haooxia

如下配置可用： pytorch=1.6.0 git clone -b pytorch_1.0.0 https://github.com/chengdazhi/Deformable-Convolution-V2-PyTorch.git

> Hi, I encountered some problems when I train the unconditional LDM. I trained the LDM with 2 RTX 3090. When should I use` --scale_lr True` to scale the learning...

> This link is invalid, can you provide it again. > https://www.aige.co.uk/resources.asp?id=1

> Set `--scale_lr=False`, then the learning rate will not be modified. Thanks for the reply, the `base_learning_rate` given by the repository is [4.5e-6](https://github.com/CompVis/latent-diffusion/blob/a506df5756472e2ebaf9078affdde2c4f1502cd4/configs/autoencoder/autoencoder_kl_64x64x3.yaml#L2C23-L2C29), so what value should I shrink to...

+1

Please do you have a solution to this issue now?

> > Please do you have a solution to this issue now? > > 我的建议是直接下载英伟达官方的FlowNet2.0预训练模型 感谢回复！

> Hi @haoxia1, > > Apologies for the delayed response. > > Regarding Question 1, I believe you're right. > > As for Question 2, you may utilize other language...