MMLAB-AI训练营笔记——Day5

今日笔记主要是关于如何使用mmdetection完成第二次作业的

1. 安装ffmpeg

• 下载解压

wget http://www.ffmpeg.org/releases/ffmpeg-3.1.tar.gz
tar -zxvf ffmpeg-3.1.tar.gz

• 进入解压后目录,输入如下命令/usr/local/ffmpeg为自己指定的安装目录

cd ffmpeg-3.1
./configure --prefix=/usr/local/ffmpeg
make && make install

• 配置变量

vi /etc/profile
在最后PATH添加环境变量：
export PATH=$PATH:/usr/local/ffmpeg/bin
保存退出
查看是否生效
source /ect/profile 设置生效

• 查看版本

ffmpeg -version 查看版本

2. 将数据集转为coco格式

原来的数据集是via格式的，这里使用脚本将其转为coco格式

import os.path as osp
import mmcv

def convert_VIA_to_coco(ann_file, out_file, image_prefix):
    data_infos = mmcv.load(ann_file)

    annotations = []
    images = []
    obj_count = 0
    for idx, v in enumerate(mmcv.track_iter_progress(data_infos.values())):
        filename = v['filename']
        img_path = osp.join(image_prefix, filename)
        height, width = mmcv.imread(img_path).shape[:2]

        images.append(dict(
            id=idx,
            file_name=filename,
            height=height,
            width=width))

        bboxes = []
        labels = []
        masks = []

#多个类别标注，循环获取每一个一个类别
        for n in range(len(v['regions'])):
            obj = v['regions'][str(n)]
            obj = obj['shape_attributes']
            px = obj['all_points_x']
            py = obj['all_points_y']
            poly = [(x + 0.5, y + 0.5) for x, y in zip(px, py)]
            poly = [p for x in poly for p in x]

            x_min, y_min, x_max, y_max = (
                min(px), min(py), max(px), max(py))

            data_anno = dict(
                image_id=idx,
                id=obj_count,
                category_id=n,
                bbox=[x_min, y_min, x_max - x_min, y_max - y_min],
                area=(x_max - x_min) * (y_max - y_min),
                segmentation=[poly],
                iscrowd=0)
        annotations.append(data_anno)
        obj_count += 1


    coco_format_json = dict(
        images=images,
        annotations=annotations,
        categories=[{'id': 0, 'name': 'fish'} , {'id': 1, 'name': 'face'}])#添加自己训练数据的类别
    mmcv.dump(coco_format_json, out_file)

convert_VIA_to_coco("./data/balloon/train/via_region_data.json", "./data/balloon/train/annotation_coco.json", "./data/balloon/train")
convert_VIA_to_coco("./data/balloon/val/via_region_data.json", "./data/balloon/val/annotation_coco.json", "./data/balloon/val")

3. 修改配置文件

主要针对数据集路径以及模型类别进行修改

# model settings
model = dict(
    type='MaskRCNN',
    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,
        num_outs=5),
    rpn_head=dict(
        type='RPNHead',
        in_channels=256,
        feat_channels=256,
        anchor_generator=dict(
            type='AnchorGenerator',
            scales=[8],
            ratios=[0.5, 1.0, 2.0],
            strides=[4, 8, 16, 32, 64]),
        bbox_coder=dict(
            type='DeltaXYWHBBoxCoder',
            target_means=[.0, .0, .0, .0],
            target_stds=[1.0, 1.0, 1.0, 1.0]),
        loss_cls=dict(
            type='CrossEntropyLoss', use_sigmoid=True, loss_weight=1.0),
        loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
    roi_head=dict(
        type='StandardRoIHead',
        bbox_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=7, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        bbox_head=dict(
            type='Shared2FCBBoxHead',
            in_channels=256,
            fc_out_channels=1024,
            roi_feat_size=7,
            # num_classes=80,
            num_classes=1,
            bbox_coder=dict(
                type='DeltaXYWHBBoxCoder',
                target_means=[0., 0., 0., 0.],
                target_stds=[0.1, 0.1, 0.2, 0.2]),
            reg_class_agnostic=False,
            loss_cls=dict(
                type='CrossEntropyLoss', use_sigmoid=False, loss_weight=1.0),
            loss_bbox=dict(type='L1Loss', loss_weight=1.0)),
        mask_roi_extractor=dict(
            type='SingleRoIExtractor',
            roi_layer=dict(type='RoIAlign', output_size=14, sampling_ratio=0),
            out_channels=256,
            featmap_strides=[4, 8, 16, 32]),
        mask_head=dict(
            type='FCNMaskHead',
            num_convs=4,
            in_channels=256,
            conv_out_channels=256,
            num_classes=1,
            loss_mask=dict(
                type='CrossEntropyLoss', use_mask=True, loss_weight=1.0))),
    # model training and testing settings
    train_cfg=dict(
        rpn=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.7,
                neg_iou_thr=0.3,
                min_pos_iou=0.3,
                match_low_quality=True,
                ignore_iof_thr=-1),
            sampler=dict(
                type='RandomSampler',
                num=256,
                pos_fraction=0.5,
                neg_pos_ub=-1,
                add_gt_as_proposals=False),
            allowed_border=-1,
            pos_weight=-1,
            debug=False),
        rpn_proposal=dict(
            nms_pre=2000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.5,
                neg_iou_thr=0.5,
                min_pos_iou=0.5,
                match_low_quality=True,
                ignore_iof_thr=-1),
            sampler=dict(
                type='RandomSampler',
                num=512,
                pos_fraction=0.25,
                neg_pos_ub=-1,
                add_gt_as_proposals=True),
            mask_size=28,
            pos_weight=-1,
            debug=False)),
    test_cfg=dict(
        rpn=dict(
            nms_pre=1000,
            max_per_img=1000,
            nms=dict(type='nms', iou_threshold=0.7),
            min_bbox_size=0),
        rcnn=dict(
            score_thr=0.05,
            nms=dict(type='nms', iou_threshold=0.5),
            max_per_img=100,
            mask_thr_binary=0.5)))

# dataset settings
dataset_type = 'CocoDataset'
data_root = './data/balloon'
CLASSES = ('balloon', )
img_norm_cfg = dict(
    mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
    dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks']),
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='Resize', keep_ratio=True),
            dict(type='RandomFlip'),
            dict(type='Normalize', **img_norm_cfg),
            dict(type='Pad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(type='Collect', keys=['img']),
        ])
]
data = dict(
    samples_per_gpu=2,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + '/train/annotation_coco.json',
        img_prefix=data_root + '/train/',
        pipeline=train_pipeline),
    val=dict(
        type=dataset_type,
        ann_file=data_root + '/val/annotation_coco.json',
        img_prefix=data_root + '/val/',
        pipeline=test_pipeline),
    test=dict(
        type=dataset_type,
        ann_file=data_root + '/val/annotation_coco.json',
        img_prefix=data_root + '/val/',
        pipeline=test_pipeline))
evaluation = dict(metric=['bbox', 'segm'])

# optimizer
optimizer = dict(type='SGD', lr=0.001, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.0001,
    step=[16, 22])
runner = dict(type='EpochBasedRunner', max_epochs=10)

checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=25,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
custom_hooks = [dict(type='NumClassCheckHook')]

dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = "./mask_rcnn_r50_fpn_mstrain-poly_3x_coco_20210524_201154-21b550bb.pth"
resume_from = None
workflow = [('train', 1)]

# disable opencv multithreading to avoid system being overloaded
opencv_num_threads = 0
# set multi-process start method as `fork` to speed up the training
mp_start_method = 'fork'

# Default setting for scaling LR automatically
#   - `enable` means enable scaling LR automatically
#       or not by default.
#   - `base_batch_size` = (8 GPUs) x (2 samples per GPU).
auto_scale_lr = dict(enable=False, base_batch_size=16)