htc_x101_64x4d_fpn_dconv_c3-c5_mstrain_400_1400_16x1_20e_coco.py

_base_ = './htc_r50_fpn_1x_coco.py'
model = dict(
    pretrained='open-mmlab://resnext101_64x4d',
    backbone=dict(
        type='ResNeXt',
        depth=101,
        groups=64,
        base_width=4,
        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',
        dcn=dict(type='DCN', deform_groups=1, fallback_on_stride=False),
        stage_with_dcn=(False, True, True, True)))
# dataset settings
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, with_seg=True),
    dict(
        type='Resize',
        img_scale=[(1600, 400), (1600, 1400)],
        multiscale_mode='range',
        keep_ratio=True),
    dict(type='RandomFlip', flip_ratio=0.5),
    dict(type='Normalize', **img_norm_cfg),
    dict(type='Pad', size_divisor=32),
    dict(type='SegRescale', scale_factor=1 / 8),
    dict(type='DefaultFormatBundle'),
    dict(
        type='Collect',
        keys=['img', 'gt_bboxes', 'gt_labels', 'gt_masks', 'gt_semantic_seg']),
]
data = dict(
    samples_per_gpu=1, workers_per_gpu=1, train=dict(pipeline=train_pipeline))
# learning policy
lr_config = dict(step=[16, 19])
total_epochs = 20