flysssss
flysssss
Great project! I have some confusion。 I saw the txt file of the recognition result of the door and window. In the floorplan_ to_ 3dObject_ in_ blender. py file also...
Do you have any plans about the hand keypoints pre-models? 
环境: H100 基础镜像: docker pull pytorch/pytorch:2.3.0-cuda11.8-cudnn8-devel python3.10 步骤: 按照步骤https://hf-mirror.com/Tencent-Hunyuan/TensorRT-libs/blob/main/README_zh.md提示进行 报错:   CUDA runtime API error cudaErrorNoKernelImageForDevice at line 298 in file fMHAPlugin.cu CUDA runtime API error cudaErrorNoKernelImageForDevice at line...
你好,我采用开放词汇目标检测微调方式训练1个epoch后,进行推理测试。数据集采用coco的格式构建,共75类,转义成英文单词的话,每类2-4个单词。测试时,如果将75类全部写入-texts 入参时,目标识别不出来,减少到55类,正常检出。通过修改闭集class_names.py文件里面coco类别也是一样的问题。是因为单次推理时Token数超过265的原因吗?