0781532

How to train TCSynth dataset of traditional Chinese character test images?

1

Hello, I try to use train.py from your suggested porosity below https://github.com/GitYCC/deep-text-recognition-benchmark to train the "TCSynth dataset" of traditional Chinese character test images but failed. the error shown that: num-samples...

Dear Soimy, Can we set up the output files with: 1. CMYK color format, instead of RGBA8888? 2. 300dpi, instead of 240dpi? 3. rectangular frame with specified width & height,...

I have encountered some challenges when using Deepspeed that we hope to address with your expertise. 1. During fine-tuning LLM LLama-7b-chat-hf and LLama-13b-chat-hf with multiple GPUs, I observed the following...

[HELP] Runable solution of RTX 5090 GPU + Linux Driver version + Pytorch version + Deepspeed version for LLM finetuning

5

### Reminder - [x] I have read the above rules and searched the existing issues. ### System Info I want to finetune a LLM (e.g Llama-3-8B) using RTX 5090 on...