EasyCV/configs/detection/fcos/fcos_r50_caffe_1x_coco.py

_base_ = './fcos_r50_torch_1x_coco.py'

model = dict(
    pretrained=
    'https://pai-vision-data-hz.oss-cn-zhangjiakou.aliyuncs.com/pretrained_models/easycv/resnet/detectron/resnet50_caffe.pth',
    backbone=dict(style='caffe'))

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='MMResize', img_scale=(1333, 800), keep_ratio=True),
    dict(type='MMRandomFlip', flip_ratio=0.5),
    dict(type='MMNormalize', **img_norm_cfg),
    dict(type='MMPad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(
        type='Collect',
        keys=['img', 'gt_bboxes', 'gt_labels'],
        meta_keys=('filename', 'ori_filename', 'ori_shape', 'ori_img_shape',
                   'img_shape', 'pad_shape', 'scale_factor', 'flip',
                   'flip_direction', 'img_norm_cfg'))
]
test_pipeline = [
    dict(
        type='MMMultiScaleFlipAug',
        img_scale=(1333, 800),
        flip=False,
        transforms=[
            dict(type='MMResize', keep_ratio=True),
            dict(type='MMRandomFlip'),
            dict(type='MMNormalize', **img_norm_cfg),
            dict(type='MMPad', size_divisor=32),
            dict(type='ImageToTensor', keys=['img']),
            dict(
                type='Collect',
                keys=['img'],
                meta_keys=('filename', 'ori_filename', 'ori_shape',
                           'ori_img_shape', 'img_shape', 'pad_shape',
                           'scale_factor', 'flip', 'flip_direction',
                           'img_norm_cfg'))
        ])
]

train_dataset = dict(pipeline=train_pipeline)
val_dataset = dict(pipeline=test_pipeline)

data = dict(
    imgs_per_gpu=2, workers_per_gpu=2, train=train_dataset, val=val_dataset)