/acuity-models

Acuity Model Zoo

Primary LanguageJavaScript

Acuity Model Zoo

Acuity model zoo contains a set of popular neural-network models created or converted (from Caffe or Tensorflow) by Acuity toolset.

Model Viewer

Acuity uses JSON format to describe a neural-network model, and we provide an online model viewer to help visualized data flow graphs. The model viewer is inspired by netscope.

Classification

Detection

Segmentation

About Acuity

Acuity is a python based neural-network framework built on top of Tensorflow, it provides a set of easy to use high level layer API as well as infrastructure for optimizing neural networks for deployment on Vivante Vision IP powered hardware platforms.

Acuity Workflow

  • Importing from popular frameworks such as Caffe and Tensorflow

    AcuityNet natively supports Caffe and Tensorflow imports, although it can be expanded to other NN frameworks.

  • Fixed Point Quantization

    AcuityNet provides accurate Fixed Point Quantization from floating point 32 with a calibration dataset and produces accuracy numbers before and after quantization for comparison

  • Graph Optimization

    Neural-network graph optimization is performed to reduce graph complexity for inference, such as Layer Merging, Layer Removal and Layer Swapping

    • Merge consective layers into dense layers, such as ConvolutionReluPool, FullyConnectedRelu, etc.
    • Fold BatchNrom layers into Convolution
    • Swap layer ordering when suitable to reduce output size
    • Remove Concatenation layers
    • Intelligent layer optimization when mathamatically equivalent
  • Tensor Pruning

    Pruning neural networks tensors to remove ineffective connections and neurons to create sparse matrix

  • Training and Validation

    Acuitynet provides capability to train and validate Neural Networks

  • Inference Code Generator

    Generates OpenVX Neural Network inference code which can run on any OpenVX enabled platforms