-
Hi sophie091524, hi everyone,
I was trying to use your DAE algorithm. During the training phase I got an Out Of Memory error despite setting batch_num = 1.
The error seems to come from the loss…
-
Hi,
After doing fine-tuning, I have checked MSE plots in two tabs: "
offline_metrics_red_cube/text_conditioned" and "training", and they were quite different.
![image](https://github.com/octo-m…
-
请问为啥要在隐空间里利用diffusion model生成编码向量Z呢?直接用对编码向量计算mse损失来重建不行吗?我的意思是gt生成z,原文是将LR图像利用diffusion生成这个Z,为啥不直接LR用一个简单的mse生成这个Z呢,
-
如果论文中的MSE是反标准化后算出来的结果,那么该模型效果还是比较好的,但是根据代码,论文中的MSE好像是未反标准化算出来的结果,那这效果也太差了吧,跟直接猜跟昨天结果一样算出来的MSE差不多
-
Hello, the paper is very interesting. I tried to run the proposed code, but got MSE 39. After that, I tried to change the Lmoment to 0.1 and 0.01, but got MSE still around 40. What am I missing ?
-
Is it that my package for sentence-transformers not updated?
**### AttributeError: module 'sentence_transformers.evaluation' has no attribute 'MSEEvaluator'**
-
This is in the tutorials. I don't think it is necessary to remove the MSE/MAE/scaled MSE, but possibly move those down to a "Misc" section. The comparisons should be of variance explained ( which, I a…
-
Hi,Dr. @MingjunZhong
Thanks for sharing the code. This time I am trying to reproduce result of REDD based seq2point. But the results I get for REDD are quite different from your reported results. Co…
-
Hi,
How much loss(MSE) did u obtained after your training got completed, I've trained my model for about 100 epochs and its ~100 ?
Moreover, I'm using RandomCrop of patches of LR and HR for trainin…
-
当我运行 run.py 时,缺少以下三个 Hugging Face 模型:
/data2/chengjunhao/THEATERGEN/pretrained_models/vae_ft_mse
/data2/chengjunhao/THEATERGEN/pretrained_models/diffusion_1.5_comic
/diffusion_1.5/unet
您能否提供这些模型…