SeeSR

SeeSR copied to clipboard

DAPE微调细节和收敛问题

1

我按照作者实验设置，将DIV2K，Flickr2K，FFHQ1w张，OST，共计2.3w张做成配对图片后放到DAPE中微调，设置也按照dape.yaml的配置做的，然后模型收敛不了（l_logits在0.5左右），放在推理部分也不能产生有效标签信息（全是null）。想问问大家是怎么解决收敛问题的？

aulaywang

复现训练过程中，训练中间的checkpoint测试发现效果并不好，这正常吗？

13

beyondbatman-master

论文中效果对比有什么意义呢？这么大的模型。。

4

gjd2017

compared to PASD

1

为了方便，直接用中文了～ seesr相比PASD的改进是不是主要是在representation branch上（针对低质量图片做了训练），sd和controlnet部分差不多？ 另外就是seesr没有像PASD那样在controlnet的输入上做显式地增强？

Feynman1999

训练代码 在加载SD的Unet的权重时会报错

10

  我发现 UNet2DConditionModel的state_dict().keys() 和 SD的Unet的state_dict.keys()不匹配导致报错

ZifanCui

raise EnvironmentError( OSError: Can't load tokenizer for 'bert-base-uncased'

6

SeeSR-main/test_seesr.py", line 125, in load_tag_model model = ram(pretrained='preset/models/ram_swin_large_14m.pth', SeeSR-main/ram/models/ram_lora.py", line 319, in ram model = RAMLora(**kwargs) SeeSR-main/ram/models/ram_lora.py", line 107, in __init__ self.tokenizer = init_tokenizer() SeeSR-main/ram/models/utils.py", line 131, in init_tokenizer tokenizer...

windcr

关于sd-turbo训练问题

2

Hi，想请教一下基于sd-turbo的训练具体是怎么做的呢？我尝试过仅把sd2-base换成turbo，发现训出来的结果相比baseline要更模糊一些

Yu-xi-99

FID problem

1

Hello, thank you for sharing the code of SeeSR! That's an amazing work indeed! When I tried to calculate the metric FID using the code proposed in `basicsr/metrics/fid.py`, the result...

striveAgain

The work you've done on this article is truly commendable, providing me with a wealth of inspiration and insight. I have a question. Regarding the "TCA module" discussed in your...

ZhihaoChe

Cuda out of memory(Training process)

1

Hellow ! I follow the following settings, and I used the NVIDIA GeForce RTX 3090 (24GB) to run the trianing code. However, I met the problem of cuda out of...

Shengqi77