Sony Custom Layers package
Project description
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
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
Supported Versions
Currently, SCL is being tested on a matrix of Python and TensorFlow versions:
Framework | Tested FW versions | Tested Python version | Serialization |
---|---|---|---|
TensorFlow | 2.10 | 3.8-3.10 | .h5 |
TensorFlow | 2.11 | 3.8-3.10 | .h5 |
TensorFlow | 2.12 | 3.8-3.11 | .h5 .keras |
TensorFlow | 2.13 | 3.8-3.11 | .keras |
TensorFlow | 2.14 | 3.9-3.11 | .keras |
Implemented Layers
SCL currently includes implementations of the following layers:
TensorFlow
Layer Name | Description | API documentation |
---|---|---|
FasterRCNNBoxDecode | Box decoding per Faster R-CNN with clipping | doc |
SSDPostProcess | Post process as described in SSD: Single Shot MultiBox Detector | doc |
Torch
- SCL aims to implement torch layers at a later stage
Loading the model
TensorFlow
with sony_custom_layers.keras.custom_layers_scope():
model = tf.keras.models.load_model(path)
See source for further details.
License
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distributions
No source distribution files available for this release.See tutorial on generating distribution archives.
Built Distribution
Close
Hashes for sony_custom_layers-0.1.0-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | fe8bb3ed256eb7a3bc07d9f931557de57490d18eabee20407d0d2fec93cf236a |
|
MD5 | f669565278d071f8730f8dbf646a2ef3 |
|
BLAKE2b-256 | b8a26aef532823ed57dc172250656d5e66a17400897edf65d4cc4fd19ab32efb |