Bin-ze

转换一切顺利，但是检测到的物体置信度为负数

5

我按照您的readme在开发板上进行了模型部署，一切顺利，但是检测物体的置信度为负数，这是因为什么原因造成的，因为我没有在trt推理下评估模型的指标，所以我很难确定这样带来的性能影响，如果你可以回答我的疑问，我将很感激

[Bug] Training ABCNet but the e2e indicators are all 0

9

### Prerequisite - [X] I have searched [Issues](https://github.com/open-mmlab/mmocr/issues) and [Discussions](https://github.com/open-mmlab/mmocr/discussions) but cannot get the expected help. - [X] The bug has not been fixed in the [latest version (0.x)](https://github.com/open-mmlab/mmocr) or...

Great job! I'm trying to use opensfm to reconstruct 360 images I followed the official tutorial and successfully reconstructed the collected 360 images. My configuration file is as follows： ’‘’...

How to use hloc to obtain accurate poses when only using a camera to capture an indoor scene？

2

Noting the excellent performance of HLOC, I wanted to use it for pose estimation in indoor scenes. I collected multiple sets of indoor data, but when visualizing poses, I found...

Note that pixsfm only uses the GPU to accelerate when performing dense feature extraction, and the remaining steps are completed on the CPU. However, the GPU will continue to be...

absolute_pose_estimation

1

I try to use absolute_pose_estimation to calculate the camera pose of the newly added scene. I want to know whether BA is used to optimize the camera pose after calling...

Added distributed training logic for HDMapNet and does not affect precision

when run: ``` rec2_from_rec1 = pycolmap.align_reconstructions_via_reprojections(reconstruction_1, reconstruction_2) reconstruction_1.transform(rec2_from_rec1) print(rec2_from_rec1.scale, rec2_from_rec1.rotation, rec2_from_rec1.translation) ``` only reconstruction_1 and reconstruction_2 have same images work, other time: ``` In [4]: pycolmap.align_reconstructions_via_reprojections(reconstruction_1, reconstruction_2) F20240407 16:35:44.643065 32617...

ba error

2

I do ba from a known colmap model： ``` from pixsfm.refine_colmap import PixSfM from pathlib import Path refiner = PixSfM() path_to_input_model = ~ path_to_output_model= ~ path_to_image_dir = ~ model, _,...