search

OSUPCVLab / SegFormer3D

Official Implementation of SegFormer3D: an Efficient Transformer for 3D Medical Image Segmentation (CVPRW 2024)
https://openaccess.thecvf.com/content/CVPR2024W/DEF-AI-MIA/papers/Perera_SegFormer3D_An_Efficient_Transformer_for_3D_Medical_Image_Segmentation_CVPRW_2024_paper.pdf
GNU General Public License v3.0
69 stars 11 forks source link

how to train my own dataset? #12

Open wydilearn opened 1 month ago

wydilearn commented 1 month ago

I can not preprocess the dataset using providing codes. Please provide full explicit comments for how to use other datset.

wydilearn commented 1 month ago

My terminal only print the two sentences without doing anything: "started preprocessing Brats2017..." "finished preprocessing Brats2017..." Is this a incomplete codes?

bnavard commented 1 month ago

The preprocessing code only processes Brats dataset. What is your dataset ?

wydilearn commented 1 month ago

My dataset has only one channel, and I have transform my dataset correctly, but I still cannot train the dataset. Could you please explain which part of the codes that I need to edit?

wydilearn commented 1 month ago

In addition, my labels have three classes.

wydilearn commented 1 month ago

And my image size is 128x48x96

wydilearn commented 1 month ago

无标题 In addition, I don't find the test codes. I can not test the model after training it.

bnavard commented 1 month ago

If your dataset is BraTS you can use our datapreprcoessing. What is your dataset ? If you are using a data with different shape (other than 128x128x128) you need to change the SegFormer3D architecture config such that the path embeddings works with your dataset size. For that you should change your experiment config.