Hang Guo

About the default_init_weights

1

Thanks for your great work! Currently, I try to reproduce your work. However, I meet some problem when I couldn't find the function `default_init_weights` . I would appreciate it if...

Thanks for your great work! Currently, I try to reproduce your work. However, I meet some problem when I couldn't find the function `default_init_weights` . I would appreciate it if...

Thanks for your great work! Currently, I try to reproduce your work. However, I meet some problem when I couldn't find the function `default_init_weights` . I would appreciate it if...

关于训练和测试阶段图像大小不一致的疑问

1

您好，非常感谢您的工作，对我的启发很大。 在运行代码的时候我有一个问题，就是在训练的时候模型的输入是一个patch，但是在测试的时候是整个图像输入。 这样的话，训练和测试的输入图像大小不就不一样了吗？这种大小不一致性会在测试阶段对Moco的Encoder和后面的SR产生影响吗？ 谢谢您！

Hi authors, Thanks for your ownsome work of Dynamic Low-Resolution Distillation for Cost-Efficient End-to-End Text Spotting. I have a question about the implementation about beam search. It seems that the...

add new paper "Exploiting Diffusion Priors for All-in-One Image Restoration" in the subtitle of Image Restoration.

Question about the Bitshift between attn@V

1

hi, authors In eq.16, I noticed you have used the Attn@Vq = 2**(-Attn_q) @ V_q = V_q >> Attn_q. However, to my knowledge, the second equation is not hold, i.e.,...

How to reproduce the results in the paper

4

Hi, sorry to bother you. In the released code of `smaple_lora_int_model.py`, is seems only one image is sampled as a toy example. How to reproduce the results of 500K samples...

Hi, sorry to bother you. In the class `QuantModel_intnlora`, I notice you have used the count number to decide to employ `QuantModule`([this line](https://github.com/ThisisBillhe/EfficientDM/blob/293e212b8c62c356a6da44d6550cd296c87b9f63/quant_scripts/quant_model.py#L94)) or `QuantModule_intnlora` ([this line](https://github.com/ThisisBillhe/EfficientDM/blob/293e212b8c62c356a6da44d6550cd296c87b9f63/quant_scripts/quant_model.py#L96C43-L96C63)). The obtain of...

Hi, Thanks very much for sharing this awesome repo. In the paper, you have given the results on CIFAR-10 with DDIM and ImageNet with LDM-1.4. I only find the code...