joytag

joytag copied to clipboard

Great work. Will you release finetune code?

3

Do you have plans to release code for finetuning?

LianghuiGuo

When can we update, or together we can do some work to the best of our ability on this project. I think there may be some images that require manual...

redpintings

ONNX format model?

7

thank you for this model! May I ask if you could possibly provide an ONNX format for the model? I want to try and use it in extensions for stable...

dfl

Hey there, I'd like to maybe help you with further training efforts. Do you have a way I can contact you outside of Github?

d8ahazard

On validation metrics and thresholds

2

First of all, nice job! I noticed in the validation arena you're using my suggested thresholds for my models, and a "default" one for yours. That's doing your work a...

SmilingWolf

Great project! I created a .py script that tags all files in an \input\ folder

4

In case it's of interest: ``` from Models import VisionModel from PIL import Image import torch.amp.autocast_mode from pathlib import Path import torch import torchvision.transforms.functional as TVF import os import tiktoken...

MNeMoNiCuZ

pytouch feature： `torch.backends.cuda.sdp_kernel()` is deprecated. In the future, this context manager will be removed. Please see `torch.nn.attention.sdpa_kernel()` for the new context manager, with updated signature.’

MoConWu

Hello, is there a discord server or a place in which we can chat? Thanks

yumlevi

Hello! I found a google colab notebook which let you run and use joy caption with gradio: https://colab.research.google.com/github/camenduru/joy-caption-jupyter/blob/main/joy_caption_jupyter.ipynb Is there any way to use joy tag instead of joy caption...

Bullseye110

"from Models import VisionModel" gives unresolved reference

1

Hey there, I installed the requirements via pip but still am getting the issue of "unresolved reference" regarding from Models import Vision Model.  I installed Torch again from the...

geonom