd mmdetection/

# single-gpu training

python tools/train.py \

configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \

--work-dir _train

# multi-gpu training

bash ./tools/dist_train.sh \

configs/faster_rcnn/faster_rcnn_r50_fpn_1x_coco.py \

2 \

--work-dir _train

自定义数据集训练模型

自定义数据集

这里从 Pascal VOC 数据集拿出 cat 作为自定义数据集来演示，

conda activate open-mmlab

# Dataset Management Framework (Datumaro)

pip install 'git+https://github.com/openvinotoolkit/datumaro'

# pip install tensorflow

datum convert --input-format voc --input-path ~/datasets/VOC2012 \

--output-format coco --output-dir ~/datasets/coco_voc2012_cat \

--filter '/item[annotation/label="cat"]'

数据集需要是 COCO 格式，以上直接用 datum 从 VOC 拿出 cat 并转为了 COCO 格式。

准备配置文件

添加 configs/voc_cat/faster_rcnn_r50_fpn_1x_voc_cat.py 配置文件，内容如下：

# The new config inherits a base config to highlight the necessary modification

_base_ = [

    '../_base_/models/faster_rcnn_r50_fpn.py',

    '../_base_/datasets/coco_detection.py',

    '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'

]

# We also need to change the num_classes in head to match the dataset's annotation

model = dict(

    roi_head=dict(

        bbox_head=dict(num_classes=1)))

# Modify dataset related settings

dataset_type = 'COCODataset'

classes = ('cat',)

data_root = '/home/john/datasets/'

data = dict(

    train=dict(

        img_prefix=data_root + 'VOC2012/JPEGImages/',

        classes=classes,

        ann_file=data_root + 'coco_voc2012_cat/annotations/instances_train.json'),

    val=dict(

        img_prefix=data_root + 'VOC2012/JPEGImages/',

        classes=classes,

        ann_file=data_root + 'coco_voc2012_cat/annotations/instances_val.json'),

    test=dict(

        img_prefix=data_root + 'VOC2012/JPEGImages/',

        classes=classes,

        ann_file=data_root + 'coco_voc2012_cat/annotations/instances_val.json'))

evaluation = dict(interval=100)

# Modify schedule related settings

optimizer = dict(type='SGD', lr=0.005, momentum=0.9, weight_decay=0.0001)

total_epochs = 10000

# Modify runtime related settings

checkpoint_config = dict(interval=10)

# We can use the pre-trained model to obtain higher performance

# load_from = 'checkpoints/*.pth'