fast_rcnn_r50_caffe_c4_1x.py

# model settings
norm_cfg = dict(type='BN', requires_grad=False)
model = dict(
    type='FastRCNN',
    pretrained='open-mmlab://resnet50_caffe',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=3,
        strides=(1, 2, 2),
        dilations=(1, 1, 1),
        out_indices=(2, ),
        frozen_stages=1,
        norm_cfg=norm_cfg,
        norm_eval=True,
        style='caffe'),
    shared_head=dict(
        type='ResLayer',
        depth=50,
        stage=3,
        stride=2,
        dilation=1,
        style='caffe',
        norm_cfg=norm_cfg,
        norm_eval=True),
    bbox_roi_extractor=dict(
        type='SingleRoIExtractor',
        roi_layer=dict(type='RoIAlign', out_size=14, sample_num=2),
        out_channels=1024,
        featmap_strides=[16]),
    bbox_head=dict(
        type='BBoxHead',
        with_avg_pool=True,
        roi_feat_size=7,
        in_channels=2048,
        num_classes=81,
        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='SmoothL1Loss', beta=1.0, loss_weight=1.0)))
# model training and testing settings
train_cfg = dict(
    rcnn=dict(
        assigner=dict(
            type='MaxIoUAssigner',
            pos_iou_thr=0.5,
            neg_iou_thr=0.5,
            min_pos_iou=0.5,
            ignore_iof_thr=-1),
        sampler=dict(
            type='RandomSampler',
            num=512,
            pos_fraction=0.25,
            neg_pos_ub=-1,
            add_gt_as_proposals=True),
        pos_weight=-1,
        debug=False))
test_cfg = dict(
    rcnn=dict(
        score_thr=0.05, nms=dict(type='nms', iou_thr=0.5), max_per_img=100))
# dataset settings
dataset_type = 'CocoDataset'
data_root = 'data/coco/'
img_norm_cfg = dict(
    mean=[102.9801, 115.9465, 122.7717], std=[1.0, 1.0, 1.0], to_rgb=False)
data = dict(
    imgs_per_gpu=1,
    workers_per_gpu=2,
    train=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_train2017.json',
        img_prefix=data_root + 'train2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        proposal_file=data_root + 'proposals/rpn_r50_c4_1x_train2017.pkl',
        flip_ratio=0.5,
        with_mask=False,
        with_crowd=True,
        with_label=True),
    val=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
        flip_ratio=0,
        with_mask=False,
        with_crowd=True,
        with_label=True),
    test=dict(
        type=dataset_type,
        ann_file=data_root + 'annotations/instances_val2017.json',
        img_prefix=data_root + 'val2017/',
        img_scale=(1333, 800),
        img_norm_cfg=img_norm_cfg,
        size_divisor=32,
        proposal_file=data_root + 'proposals/rpn_r50_c4_1x_val2017.pkl',
        flip_ratio=0,
        with_mask=False,
        with_label=False,
        test_mode=True))
# optimizer
optimizer = dict(type='SGD', lr=0.01, momentum=0.9, weight_decay=0.0001)
optimizer_config = dict(grad_clip=dict(max_norm=35, norm_type=2))
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=1.0 / 3,
    step=[8, 11])
checkpoint_config = dict(interval=1)
# yapf:disable
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])
# yapf:enable
# runtime settings
total_epochs = 12
dist_params = dict(backend='nccl')
log_level = 'INFO'
work_dir = './work_dirs/fast_rcnn_r50_caffe_c4_1x'
load_from = None
resume_from = None
workflow = [('train', 1)]