liyues / patrecon Goto Github PK

Hi,
first of all, thanks for making your code public!
I have been reading your paper and wanted to try using your code, but the exp folder seems to be missing and also a 3D_CT.bin file.

I would really appreciate it, if you can help me get it running, or tell me how to replace the data the model needs!

trained model for running experiment is not available!
Would you please provide the pretrained model.

Hello! Thank you for sharing your work!
Can this be done with bones?

Hello Mrs. Liyues,

I would like to use more than one GPU, how can I achieve this? In trainer net at line 25: self.model = nn.DataParallel(self.model).cuda(), I should add gpu ids inside DataParallel besides self.model right? Should I also increase the batch size to be more than the used GPU? Also did you tried batch size more than 1? What was the result if you tried?
Thanks in advance.

Hello Mrs. Liyues,
I would like to retrain the model. What are the input parameters of the model. If it's convenient, can you upload a training code. Thank you very much.

Greeting!
We want to reproduce the experimental results of the paper. We used 147-layer 128*128 lung CT and found that different data augmentation methods have a great impact on the SSIM results. Now we use rotation ±2.5 degrees and displacement ±0.75 pixels. In the final test, the SSIM value can only reach 0.73, but the SSIM can reach 0.80 by only rotating ±5 degrees, all using the original network.
We want to know the data augmentation method in detail.

Hi! this is a great paper! and I want to ask how to use trainer.py to train the model?

Dear Dr. Shen,

I am Haonan Xiao, a Ph.D. student from Prof. Jing Cai's group at The Hong Kong Polytechnic University. Our group read your paper about volumetric image reconstruction from 2D projections and we think it is very interesting and inspiring. It would be great if we can have further discussion on it, however, I cannot find your contact information. I really appreciate it if you can leave me a message at [email protected].

Thank you!

Best,
Haonan Xiao | 肖昊男
Ph.D. Student
Department of Health Technology and Informatics (HTI)
The Hong Kong Polytechnic University

Hello Mrs. Liyues,
I would like to retrain the model. What are the input parameters of the model. If it's convenient, can you upload a training code. Thank you very much.

Hello! I am interested in your thesis(PatRecon), so implemented your code in my Ubuntu 18.04 with the following requirements you gave.

pytorch: 0.4.1
numpy: 1.15.0
sklearn: 0.19.1
skimage: 0.14.0
PIL: 5.1.0
matplotlib: 2.2.2

sudo apt-get update
sudo apt-get install python3.5

python3 test.py --vis_plane 0
python3 test.py --vis_plane 1
python3 test.py --vis_plane 2

When finishing this code, I can see bunch of images that include Prediction, Groundtruth, and Difference image.
I think I followed what you said correctly, but it gave me wrong outputs. Does it have other requirements I should install?