sony-custom-layers-dev 0.4.0.dev6

Sony Custom Layers package

Sony Custom Layers (SCL)

Sony Custom Layers (SCL) is an open-source project implementing detection post process NN layers not supported by the TensorFlow Keras API or Torch's torch.nn for the easy integration of those layers into pretrained models.

Table of Contents

• Getting Started
  • Installation
  • Supported Versions
• API
  • TensorFlow API
  • PyTorch API
• License

Getting Started

This section provides an installation and a quick starting guide.

Installation

To install the latest stable release of SCL, run the following command:

pip install sony-custom-layers

By default, no framework dependencies are installed. To install SCL including the latest tested dependencies (up to patch version) for TensorFlow:

pip install sony-custom-layers[tf]

To install SCL including the latest tested dependencies (up to patch version) for PyTorch/ONNX/OnnxRuntime:

pip install sony-custom-layers[torch]

Supported Versions

TensorFlow

Tested FW versions	Tested Python version	Serialization
2.10	3.9-3.10	.h5
2.11	3.9-3.10	.h5
2.12	3.9-3.11	.h5 .keras
2.13	3.9-3.11	.keras
2.14	3.9-3.11	.keras
2.15	3.9-3.11	.keras

PyTorch

Tested FW versions	Tested Python version	Serialization
torch 2.0-2.4 torchvision 0.15-0.19 onnxruntime 1.15-1.19 onnxruntime_extensions 0.8-0.12 onnx 1.14-1.16	3.9-3.12	.onnx (via torch.onnx.export)

API

For sony-custom-layers API see https://sony.github.io/custom_layers

TensorFlow API

For TensorFlow layers see KerasAPI

To load a model with custom layers in TensorFlow, see custom_layers_scope

PyTorch API

For PyTorch layers see PyTorchAPI

No special handling is required for torch.onnx.export and onnx.load.

For OnnxRuntime support see load_custom_ops

License

Apache License 2.0.