BiRefNet

BiRefNet copied to clipboard

Error When Resuming Training from Pre-trained Model

3

## Environment - **Hardware**: AWS `ml.g5.48xlarge` instance - **Model**: BiRefNet - **Dataset**: Custom dataset (~500 images) ## Context I successfully trained a model from scratch using my custom dataset of...

kiveboxops

Train with my custom large dataset

3

I have a large dataset of 300K images with different objects,car,human, animals, etc. Should I need to train from scratch or I can do transfer learning from your general pre-trained...

yaju1234

Finetunning Issue

5

Hello @ZhengPeng7 I am getting issue in Finetunning and Results 1. when i start the traininig its working well but when i give the path of checkpoint with the --resume...

Kaustubh-cpu

Assistance needed with Fine-Tuning Model on Custom Dataset

9

Hi @ZhengPeng7, Appreciate your excellent work on this model. I tried the HF demo with the General weights to remove the background from the car's interior image, but it was...

kparikh-tenup

General question

1

Hi, and thanks for making this code available! General question, how are the segments chosen by the model? My use case is human segmentation with a complex background. Which of...

antithing

未来可能实现通过提示词分割指定物体?

1

鹏啊,这是有可能的吗,这个架构里

zdoek001