yuanqianguang/myceliumseg-benchmark

How yuanqianguang/myceliumseg-benchmark works

MMSegmentation is a semantic-segmentation framework, with a repository-specific mycelium dataset and SegFormer configuration/model alongside the broader model zoo. Its visible inference workflow loads a configured segmentor, prepares an image through the test pipeline, runs the model, and returns a segmentation result; evaluation provides segmentation metrics. The README is empty, and several core modules are indexed but unsampled, so the graph limits call relationships to those shown in excerpts or the source index.

Main entry points: inference.py Inference API · custom.py Custom dataset base · datasets/builder.py Dataset builder · models/builder.py Model builder

Components 21

Data preparation

Pipeline composition mmseg/datasets/pipelines/compose.py
Image transforms mmseg/datasets/pipelines/transforms.py
Pipeline loading mmseg/datasets/pipelines/loading.py
Batch formatting mmseg/datasets/pipelines/formating.py
Dataset builder mmseg/datasets/builder.py
Custom dataset base mmseg/datasets/custom.py
Dataset wrappers mmseg/datasets/dataset_wrappers.py
Pascal Context mmseg/datasets/pascal_context.py

Segmentation models

Model builder mmseg/models/builder.py
ResNet backbone mmseg/models/backbones/resnet.py
Model utilities mmseg/models/utils
Point decode head mmseg/models/decode_heads/point_head.py
Lovasz loss mmseg/models/losses/lovasz_loss.py

Inference and evaluation

Inference API mmseg/apis/inference.py
Segmentation metrics mmseg/core/evaluation/metrics.py
Boundary metrics mmseg/core/evaluation/extra_metrics.py

Mycelium specialization

EPA dataset mycelium_model/dataset/EPA_mycelium.py
Mycelium SegFormer config mycelium_model/model/segformer.b0.1024x1024.mycelium.507.py

Other components

User
Input image
Segmentation result

Connections 13

User → Inference API: requests inference mmseg/apis/inference.py
Input image → Inference API: supplies image mmseg/apis/inference.py
Inference API → Pipeline composition: composes pipeline mmseg/apis/inference.py
Inference API → Model builder: builds segmentor mmseg/apis/inference.py
Inference API → Segmentation result: returns result mmseg/apis/inference.py
Dataset builder → Dataset wrappers: builds wrappers mmseg/datasets/builder.py
Pascal Context → Custom dataset base: extends base mmseg/datasets/pascal_context.py
Custom dataset base → Dataset builder: uses registry mmseg/datasets/custom.py
Custom dataset base → Pipeline composition: uses pipelines mmseg/datasets/custom.py
Image transforms → Dataset builder: registers transforms mmseg/datasets/pipelines/transforms.py
ResNet backbone → Model builder: registers backbone mmseg/models/backbones/resnet.py
Model builder → ResNet backbone: builds backbone mmseg/models/backbones/resnet.py
Segmentation metrics → Boundary metrics: imports metrics mmseg/core/evaluation/metrics.py

Drawn by GitDiagram on November 13, 2026 from the repository's file tree, README and source files. Read as Markdown ·