search

OpenGVLab / InternImage

[CVPR 2023 Highlight] InternImage: Exploring Large-Scale Vision Foundation Models with Deformable Convolutions
https://arxiv.org/abs/2211.05778
MIT License
2.5k stars 232 forks source link

TypeError: unsupported operand type(s) for -: 'tuple' and 'int' #299

Open zhouxuedaasd opened 3 months ago

zhouxuedaasd commented 3 months ago

nn.Conv2d( channels, channels, kernel_size=dw_kernel_size, stride=1, padding=(dw_kernel_size - 1) // 2, groups=channels) dw_kernel_size 是元组无法进行计算