urbaneman

Would you like to provide a more standard version?

1

Hello, when test your network, it says that > I0918 15:13:54.308856 12776 net.cpp:137] Memory required for data: 998273536 > I0918 15:13:54.308861 12776 layer_factory.hpp:77] Creating layer loss > [libprotobuf FATAL google/protobuf/stubs/common.cc:61]...

The mAP of EfficientDet-D0

7

Hello, @toandaominh1997 , thanks for your great work. I saw your update of the EfficientDet-D0's weight and result. In the table of benchmarking, the title is > PASCAL VOC 2007...

buildEngineWithConfig() get error of Plugin Op DCNv2_TRT

2

Hi, @eweill-nv,thanks for your work. I'm try to register the "DCNv2_TRT" layer with your code. It register sucessful, however got the error of "DCNv2_TRT" in parser onnx: ``` ---------------------------------------------------------------- Input...

感谢您的工作和对开源社区的贡献。 我想在自己的数据使用RT-DETR，数据目标在原尺度为正方形目标，我想利用这个信息，在数据处理时保持原图比例，我也参考了这个[issue13](https://github.com/lyuwenyu/RT-DETR/issues/13)，但是里面没有 Attention Mask 相关讨论。 我想咨询的问题是： 在图像保持原图比例缩放时，会引入填充像素，填充部分的Attention Mask在DETR中会被置为1，并在encode的时候忽略 https://github.com/facebookresearch/detr/blob/29901c51d7fe8712168b8d0d64351170bc0f83e0/models/backbone.py#L72 但是在 RT-DETR 中采用直接resize的方法，没有填充，`keep_ratio: False`，Attention Mask作用在了CDN中 https://github.com/lyuwenyu/RT-DETR/blob/5b628eaa0a2fc25bdafec7e6148d5296b144af85/rtdetr_pytorch/src/zoo/rtdetr/hybrid_encoder.py#L299 我需要在原图比例上使用RT-DETR，那么**PAN结构的特征融合时填充像素特征是否会影响非填充目标特征的表达**？**是否需要对遮挡像素的特征做mask**?

我现在想将nuScenes数据集转换到Xtreme1格式，进行Lidar Fusion的标注，目前已完成了相机内外参的转换和数据到导出，且观察标注框的点云重投影符合预期，以上是背景。 现在我想进一步的将nuScenes数据集GT导出为预标注，方便进行任意模型生成伪标签，在进一步进行人工标注，我按照 [issue 85](https://github.com/xtreme1-io/xtreme1/issues/85#issuecomment-1432350238) 中的实例json导出了GT，但是upload - Contains annotation result - Ground Truth，提示 `success with error`，后端错误如下 ``` backend-1 | 2025-08-07 09:38:30.048 INFO 1 --- [pool-6-thread-5] ai.basic.x1.usecase.UploadDataUseCase : Get data content,frameName:ca9a282c9e77460f8360f564131a8af5,content:[{"name":"camera_config","type":"directory","files":[{"name":"ca9a282c9e77460f8360f564131a8af5.json","fileId":7299,"type":"file"}]},{"name":"camera_image_0","type":"directory","files":[{"name":"ca9a282c9e77460f8360f564131a8af5.jpg","fileId...