hrnet_w32_coco_256x192.py

# Copyright (c) OpenMMLab. All rights reserved.
log_level = 'INFO'
load_from = None
resume_from = None
dist_params = dict(backend='nccl')
workflow = [('train', 1)]
checkpoint_config = dict(interval=10)
evaluation = dict(interval=10, metric='mAP', key_indicator='AP')

optimizer = dict(
    type='Adam',
    lr=5e-4,
)
optimizer_config = dict(grad_clip=None)
# learning policy
lr_config = dict(
    policy='step',
    warmup='linear',
    warmup_iters=500,
    warmup_ratio=0.001,
    step=[170, 200])
total_epochs = 210
log_config = dict(
    interval=50,
    hooks=[
        dict(type='TextLoggerHook'),
        # dict(type='TensorboardLoggerHook')
    ])

channel_cfg = dict(
    num_output_channels=17,
    dataset_joints=17,
    dataset_channel=[
        [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16],
    ],
    inference_channel=[
        0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13, 14, 15, 16
    ])

# model settings
model = dict(
    type='TopDown',
    pretrained='https://download.openmmlab.com/mmpose/'
    'pretrain_models/hrnet_w32-36af842e.pth',
    backbone=dict(
        type='HRNet',
        in_channels=3,
        extra=dict(
            stage1=dict(
                num_modules=1,
                num_branches=1,
                block='BOTTLENECK',
                num_blocks=(4, ),
                num_channels=(64, )),
            stage2=dict(
                num_modules=1,
                num_branches=2,
                block='BASIC',
                num_blocks=(4, 4),
                num_channels=(32, 64)),
            stage3=dict(
                num_modules=4,
                num_branches=3,
                block='BASIC',
                num_blocks=(4, 4, 4),
                num_channels=(32, 64, 128)),
            stage4=dict(
                num_modules=3,
                num_branches=4,
                block='BASIC',
                num_blocks=(4, 4, 4, 4),
                num_channels=(32, 64, 128, 256))),
    ),
    keypoint_head=dict(
        type='TopdownHeatmapSimpleHead',
        in_channels=32,
        out_channels=channel_cfg['num_output_channels'],
        num_deconv_layers=0,
        extra=dict(final_conv_kernel=1, ),
        loss_keypoint=dict(type='JointsMSELoss', use_target_weight=True)),
    train_cfg=dict(),
    test_cfg=dict(
        flip_test=True,
        post_process='default',
        shift_heatmap=True,
        modulate_kernel=11))

data_cfg = dict(
    image_size=[192, 256],
    heatmap_size=[48, 64],
    num_output_channels=channel_cfg['num_output_channels'],
    num_joints=channel_cfg['dataset_joints'],
    dataset_channel=channel_cfg['dataset_channel'],
    inference_channel=channel_cfg['inference_channel'],
    soft_nms=False,
    nms_thr=1.0,
    oks_thr=0.9,
    vis_thr=0.2,
    use_gt_bbox=False,
    det_bbox_thr=0.0,
    bbox_file='data/coco/person_detection_results/'
    'COCO_val2017_detections_AP_H_56_person.json',
)

test_pipeline = [
    dict(type='LoadImageFromFile'),
    dict(type='TopDownGetBboxCenterScale', padding=1.25),
    dict(type='TopDownAffine'),
    dict(type='ToTensor'),
    dict(
        type='NormalizeTensor',
        mean=[0.485, 0.456, 0.406],
        std=[0.229, 0.224, 0.225]),
    dict(
        type='Collect',
        keys=['img'],
        meta_keys=[
            'image_file', 'center', 'scale', 'rotation', 'bbox_score',
            'flip_pairs'
        ]),
]

data_root = 'data/coco'
data = dict(
    samples_per_gpu=64,
    workers_per_gpu=2,
    test_dataloader=dict(samples_per_gpu=32),
    test=dict(
        type='TopDownCocoDataset',
        ann_file=f'{data_root}/annotations/person_keypoints_val2017.json',
        img_prefix=f'{data_root}/val2017/',
        data_cfg=data_cfg,
        pipeline=test_pipeline),
)