open-mmlab/mmrotate

mAP of s2anet under different batchsizes

Open

#59 opened on Mar 3, 2022

View on GitHub
 (11 comments) (0 reactions) (0 assignees)Python (641 forks)github user discovery
help wantedreimplementation

Repository metrics

Stars
 (2,141 stars)
PR merge metrics
 (No merged PRs in 30d)

Description

I train the s2anet (fp16) in batchsize 2 and batchsize 8, and got a 3.7% difference on mAP. It's a little weird.

batchsize lr mAP
8 0.01 70.03
2 0.025 73.74

full config for bs8:

dataset_type = 'DOTADataset'
data_root = '/datasets/Dota_mmrotate/dota/'
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),
    dict(type='RResize', img_scale=(1024, 1024)),
    dict(
        type='RRandomFlip',
        flip_ratio=[0.25, 0.25, 0.25],
        direction=['horizontal', 'vertical', 'diagonal'],
        version='le135'),
    dict(
        type='Normalize',
        mean=[123.675, 116.28, 103.53],
        std=[58.395, 57.12, 57.375],
        to_rgb=True),
    dict(type='Pad', size_divisor=32),
    dict(type='DefaultFormatBundle'),
    dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
]
test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(
        type='MultiScaleFlipAug',
        img_scale=(1024, 1024),
        flip=False,
        transforms=[
            dict(type='RResize'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img'])
        ])
]
data = dict(
    samples_per_gpu=8,
    workers_per_gpu=8,
    train=dict(
        type='DOTADataset',
        ann_file='/datasets/Dota_mmrotate/dota/trainval/annfiles/',
        img_prefix='/datasets/Dota_mmrotate/dota/trainval/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(type='LoadAnnotations', with_bbox=True),
            dict(type='RResize', img_scale=(1024, 1024)),
            dict(
                type='RRandomFlip',
                flip_ratio=[0.25, 0.25, 0.25],
                direction=['horizontal', 'vertical', 'diagonal'],
                version='le135'),
            dict(
                type='Normalize',
                mean=[123.675, 116.28, 103.53],
                std=[58.395, 57.12, 57.375],
                to_rgb=True),
            dict(type='Pad', size_divisor=32),
            dict(type='DefaultFormatBundle'),
            dict(type='Collect', keys=['img', 'gt_bboxes', 'gt_labels'])
        ],
        version='le135'),
    val=dict(
        type='DOTADataset',
        ann_file='/datasets/Dota_mmrotate/dota/trainval/annfiles/',
        img_prefix='/datasets/Dota_mmrotate/dota/trainval/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1024, 1024),
                flip=False,
                transforms=[
                    dict(type='RResize'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='DefaultFormatBundle'),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        version='le135'),
    test=dict(
        type='DOTADataset',
        ann_file='/datasets/Dota_mmrotate/dota/test/images/',
        img_prefix='/datasets/Dota_mmrotate/dota/test/images/',
        pipeline=[
            dict(type='LoadImageFromFile'),
            dict(
                type='MultiScaleFlipAug',
                img_scale=(1024, 1024),
                flip=False,
                transforms=[
                    dict(type='RResize'),
                    dict(
                        type='Normalize',
                        mean=[123.675, 116.28, 103.53],
                        std=[58.395, 57.12, 57.375],
                        to_rgb=True),
                    dict(type='Pad', size_divisor=32),
                    dict(type='DefaultFormatBundle'),
                    dict(type='Collect', keys=['img'])
                ])
        ],
        version='le135'))
evaluation = dict(interval=12, metric='mAP', nproc=1)
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))
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.3333333333333333,
    step=[8, 11])
runner = dict(type='EpochBasedRunner', max_epochs=12)
checkpoint_config = dict(interval=4)
log_config = dict(
    interval=50,
    hooks=[dict(type='TextLoggerHook'),
           dict(type='TensorboardLoggerHook')])
custom_hooks = [dict(type='NumClassCheckHook')]
dist_params = dict(backend='nccl')
log_level = 'INFO'
load_from = None
resume_from = None
workflow = [('train', 1)]
fp16 = dict(loss_scale=dict(init_scale=512))
angle_version = 'le135'
model = dict(
    type='S2ANet',
    backbone=dict(
        type='ResNet',
        depth=50,
        num_stages=4,
        out_indices=(0, 1, 2, 3),
        frozen_stages=1,
        zero_init_residual=False,
        norm_cfg=dict(type='BN', requires_grad=True),
        norm_eval=True,
        style='pytorch',
        init_cfg=dict(type='Pretrained', checkpoint='torchvision://resnet50')),
    neck=dict(
        type='FPN',
        in_channels=[256, 512, 1024, 2048],
        out_channels=256,
        start_level=1,
        add_extra_convs='on_input',
        num_outs=5),
    fam_head=dict(
        type='RotatedRetinaHead',
        num_classes=15,
        in_channels=256,
        stacked_convs=2,
        feat_channels=256,
        assign_by_circumhbbox=None,
        anchor_generator=dict(
            type='RotatedAnchorGenerator',
            scales=[4],
            ratios=[1.0],
            strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='DeltaXYWHAOBBoxCoder',
            angle_range='le135',
            norm_factor=1,
            edge_swap=False,
            proj_xy=True,
            target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
            target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
    align_cfgs=dict(
        type='AlignConv',
        kernel_size=3,
        channels=256,
        featmap_strides=[8, 16, 32, 64, 128]),
    odm_head=dict(
        type='ODMRefineHead',
        num_classes=15,
        in_channels=256,
        stacked_convs=2,
        feat_channels=256,
        assign_by_circumhbbox=None,
        anchor_generator=dict(
            type='PseudoAnchorGenerator', strides=[8, 16, 32, 64, 128]),
        bbox_coder=dict(
            type='DeltaXYWHAOBBoxCoder',
            angle_range='le135',
            norm_factor=1,
            edge_swap=False,
            proj_xy=True,
            target_means=(0.0, 0.0, 0.0, 0.0, 0.0),
            target_stds=(1.0, 1.0, 1.0, 1.0, 1.0)),
        loss_cls=dict(
            type='FocalLoss',
            use_sigmoid=True,
            gamma=2.0,
            alpha=0.25,
            loss_weight=1.0),
        loss_bbox=dict(type='SmoothL1Loss', beta=0.11, loss_weight=1.0)),
    train_cfg=dict(
        fam_cfg=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.5,
                neg_iou_thr=0.4,
                min_pos_iou=0,
                ignore_iof_thr=-1,
                iou_calculator=dict(type='RBboxOverlaps2D')),
            allowed_border=-1,
            pos_weight=-1,
            debug=False),
        odm_cfg=dict(
            assigner=dict(
                type='MaxIoUAssigner',
                pos_iou_thr=0.5,
                neg_iou_thr=0.4,
                min_pos_iou=0,
                ignore_iof_thr=-1,
                iou_calculator=dict(type='RBboxOverlaps2D')),
            allowed_border=-1,
            pos_weight=-1,
            debug=False)),
    test_cfg=dict(
        nms_pre=2000,
        min_bbox_size=0,
        score_thr=0.05,
        nms=dict(iou_thr=0.1),
        max_per_img=2000))
work_dir = './work_dirs/s2a_bs8_fp16'
auto_resume = False
gpu_ids = range(0, 1)

Contributor guide

Research direction
Investigate the effect of batch size on learning rate scaling and batch normalization statistics in S2ANet. Compare the learning rate schedules (lr=0.01 for bs8 vs lr=0.025 for bs2) and check if the linear scaling rule is properly applied. Also verify whether batch normalization layers are frozen or updated during training, and analyze the impact of different batch sizes on the variance of gradient estimates and the stability of training with FP16.
Tech stack
pythonpytorch
Domain
machine learning
Issue type
Bug
DifficultyEstimated implementation difficulty for a new contributor, from 1 for very small changes to 5 for expert-level work.
3
Estimated timeA rough time range for an experienced contributor to investigate, implement, test, and prepare a pull request.
1-2 days
Activity statusHow available the issue appears right now: fresh, active, stale, blocked, or waiting on maintainer input.
Active
ClarityHow clearly the issue explains the expected change, acceptance criteria, and next step.
Mostly clear
Prerequisites
PythonPyTorchObject detection basics
Newbie friendlinessA 1-100 score estimating how approachable this issue is for first-time contributors.
40