trikim

Compile caffe error on GPU mode

1

I have succeed to compile caffe with CPU mode. But when I tried to compile it with GPU mode, I met these problems. ... [ 5%] Building NVCC (Device) object...

train_all(rpn_config, rcnn_config, gpu_id) Error

2

I finished the Setup by following your instruction. When I tried to train the model, I encountered the problem as below. Preloaded imdb train.. done Computing roidb train.. Reference to...

Is the cropped proposals as the inputs of BCN right? In "SDS-RCNN/experiments/test_rcnn.m", I am confused the operation at 67th line and 68th line. The code is shown as below, I...

Segmentation fault (core dumped) error.

2

I've installed the env by requirements.txt, the lib versions are the same, except the python version is 3.10. First, I encountered two problems: `LlamaTokenizer requires the SentencePiece library but it...

save model error

6

It takes long time before saving model at [line 426](https://github.com/bytedance/UNO/blob/23472178a05357248411160f467266edb38ad24f/train.py#L426). If I comment this line, `accelerator.wait_for_everyone()` the program can continue to run, but the saved dit_lora parameter is empty.