gojosatoru

When our custom dataset label is not named after the coco dataset file, we are likely to trigger the following bugs when we run the eval script: AssertionError: Results do...

Can you give me the config file of yolo-world about image_demo.py?

1

I have read your image_demo.py, but the config file should be given into the example file.

YOLOv6量化后仅能预测一类

3

我采用了你们在YOLOv6官方仓库的量化代码[(https://github.com/meituan/YOLOv6/tree/main/tools/quantization/ppq)]，但是在完成所有的流程后，仅能预测一类出来，我猜测这跟nms中你们给的nms_forward_function函数，因为它内部仅定义了全0的向量，这导致了无法预测出出了类别0 (person)以外的类别，不知道你们能否给出有效的nm_forward_function函数呢？非常感谢！

How can I use CLIP model to obtain the image and text embeddings?

3

Now I need to try to use the prompt training scheme to finetune the yolo-world. But according to the `docs/prompt_yolo_world.md`, I need to extract the image embedding/text embedding by using...

Finetune question

3

Dear author, now if I want to add a GQA dataset for training, what do I need to do exactly?

Hello, I have implemented the link to convert SAM-HQ from PTH to [Tensorrt](https://github.com/zhujiajian98/sam-hq-tensorrt), I can test it together when I have time, thank you very much!