search

open-mmlab / mmocr

OpenMMLab Text Detection, Recognition and Understanding Toolbox
https://mmocr.readthedocs.io/en/dev-1.x/
Apache License 2.0
4.34k stars 749 forks source link

[Docs] Are the two convolutional neural network settings used in the ASTER model the same? #1921

Open OuXiao514 opened 1 year ago

OuXiao514 commented 1 year ago

Branch

master branch https://mmocr.readthedocs.io/en/latest/

📚 The doc issue

Are the two convolutional neural network settings used in the ASTER model the same? backbone=dict( type='ResNet', in_channels=3, stem_channels=[32], block_cfgs=dict(type='BasicBlock', use_conv1x1='True'), arch_layers=[3, 4, 6, 6, 3], arch_channels=[32, 64, 128, 256, 512], strides=[(2, 2), (2, 2), (2, 1), (2, 1), (2, 1)], init_cfg=[ dict(type='Kaiming', layer='Conv2d'), dict(type='Constant', val=1, layer='BatchNorm2d'), ])

Suggest a potential alternative/fix

Are the two convolutional neural network settings used in the ASTER model the same?

Mountchicken commented 1 year ago

Hi @OuXiao514 The configuration of ResNet is the same as in the original paper.