CarlHuang comments

Results 17 comments of


                                            CarlHuang

Could you please provide the demo.py

> https://github.com/lalalafloat/VNext/blob/main/projects/IDOL/demo_idol.py > > python projects/IDOL/demo_idol.py --config-file projects/IDOL/configs/coco_pretrain/r50_coco_sequence.yaml --input input.png --output result.png Can you sucessfully run demo visualize ??

Could you please provide the demo.py

Is GIOU or DIOU or CIOU better than IOU?

> > > > It doesn't work by increasing the learning rate. so the conclusion is CIOU /DIOU is not better than IOU loss in YOLOX ?

download pretrain model issue

![image](https://user-images.githubusercontent.com/104048874/165028973-defce4ed-597b-4462-8b3c-121fbdc44853.png)

Is there any demo for inference video or images?

also look forward demo /inference script too.

[Data preparation code] Is there any code for data preparation?

same question...hope have answer..

[Data preparation code] Is there any code for data preparation?

@qm-intel do you get the data preparation code about stage2 or stage 3?

For finetuning, add an alternative to LlamaFactory

Cound you have a plan to add continue pretraining support ?

For finetuning, add an alternative to LlamaFactory

> > Cound you have a plan to add continue pretraining support ? > > I think Finetune itself is kind of continue pretraining. yes, you are right. I want...

For finetuning, add an alternative to LlamaFactory

thanks,,good idea.