xmindflow / deformablelka Goto Github PK
View Code? Open in Web Editor NEW[WACV 2024] Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation
Home Page: https://arxiv.org/abs/2309.00121
[WACV 2024] Beyond Self-Attention: Deformable Large Kernel Attention for Medical Image Segmentation
Home Page: https://arxiv.org/abs/2309.00121
How to solve this? Or can I download D3D in other ways?
what is the role of 2D/deformable_LKA/deformable_2dconvolution.py and 2D/deformable_LKA/deformable_3dconvolution.py ?
Are they python implementation of dcn? If that's the case, why you need to use D3D?
Futhermore, as far as I konwn, D3D process THW data, they don't deform at T. I can't see the any modifications to D3D's dcn library.
So how do you deform at three spatial dimension? I mean, D, H, W. Thank you very much.
I find the code finally output 13 classes' results, but in inference_synpase.py, you wanna 8 classes like other papers. i wonder is the final result save in "summary.json"? and when i reproduce the code, i find inference_synpase.py didnt work , as well as write in the text. Then my final result is different from your paper, the result is in the image
what is the differences among DeformConv, DeformConvPack, DeformConvPack_experimental,
DeformConv_d, and DeformConvPack_d?
"Hello, author. Your work on deformable DLKA is very impressive. However, we seem to have found an issue: in your paper, the DSC for the Synapse using the nnformer is 86.57%, which is exactly the same as the data run in the nnformer paper. But your experimental environment is not the same as the nnformer's environment. That is to say, you have achieved completely identical experimental results in different environments?"
nnformer:
nnformer-experiment:We run all experiments based on Python 3.6, PyTorch 1.8.1
and Ubuntu 18.04. All training procedures have been per�formed on a single NVIDIA 2080 GPU with 11GB memory.
The initial learning rate is set to 0.01 and we employ a
“poly” decay strategy as described in Equation 7. The default
optimizer is SGD where we set the momentum to 0.99. The
weight decay is set to 3e-5. We utilize both cross entropy loss
and dice loss by simply summing them up. The number of
training epochs (i.e., max epoch in Equation 7) is 1000 and
one epoch contains 250 iterations. The number of heads of
multi-head self-attention used in different encoder stages is [6,
12, 24, 48] on Synapse. In the rest two datasets, the number
of heads becomes [3, 6, 12, 24].
deformable dlka-experiment:
We have implemented both 2D and 3D models using
the PyTorch framework and performed training on a sin�gle RTX 3090 GPU. For the 2D method, a batch size of 20
was used, along with Stochastic Gradient Descent (SGD)
employing a base learning rate of 0.05, a momentum of 0.9,
and a weight decay of 0.0001. The training process con�sisted of 400 epochs, employing a combination of cross�entropy and Dice loss,
"In light of this, we are very curious to know whether the segmentation figures for the Synapse using the nnformer in your paper were taken directly from the nnformer's work?"
Hello, I would like to know where the complete code flow of the Deformable LKA module in Figure 2 in your paper is, but I didn't find it
Hello, your work is excellent, and I'm eager to delve deeper into learning. However, I encountered an issue while running the training code, which indicates that the pre-training weight file is missing.
As shown below:
FileNotFoundError: [Errno 2] No such file or directory: './pretrained_pth/maxvit/maxvit_rmlp_small_rw_224_sw-6ef0ae4f.pth'
I couldn't find this particular pre-training weight file on the code homepage. Would you mind providing it? If possible, here's my email: [email protected].
Hello, while I was training the model, the system reminded me that it couldn't find the file “maxvit_rmlp_small_rw_224_sw-6ef0ae4f.pth”. How can I solve it? thanks ( :
Hello author, I noticed a strange phenomenon while reproducing the results of DAEFormer on the ISIC2018 dataset. After starting training on the preprocessed dataset, I noticed a gradient explosion in the loss value section. May I ask if this is caused by some issues with the code of the processed dataset
Hello! Thank you for resolving my issue earlier. I now realize that I ran it first but couldn't find the file. Where does it exist? Thank you very much!
Dear author:
When I run train_MaxViT_deform_LKA.py
the result:FileNotFoundError: [Errno 2] No such file or directory: './pretrained_pth/maxvit/maxvit_rmlp_small_rw_224_sw-6ef0ae4f.pth'
Hello author, while reproducing ISIC2018 and ISIC2018, I found a significant difference between the final results and those in your paper. May I ask if you have done any processing on the dataset, or could you upload the dataset you have processed.
Dear author:
Due to the poor performance of my computer, it is difficult to finish running the train_MaxViT_deform_LKA.py file.
When I run the test.py file it shows that I don't have best_model.pth and best_model.pth.txt
Do I need to run train_MaxViT_deform_LKA.py completely to obtain these two files? Or can these two files be downloaded directly?
Dear author, When I want to use synapse code to train kipa22 dataset, I meet this problem. But I don't know what's wrong with this. I do not know whether there is a problem with the size format of my data, or the parameters in the code need to be modified? Thanks for your help, may be this is a easy problem, but I don't know how to dealt with it.
I processed the date just use the nnUnet's code, then I copy the processed data to this project's folder.
Traceback (most recent call last):
File "d_lka_former/run/run_training.py", line 211, in
main()
File "d_lka_former/run/run_training.py", line 195, in main
trainer.run_training()
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/training/network_training/d_lka_former_trainer_synapse.py", line 490, in run_training
ret = super().run_training()
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/training/network_training/Trainer_synapse.py", line 321, in run_training
super(Trainer_synapse, self).run_training()
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/training/network_training/network_trainer_synapse.py", line 485, in run_training
l = self.run_iteration(self.tr_gen, True)
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/training/network_training/d_lka_former_trainer_synapse.py", line 295, in run_iteration
output = self.network(data)
File "/home/javier/conda3/envs/d_lka_net_3d/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/network_architecture/synapse/d_lka_former_synapse.py", line 153, in forward
x_output, hidden_states = self.d_lka_former_encoder(x_in)
File "/home/javier/conda3/envs/d_lka_net_3d/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/network_architecture/synapse/model_components.py", line 69, in forward
x, hidden_states = self.forward_features(x)
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/network_architecture/synapse/model_components.py", line 56, in forward_features
x = self.stages0
File "/home/javier/conda3/envs/d_lka_net_3d/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/javier/conda3/envs/d_lka_net_3d/lib/python3.8/site-packages/torch/nn/modules/container.py", line 139, in forward
input = module(input)
File "/home/javier/conda3/envs/d_lka_net_3d/lib/python3.8/site-packages/torch/nn/modules/module.py", line 1130, in _call_impl
return forward_call(*input, **kwargs)
File "/home/javier/Desktop/deformableLKA-main/3D/d_lka_former/network_architecture/synapse/transformerblock.py", line 60, in forward
x = x + self.pos_embed
RuntimeError: The size of tensor a (71680) must match the size of tensor b (32768) at non-singleton dimension 1
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for D3D
ERROR: Could not build wheels for D3D, which is required to install pyproject.toml-based projects
because i dont have an identification of the from identity provider 'live.com' does not exist in tenant 'Mohamed Bin Zayed University of Artificial Intelligence' and cannot access the application '00000003-0000-0ff1-ce00-000000000000'(Office 365 SharePoint Online) in that tenant. The account needs to be added as an external user in the tenant first. Sign out and sign in again with a different Azure Active Directory user account. can you change the source? thank u!
When training synapse data in 2D, processing 12% and then error:
Traceback (most recent call last):
File "train_MaxViT_deform_LKA.py", line 134, in
trainer[dataset_name](args, net, args.output_dir)
File "/home/sjh/mydisk/project/deformableLKA/2D/trainer_MaxViT_deform_LKA.py", line 168, in trainer_synapse
image = image_batch[1, 0:1, :, :]
IndexError: index 1 is out of bounds for dimension 0 with size 1
Who can handle this problem?
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.