Release 0.4.0

[qubvel]

New models

Segformer

contributed by @brianhou0208

Originally, SegFormer is a transformer-based semantic segmentation model known for its simplicity and efficiency. It uses a lightweight hierarchical encoder to capture multi-scale features and a minimal decoder for fast inference.

With segmentation-models-pytorch you can utilize the model with a native Mix Vision Transformer encoder as long as with 800+ other encoders supported by the library. Original weights are also supported and can be loaded as follows:

import segmentation_models_pytorch as smp

model = smp.from_pretrained("smp-hub/segformer-b5-640x640-ade-160k")

See more checkpoints on the HF Hub.

Or with any other supported encoder:

import segmentation_models_pytorch as smp

model = smp.Segformer("resnet34")

UperNet

contributed by @brianhou0208

UPerNet (Unified Perceptual Parsing Network) is a versatile semantic segmentation model designed to handle diverse scene parsing tasks. It combines a Feature Pyramid Network (FPN) with a Pyramid Pooling Module (PPM) to effectively capture multi-scale context.

import segmentation_models_pytorch as smp

model = smp.UPerNet("resnet34")

New Encoders

Thanks to @brianhou0208 contribution 800+ timm encoders are now supported in segmentation_models.pytorch. New modern encoders like convnext, efficientvit, efficientformerv2, hiera, mambaout and others can be used as easily as:

import segmentation_models_pytorch as smp

model = smp.create_model("upernet", encoder_name="tu-mambaout_small")
# or
model = smp.UPerNet("tu-mambaout_small")

New examples

• Added example for multi-class segmentation by @TimbusCalin
• Added example for onnx export

Other changes

• Project migrated to pyproject.toml by @adamjstewart
• Better dependency managing and testing (minimal and latest dependencies, linux/windows/mac platforms) by @adamjstewart
• Better type annotations
• Tests are refactored for faster CI and local testing by @qubvel

All changes

...

[codecov]

Codecov Report

All modified and coverable lines are covered by tests ✅

Files with missing lines	Coverage Δ
segmentation_models_pytorch/__version__.py	100.00% <100.00%> (ø)

[qubvel]

I'm going to make a release tomorrow, feel free to to add anything to release notes in case I forgot something/someone (there will be a full list of changes also, without dependabot PRs).

[adamjstewart]

All tests passing. Only warnings are due to our pretrainedmodels dep which I plan on removing anyway. Should be good to go!