-
hello，
i'm very interested in the paper. I have some questions about the execution of the entire process.
1."python train.py --machine ws --config configs/cityscapes_monodepth_highres_dec5_crop.yml
…
-
losses = model.train(dataset=dataset, opt="LBFGS", steps=50,device=device)
运行后报TypeError: train() got an unexpected keyword argument 'dataset'
在将dataset=dataset改成dataset后继续报TypeError: train() got an…
-
Sorry if this feels like a bit much, but it's something i've been looking forward to for many years.
**Is your idea a new setting, a change to an existing setting, or something else? Please des…
-
Thanks for the author's impressive work! And I have a few questions.
1. Do you have any plans to release the trained checkpoint for your model?
2. I tried to reproduce your results on the COCO dat…
-
Hi,
Thank you for this work.
I would like to enquire about MIA-Efficiency computation.
The following snippet
```
svc_mia_forget_efficacy = SVC_MIA(
shadow_train=shadow_train_loader…
-
Hello author, thank you for your great contribution. I am new to segmentation and I have a problem in trying to run the given segmatation code, I don't know how ADE20K should be adjusted to what kind …
-
This is my first time using Kohya_SS, and I've followed two guides, one from YouTube https://www.youtube.com/watch?v=ovuO8bT9Nzw and another from Civitai https://civitai.com/articles/6438/how-to-train…
-
You mentioned that we should put the pre-trained model into the some specific folder. But why we need this pre-traine dmodel? if we want to train the model ?
-
**Describe the bug**
Trains will forget all interrupts when coupling, regardless of direction, or what it's coupling to, even if the connects to engine with the exact same schedule. This does not hap…
-
Since it appears that Flux LoRA training can still be effective when only training specific layers, I am wondering if this functionality can be expanded to Finetuning, since this is where the biggest …