mmdetection에서 albu 라이브러리 적용하는 방법

retinanet_18 기준입니다.
저는 noodle을 detection하는 프로젝트를 해서 파일명을 noodle관련으로 바꿔줬습니다. 각자의 프로젝트에 맞게 이름 수정하면 될 것 같습니다!

1. mmdetection > configs > base > datasets > noodles_detection.py을 생성한 후 원하는 albumentation을 구성한다.

   • mmdetection/configs/base/datasets/coco_detection.py 복붙해서 albu 구성하기!
   • mmdetection/configs/albu_example 에 albu 예시가 있음
   • 위의 예시는 mask_rcnn 기준이므로 train_pipeline에서 mask 관련된 것은 지워줬음

   # dataset settings
   dataset_type = 'CocoDataset'
   data_root = 'data/coco/'
   img_norm_cfg = dict(
       mean=[123.675, 116.28, 103.53], std=[58.395, 57.12, 57.375], to_rgb=True)
   albu_train_transforms = [
       dict(
           type='ShiftScaleRotate',
           shift_limit=0.0625,
           scale_limit=0.0,
           rotate_limit=0,
           interpolation=1,
           p=0.5),
       dict(
           type='RandomBrightnessContrast',
           brightness_limit=[0.1, 0.3],
           contrast_limit=[0.1, 0.3],
           p=0.2),
       dict(
           type='OneOf',
           transforms=[
               dict(
                   type='RGBShift',
                   r_shift_limit=10,
                   g_shift_limit=10,
                   b_shift_limit=10,
                   p=1.0),
               dict(
                   type='HueSaturationValue',
                   hue_shift_limit=20,
                   sat_shift_limit=30,
                   val_shift_limit=20,
                   p=1.0)
           ],
           p=0.1),
       dict(type='JpegCompression', quality_lower=85, quality_upper=95, p=0.2),
       dict(type='ChannelShuffle', p=0.1),
       dict(
           type='OneOf',
           transforms=[
               dict(type='Blur', blur_limit=3, p=1.0),
               dict(type='MedianBlur', blur_limit=3, p=1.0)
           ],
           p=0.1),
   ]
   
   train_pipeline = [
       dict(type='LoadImageFromFile'),
       #dict(type='LoadAnnotations', with_bbox=True, with_mask=True),
       dict(type='LoadAnnotations', with_bbox=True),
       dict(type='Resize', img_scale=(1333, 800), keep_ratio=True),
       dict(type='Pad', size_divisor=32),
       dict(
           type='Albu',
           transforms=albu_train_transforms,
           bbox_params=dict(
               type='BboxParams',
               format='pascal_voc',
               label_fields=['gt_labels'],
               min_visibility=0.0,
               filter_lost_elements=True),
           keymap={
               'img': 'image',
              # 'gt_masks': 'masks',
               'gt_bboxes': 'bboxes'
           },
           update_pad_shape=False,
           skip_img_without_anno=True),
       dict(type='Normalize', **img_norm_cfg),
       dict(type='DefaultFormatBundle'),
       dict(
           type='Collect',
           #keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks'],
           keys=['img', 'gt_bboxes', 'gt_labels'],
           meta_keys=('filename', 'ori_shape', 'img_shape', 'img_norm_cfg',
                      'pad_shape', 'scale_factor'))
   ]
   
   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 + 'annotations/instances_train2017.json',
           img_prefix=data_root + 'train2017/',
           pipeline=train_pipeline),
       val=dict(
           type=dataset_type,
           ann_file=data_root + 'annotations/instances_val2017.json',
           img_prefix=data_root + 'val2017/',
           pipeline=test_pipeline),
       test=dict(
           type=dataset_type,
           ann_file=data_root + 'annotations/instances_val2017.json',
           img_prefix=data_root + 'val2017/',
           pipeline=test_pipeline))
   evaluation = dict(interval=1, metric='bbox')

2. mmdetection/configs/retinanet/retinanet_r18_fpn_1x_noodles.py 을 생성한다.

   • mmdetection/configs/retinanet/retinanet_r18_fpn_1x_coco.py 를 복붙해서 넣기
   • '../base/datasets/cocodetection.py' 를 '../_base/datasets/noodles_detection.py' 로 바꿔주기

     _base_ = [
         '../_base_/models/retinanet_r50_fpn.py',
         '../_base_/datasets/noodles_detection.py',
         '../_base_/schedules/schedule_1x.py', '../_base_/default_runtime.py'
     ]
     
     # optimizer
     model = dict(
         backbone=dict(
             depth=18,
             init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet18')),
         neck=dict(in_channels=[64, 128, 256, 512]))
     optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
     
     # NOTE: `auto_scale_lr` is for automatically scaling LR,
     # USER SHOULD NOT CHANGE ITS VALUES.
     # base_batch_size = (8 GPUs) x (2 samples per GPU)
     auto_scale_lr = dict(base_batch_size=16)

만난 오류!

⛔ AttributeError: module 'albumentations' has no attribute 'BboxParams'

해결방법

!pip install -U albumentations
    

설치하고 cv 버전도 맞춰줘야합니다.

!pip uninstall opencv-python-headless
!pip install opencv-python-headless==4.1.2.30