segmentation_models.pytorch
This PyTorch-based Python library provides neural networks for image semantic division. The library contains 12 different codec-coding architectures, including Unet, Segformer, and DPT. It also offers over 800 pre-trained coders with timm support.
SE
qubvel-org · Image & Photo Processing
STARS11.8K
FORKS1.9K
COMMITS846
CONTRIBUTORS77
VERSIONv0.5.0
UPDATEDyesterday
PythonPyTorchImage SegmentationNeural NetworksMIT
Common commercial products in this category: Adobe Photoshop, Adobe Lightroom, Cloudinary
What can it do?
- By writing two lines of code, you create a PyTorch-based neural network.
- You configure models using pre-trained weights and thymm support.
- For training processes, you use loss functions with common metrics such as Dice, Jaccard, and Tversky.
User reviews
- • NeutralGitHub Issue
cannot import name 'container_abcs' from 'torch._six'
“Encountering this from today: 19-Jun-2021 ImportError Traceback (most recent call last) in () 4 get_ipython().system('pip install -U segmentation-models-pytorch') 5 ----> 6 import segmentation_models_pytorch as smp 7 8 11 frames…”