gojosatoru
gojosatoru
@wondervictor Hello, in the code of `generate_text_prompts`, how can I adapt to the format of `coco_class_captions.json`?
@wondervictor Is it like `[[person], [bicycle]]`?
@wondervictor OK, thanks for your explanation.
@Hstwhale Hello, can you use the weight and the corresponding prompt you have trained to predict the specified target?
@lin-whale Hello, what I'm wondering is if your trained model can make normal predictions, or is it just random predictions? What I suspect now is that there might be an...
@lin-whale Do you mean that the yolo-world trained by prompt-tuning will be lower?
Thanks for your reply, but the config file would meet the problems that we can add our dataset to the traindataloader, how can I address the problem? @wondervictor
可以的，请问您的邮箱是多少？我直接发给您。
我现在已经可以成功量化了，但是就是推理出来的只有针对类别0的框，其他类别是无法推理的，现在非常疑惑这个点。