start
start
【队名】：小鸡毒蘑菇 【序号】：4 【论文】：[MicroNet: Improving Image Recognition with Extremely Low FLOPs](https://openaccess.thecvf.com/content/ICCV2021/html/Li_MicroNet_Improving_Image_Recognition_With_Extremely_Low_FLOPs_ICCV_2021_paper.html) 【状态】：报名 【repo链接】：https://github.com/huaibovip/paddle_MicroNet
您好，希望您那边提供一下已经训练好的模型，非常感谢，我的邮箱是[email protected]
For example, to install ros-humble directly on Debian 11.7 using apt instead of compiling from source
These issues might be better addressed if developers consider offering ROS as conda packages
> 您好，您是多卡还是单卡训练的呢？paddle的版本是？ PaddlePaddle 2.6.1 Centos 7 Python 3.10.14 cuda-version 11.7 h67201e3_3 conda-forge cudatoolkit 11.7.1 h4bc3d14_13 conda-forge cudnn 8.4.1.50 hed8a83a_0 conda-forge 多卡训练，降级paddlepaddle版到2.5.2后解决该问题
Change `RepVGGDW` to the following implementation ```python class RepVGGDW(torch.nn.Module): def __init__(self, ed) -> None: super().__init__() self.conv = Conv2d_BN(ed, ed, 3, 1, 1, groups=ed) self.conv1 = torch.nn.Conv2d(ed, ed, 1, 1, 0,...