grandpaxun242 / adabldm Goto Github PK

Hello, author! I noticed that in your model training setup, you specify only one object's one category for training at a time. It seems like the dataset paths need to be manually changed for each category. Does this mean I need to continuously change the training folder and run train.py separately for each category to train on all the data? thx for replying!

Hello author, I would like to ask how to modify the gpu id when I train and test, because I found that 0 card is used by default every time.

Hi, When the training code is available...
Big Thanks

thx for your reply!!!

https://g/GrandpaXun242/AdaBLDM/blob/44a71f07dc62d4477cc6255a96e5defe2c430b3c/train.py#L34
Hello dear authors! I wonder how many epochs I should set in training.

I got this error when I run the code

Dear author, I have trained and tested the code in the bottle/broken_large category in the mvtec_ad dataset, and I have only used a small class (broken_large), which works well. However, there is a small problem, because the location of the generated mask is random, but for the category of bottle, its borken only occurs on the ring, which means that this kind of data has a relative spatial structure. I have found that this method has poor effect on this situation, may I ask how to improve it

Cannot find "share" in the repo

dear authors, now I need to generate defects on my pcb(print circuit board) dataset, it's a dataset including 5 kinds of defects. can you please tell me how should I correct your code to generate my photos. Thank you!!

Hi, Is there any pretrained model to download and test? thanks

Hello，what you have done is impressive！Well，I am currently busy completing my undergraduate project and need some defect images to train my pixel refinement model. Is it possible to get your after trained MVTecAD dataset? I can receive the dataset personally or through the cloud drive if necessary. This will be a great help to me. Looking forward to your reply.

Dear authors! Thanks for your contributions! When running python generate_dataset.py, you set GENERATENUM = 20000 to generate target images of trainset. It seems a large number for only a defect type of a class. What's the influence of different image numbers of trainset, for example, if I set GENERATENUM = 200?

Dear author, when I run the code with command,python ./foreground_predictor/foreground_predictor.py,there is a mistake
Traceback (most recent call last): File "./foreground_predictor/foreground_predictor.py", line 10, in <module> from models import EfficientnetPM File "/home/401229/AdaBLDM-main/foreground_predictor/models.py", line 1, in <module> from futils import FeaturesCollector, load_ckpt ImportError: cannot import name 'FeaturesCollector' from 'futils' (/home/401229/AdaBLDM-main/foreground_predictor/futils.py)

I checked the futils.py file, there is no FeaturesCollector function, what should I do with it?

Because cannot directly access 'https://huggingface.co/models' to download 'openai/clip-vit-large-patch14'.
I copy 'clip-vit-large-patch14' to the corresponding '.cache/huggingface/transformers' after downloading it.
However, when run "tool_add_control.py" again, it still asks me to download model again. How can I solve this?