indoorloc 0.1.3

A unified framework for indoor localization

室内定位工具库 | Multi-dataset, multi-model indoor localization toolkit

English | 中文

---

For Beginners: 3 Lines = Complete Workflow

Skip the boilerplate. Focus on algorithms, not data formats.

import indoorloc as iloc

train, test = iloc.load_dataset('ujindoorloc')           # Load any of 36+ datasets
model = iloc.create_model('resnet18', dataset=train)     # Auto-configure model
results = model.fit(train).evaluate(test)                # Train & evaluate

Auto-download datasets · Auto-adapt dimensions · Auto-configure model

For Experts: YAML Config + CLI

Full control via OpenMMLab-style configuration system.

python tools/train.py configs/wifi/resnet18_ujindoorloc.yaml

# Override any parameter
python tools/train.py configs/wifi/resnet18_ujindoorloc.yaml \
    --model.backbone.model_name efficientnet_b0 \
    --train.lr 5e-4 --train.epochs 200

# configs/wifi/resnet18_ujindoorloc.yaml
_base_:
  - ../_base_/models/resnet.yaml

model:
  backbone:
    model_name: resnet18
    pretrained: true
  head:
    num_floors: 5
    num_buildings: 3

train:
  epochs: 100
  lr: 0.001

---

Supported Datasets

WiFi, BLE, CSI, UWB, Magnetic, and more — all with iloc.load_dataset(). View Details →

RSSI	CSI	Other
WiFi UJIndoorLoc SODIndoorLoc LongTermWiFi Tampere TUJI1 BLE iBeaconRSSI BLEIndoor BLERSSIU_UCI	WiFi CSI CSIIndoor HWILD HALOC CSIBench Massive MIMO MaMIMOCSI DICHASUS DeepMIMO	UWB UWBIndoor UWBRanging Magnetic MagneticIndoor Fusion WiFiIMUHybrid MultiModalIndoor VLC / RFID / Ultrasound VLCIndoor RFIDIndoor

---

Supported Algorithms

Traditional ML + 700+ Deep Learning backbones via timm. View Details →

Traditional	Deep Learning Backbones	Prediction Heads
k-NN Weighted k-NN SVM Random Forest Gaussian Process	CNN: ResNet, EfficientNet, ConvNeXt, MobileNet, RegNet, DenseNet... ViT: ViT, Swin, DeiT, BEiT, EVA... Hybrid: CoAtNet, MaxViT, EfficientFormer...	RegressionHead ClassificationHead FloorHead BuildingHead HybridHead HierarchicalHead

---

Installation

pip install indoorloc

More options

pip install indoorloc[vision]   # With vision support
pip install indoorloc[full]     # All features
pip install -e ".[dev]"         # Development

---

Advanced Usage

YAML Configuration

# configs/wifi/resnet18_ujindoorloc.yaml
_base_:
  - ../_base_/models/resnet.yaml

model:
  backbone:
    model_name: resnet18
    pretrained: true
  head:
    num_floors: 5
    num_buildings: 3

train:
  epochs: 100
  lr: 0.001

python tools/train.py configs/wifi/resnet18_ujindoorloc.yaml

Custom Model Registration

from indoorloc.registry import LOCALIZERS
from indoorloc.localizers.base import BaseLocalizer

@LOCALIZERS.register_module()
class MyLocalizer(BaseLocalizer):
    def fit(self, signals, locations, **kwargs):
        self._is_trained = True
        return self

    def predict(self, signal):
        pass

model = iloc.create_model('MyLocalizer')

Project Structure

indoorloc/
├── signals/          # WiFi, BLE, IMU, etc.
├── locations/        # Location classes
├── datasets/         # 36+ datasets
├── localizers/       # ML & DL algorithms
├── evaluation/       # Metrics
└── configs/          # YAML configs

Evaluation Metrics

Metric	Description
Mean Position Error	Average error (m)
Median Position Error	Median error (m)
Floor Accuracy	Floor classification
Building Accuracy	Building classification

---

License

Apache License 2.0

Citation

@software{indoorloc,
  title = {IndoorLoc: A Unified Framework for Indoor Localization},
  year = {2024},
  url = {https://github.com/qdtiger/indoorloc}
}

Acknowledgements

• OpenMMLab — Registry and config system
• timm — 700+ pretrained models