/tfdetection_anomaly

Detection Toolbox for Tensorflow2

Primary LanguageJupyter NotebookApache License 2.0Apache-2.0

TFDetection

TFDetection is an detection toolbox based on Tensorflow2. TFDetection supports to you easily apply detection to your analysis services.

Overview of Components

Object Detection Anomaly Detection Backbone Neck
  • Faster R-CNN(2015)
  • Mask R-CNN(2017)
  • RetinaNet(2017)
  • YoloV3(2018)
  • YoloV3 Tiny(2018)
  • Cascade R-CNN(2018)
  • FCOS(2019)
  • Hybrid Task Cascade R-CNN(2019)
  • EfficientDet(2019)
  • YoloV4(2020)
  • YoloV4 Tiny(2020)
  • EfficientDet Lite(2020)
  • SPADE(2020)
  • PaDiM(2020)
  • PatchCore(2021)
  • VGGNet(2015)
  • ResNet(2016)
  • Wide ResNet(2016)
  • DenseNet(2016)
  • ResNeXt(2016)
  • MobileNet(2017)
  • MobileNetV2(2018)
  • DarkNet(2018)
  • MobileNetV3(2019)
  • EfficientNet(2019)
  • ResNeSt(2020)
  • CSP DarkNet(2020)
  • SwinTransformer(2021)
  • EfficientNetV2(2021)
  • FPN(2017)
  • PANet(2018)
  • BiFPN(2019)

Requirements

  • Python 3
  • tensorflow 2.4▲ (If you installed tensorflow 2.8▲, more backbone is available.)
  • keras

Contributor