-
hi! I am Asad Ullah, I am also working on project like this. I was looking for foundation models and found your project on hugging face.
I really want to know how the resulting image looks like.
-
Hi @PhucNDA ,
I try to reproduce ScanNet200 results. I prepare the data and follow your running code instructions. I get the below results:
```
ScanNet200 Evaluation
##########################…
-
Hello, author. I spent about 2 hours running the MVTec classification work on an RTX 4070. Is this time reasonable? The results under 1-shot are about 1 point lower (for MVTec) and 5 points lower (for…
-
first thanks for all your hard work, you mentioned needing help from community in research on best params for configs;
I wrote up this article: https://civitai.com/articles/8313
and released this …
-
Hi, we have been trying to reproduce the paper's result on THP and NHP models. The predictions we get are quite far from the ground truth labels, specifically for the next event time:
- labels:
arra…
-
This is my settings:
if __name__ == "__main__":
pretrained_model_path = '/root/autodl-tmp/StoryGen/checkpoint_StorySalon/'
logdir = "./inference_StorySalon/"
num_inference_steps = 40
…
-
### Is your feature request related to a problem?
The autocomplete function gets called every single time they type a letter, so if you query the database every time, it'll get pretty slow.
### De…
-
I trained PET model on my custom crop dataset to count crop heads for 250 epochs.
> [ep 241][lr 0.0001000][95.76s]{"train_lr": 9.999999999999967e-05, "train_loss": 0.06341644998685253, "train_loss…
-
Hi, I have created a chicken TF reference database and completed the pySCENIC analysis in my chicken data.
But I find a problem in my result from pyscenic ctx program output file:
![微信图片_20241017…
-
Hello, thank you for open-sourcing your code. While reproducing your work, I found that the experimental results on the GSM8K dataset is strange.
According to your paper, fine-tuning the GSM8K data…