You are a extremely wonderful engineer
You are a extremely wonderful engineer
Han* 
KHi Dr.Furkan and everyone, is there any way to save checkpoint only after 80 epochs are completed? I want to save a checkpoint every 10 epochs like 80-90-100-110... but instead it saves 10-20-30-40... and takes too much spaces. Thank you very much.
DI don't think so, atleast in A1111... maybe we would need to write a custom script for that, should be fairly easy.
KThank you. My current workaround is to train it until 80 epochs without saving >> get 1 checkpoint >> keep training that checkpoint until 150 epochs and save every 10 so I get 90-100-110...
Mthat’s the way to do it.
Fthank you so much fıor compliments
Fyes you can do that
Fwhat are you using to do training google colab?
YHere come some more. Fantastic work!
YIm following your video "Best training setup parameters for Dreambooth using classificaiton images.
YI have prepared a folder with handpicked classification images, but when I start training dreambooth ignores them and starts creating them. Have you had this problem? Thank you in advance for any help.
Fmust be a configuration error
Fafter saving config click load
Fyou tried that?
Falso show me settings please
YThank you, let me check
Y
YIve tried saving and loading with same issue
Fshow settings please
YWhat is interesting is that it recognizes the classification images it generated on its own, but it wont recognize the ones I put in
Fok use
Fpre processing tool
Fin train tab
Fit will fix
YGreat thanks! Do I have to use a specific ratio for this?
YI intend to use a 960 x 512 when working. On the preprocess images it says 512x512
Fyour classification images probably should be same dimension
Fas your training images
Fif you dont change max resolution they will get downscaled
Ygreat, thanks a lot!
Ykeep up the great work
YIt worked! im so happy!
RHey @Furkan Gözükara SECourses are you aware of any GPT assistants who can already help with captioning datasets. I find myself constantly going back to make changes to a tag word or a string, and have to go back to all the dataset txt files, and it's quite time inefficient. Would imagine being able to leverage GPT + python would bring captioning from an hours to minutes. Any luck yet with applying these GPT agents to captioning?
Fthere are already blip and other captions
Fwith the caption thing what is important is not describing that image
Fthe important thing is which words you want to improve
Fyou want to do fine tuning right?
Dalthough BLIP makes the process much faster, in my opinion it is less accurate. Sometime it produces wrong descriptions for the images. This might affect the training right? I have not tried GPT-4's image description feature yet, but from what I heard, it is quite accurate. maybe a comparison between BLIP and GPT-4 is needed
RYes precisely. I am doing Lora of recognisable fashion model person wearing recognisable fashion outfit. I need to be able to trigger the recognisable face and clothes, so it is rigid, and to do that I am using key tags in the caption to make the ai aware what is in the picture. I havent optimised yet for face, i am working on outfit to be faithfull to my studio original photo reference that I shot. But the point is, that BLIP captioning only creates the txt structure. The caption guess is pretty useless. But anyway, what i want is an Ai assistant to propagate the editing. So i decide, i need to change a term, say about the buttons, i need the button tags to change across all the txt files in the dataset. Do you know what I mean.
RI am just asking about an Ai assistant to go in to each txt file and change them. I am using 50 images per dataset concept, and i have about 10 concepts (outfits). So that's a lot of txt files to recursively edit.
RSo I would imagine a python code would be involved to delegate text editing across all text files...
RI want to fine tune yes.
Dso you want to replace a tag with another tag and do the same for all the text files?
RYes. Say, "white button" to "4 white patterned button". There are 50 images with those buttons. Would be great for the Ai assistant, to propagate the change across all the txt files
RCLIP captioning only guesses what things are. I need something to help me edit details
RSo yes, replace tags
R--across a group of txt files
Dyou could download notepad++ and use "find and replace in files" feature, it will find and replace words in all the files you have mentioned
Roh i did not know that. It can do this already
RHow silly of me