MSCG-Net
MSCG-Net copied to clipboard
samleoqh
Multi-view Self-Constructing Graph Convolutional Networks with Adaptive Class Weighting Loss for Semantic Segmentation
Bumps [pillow](https://github.com/python-pillow/Pillow) from 6.2.2 to 9.3.0. Release notes Sourced from pillow's releases. 9.3.0 https://pillow.readthedocs.io/en/stable/releasenotes/9.3.0.html Changes Initialize libtiff buffer when saving #6699 [@radarhere] Limit SAMPLESPERPIXEL to avoid runtime DOS #6700 [@wiredfool]...
![dependabot[bot] avatar](https://avatars.githubusercontent.com/in/29110?v=4 "dependabot[bot] avatar"){kind=avatar}
Hello; Would you please upload the code for the SCG-Net Semantic Segmentation Paper, for learning and research purposes. Thanks
Bumps [protobuf](https://github.com/protocolbuffers/protobuf) from 3.10.1 to 3.18.3. Release notes Sourced from protobuf's releases. Protocol Buffers v3.18.3 C++ Reduce memory consumption of MessageSet parsing This release addresses a Security Advisory for C++...
Bumps [numpy](https://github.com/numpy/numpy) from 1.15.4 to 1.22.0. Release notes Sourced from numpy's releases. v1.22.0 NumPy 1.22.0 Release Notes NumPy 1.22.0 is a big release featuring the work of 153 contributors spread...
How to replace the acw loss with cross-entropy loss? criterion = torch.nn.CrossEntropyLoss() in train_R50.py doesn't work.
Is there an option to play around with the size of the train and val sets. For example, use x% of the train set as val set, instead of predefining...
Do you have a version of the code optimised for the IJRS 2021 paper? Self-constructing graph neural networks to model long-range pixel dependencies for semantic segmentation of remote sensing images(https://www.tandfonline.com/doi/full/10.1080/01431161.2021.1936267?scroll=top&needAccess=true)
It is great job. when I traning my dataset, most of the time，the iou is satirfactory ，but sometimes the aux loss would be very large. I debug the coed I...
Bumps [pygments](https://github.com/pygments/pygments) from 2.3.1 to 2.7.4. Release notes Sourced from pygments's releases. 2.7.4 Updated lexers: Apache configurations: Improve handling of malformed tags (#1656) CSS: Add support for variables (#1633, #1666)...
Hi @samleoqh Thank you for your release source code. It helps me a lot. During training process, I met a problem related to memory.  The process consume a lot...
