search

HRNet / Lite-HRNet

This is an official pytorch implementation of Lite-HRNet: A Lightweight High-Resolution Network.
Apache License 2.0
833 stars 126 forks source link

Where is "Topdown" type? #17

Closed ronghui19 closed 3 years ago

ronghui19 commented 3 years ago

`model = dict( type='Topdown',

num_stages=3,

pretrained=None,
backbone=dict(
    type='LiteHRNet',
    in_channels=3,
    extra=dict(
        stem=dict(
            stem_channels=32,
            out_channels=32,
            expand_ratio=1),
        num_stages=3,
        stages_spec=dict(
            num_modules=(3, 8, 3),
            num_branches=(2, 3, 4),
            num_blocks=(2, 2, 2),
            module_type=('LITE', 'LITE', 'LITE'),
            with_fuse=(True, True, True),
            reduce_ratios=(8, 8, 8),
            num_channels=(
                (40, 80),
                (40, 80, 160),
                (40, 80, 160, 320),
            )),
        with_head=False,
    )),`

any ideas about how to find out "Topdown"?

yu-changqian commented 3 years ago

Hello, this project is based on mmpose. Therefore, the Topdown pose detector is defined in here.