lsabrinax

**bug描述** 描述一下你遇到的bug, 例如报错位置、报错信息（重要, 可以直接截个图）等 2.2.1创建tensor中给的创建tensor的表格里的uniform,查了下文档好像没有直接这个操作  只有torch.Tensor(3, 3).uniform_(-1, 1)这种用法 **版本信息** pytorch: torchvision: torchtext: ...

evaluation script

2

I have a question about evaluation script in `ScanNet/BenchmarkScripts/3d_evaluation/evaluate_semantic_instance.py` between line `120` and `137`. ``` if overlap > overlap_th: confidence = pred['confidence'] # if already have a prediction for this...

Thank you for your sharing! I have a question about the UV MAP, I know uv[:,:,0] defines foreground or background, but I want to know whether the uv[:,:,1] defines the...

RuntimeError: CUDA error: an illegal memory access was encountered

1

当一张图有超过两个框的时候，我将crop的特征送入下面的全连接层和卷积网络就会报上面的错，请问这个问题有什么解决办法吗

https://github.com/weijiawu/TransDETR/blob/b6c73c5fd773e5e0d87f394631cfcab6e167b070/models/qim.py#L109

https://github.com/weijiawu/TransDETR/blob/b6c73c5fd773e5e0d87f394631cfcab6e167b070/models/TransDETR_ignored.py#L379 the code above should be `track_instances.angle[active_idxes] = torch.abs(active_track_angle - gt_angle)`? because the first dim of track_instances.angle is num_queries

Support for Imagen

4

Thanks for your nice work! I want to know whether tomesd can only support stable diffusion model, can it support other diffusion model like as imagen