vision-agent
vision-agent copied to clipboard
landing-ai
Vision agent
Description --- * Fix the overlay of multiple masks with multiple annotations. * Fix linting
Obviously It can not work when trying to detect following pictures, hopes to more smart. 
Content Dear maintainers, I would like to propose adding support for **DeepSeek** as an alternative code generator in this project. DeepSeek is a powerful AI tool that specializes in generating...
我使用gguf/DeepSeek-Janus-Pro-7B作为模型后端的服务， 测试 ` import vision_agent.tools as T import matplotlib.pyplot as plt image = T.load_image("/home/VisionAgent/examples/chat/tmp4vcajy48.png") dets = T.countgd_object_detection("person", image) viz = T.overlay_bounding_boxes(image, dets) T.save_image(viz, "people_detected.png") plt.imshow(viz) plt.show() ` 已经测试成功 输入输出图像分别为： ...
The project currently only allows pydantic 2.7.4 to be used, which is causing incompatibilities with other libraries. If possible, could the list of allowed versions be updated to allow any...
The current implementation only supports detecting one object type per call. For real-world, we often need to detect multiple object types simultaneously. This limitation forces users to make sequential API...
