fast_rcnn_r50_caffe_fpn_1x_coco.py

_base_ = './fast_rcnn_r50_fpn_1x_coco.py'

model = dict(
    backbone=dict(
        norm_cfg=dict(type='BN', requires_grad=False),
        style='caffe',
        init_cfg=dict(
            type='Pretrained',
            checkpoint='open-mmlab://detectron2/resnet50_caffe')))

# use caffe img_norm
img_norm_cfg = dict(
    mean=[103.530, 116.280, 123.675], std=[1.0, 1.0, 1.0], to_rgb=False)
train_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadProposals', num_max_proposals=2000),
    dict(type='LoadAnnotations', with_bbox=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', 'proposals', 'gt_bboxes', 'gt_labels']),
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='LoadProposals', num_max_proposals=None),
    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='ToTensor', keys=['proposals']),
            dict(
                type='ToDataContainer',
                fields=[dict(key='proposals', stack=False)]),
            dict(type='Collect', keys=['img', 'proposals']),
        ])
]
data = dict(
    train=dict(pipeline=train_pipeline),
    val=dict(pipeline=test_pipeline),
    test=dict(pipeline=test_pipeline))