lichen14

About PointRend visualization?

1

Thanks for your great job! I wonder if there any visualization work for PointRend. I wanna present the improvement due to the introduction of PointRend, just like the paper mentioned....

hi, Giovanni, I just re-implemented the MG-2D on my dataset and met with some other bug for cpu explosion. When I used MG for pre-training, I found that the utilization...

How to get "BRATS2013_Syn_Flair_Train_X.npy" and "BRATS2013_Syn_Flair_Train_S.npy" from BRATS2013 dataSet？

7

I have got the BRATS2013 dataSet from https://www.smir.ch/BRATS/Start2013，however，there are 2 big folder inside（Image_Data & Synthetic_Data） how can i get "BRATS2013_Syn_Flair_Train_X.npy" and "BRATS2013_Syn_Flair_Train_S.npy" in the code？ THX moreover, i can't find...

no test code

1

hi, thanks for sharing the code. it seems there is not any code for testing and evaluating the performance on TESTset.

hi, thansk for open-source. can you share the pre-trained weights? such as resnet50 backbone and others. thanks.

questions about parameters.

2

Hello, congratulations on the excellent paper! Can you share the parameters used for training in the args? I have reimplemented your work for DRIVE dataset, but I can not get...

It seems the definition code of dataset _RSNA PE Detection_ is not released, can you share it? thanks. : - )

关于3D交互式半自动分割的咨询

2

作者好，ISAT做2D-SAM分割已经能基本上满足我对2d图像的分割标注了，感谢！ 这个issue是想问：是否有类似的3D 标注工具呢？另外，现在的3D标注是什么个情况啊？也是需要逐slice标注了再整合在一起吗？那这样的话，似乎2D的ISAT就能做，能否支持load 3D的模型，接受3D的输入呢？例如三维的医学图像CT volume 感谢，实际使用中遇到的一个新问题，前来咨询 :smile:

cls_head 计算特征时维度不匹配？

3

https://github.com/Hzzone/PseCo/blob/0192ee521cd3786ed5f2d89231fd74567ef87d9c/fsc147/4_1_train_roi_head.py#L277 我在跑这行代码的时候总是会遇到embeddings和prompts特征维度不匹配的问题，导致 https://github.com/Hzzone/PseCo/blob/0192ee521cd3786ed5f2d89231fd74567ef87d9c/models.py#L25 这里无法直接矩阵乘 比如： - 计算 https://github.com/Hzzone/PseCo/blob/0192ee521cd3786ed5f2d89231fd74567ef87d9c/fsc147/4_1_train_roi_head.py#L277 时，embeddings 和 prompts.unsqueeze(1) 的shape 分别是 torch.Size([8192, 3, 512]) torch.Size([8192, 1, 3, 512]) ，这样直接计算会显存爆炸，需要384G ** 我试过把prompts.unsqueeze(1) 去掉unsqueeze(1) ，这样不报显存OOM的bug了，但是下面的代码会报错： - 计算 https://github.com/Hzzone/PseCo/blob/0192ee521cd3786ed5f2d89231fd74567ef87d9c/fsc147/4_1_train_roi_head.py#L283 时，embeddings 和...