Logo
Akida 1.8.4
  • Overview
  • Installation
    • Requirements
    • Quick installation
    • Running examples
  • User guide
    • Getting started
      • For beginners
      • For users familiar with deep-learning
    • Akida user guide
      • The Akida Execution Engine
        • 1. The Spiking Neural Network model
        • 2. Input data format
        • 3. Determine training mode
        • 4. Interpreting outputs
      • Neural Network model
        • Specifying the Neural Network model
        • Saving and loading
        • Input layer types
        • Data-Processing layer types
      • Using Akida Unsupervised Learning
        • Learning constraints
        • Compiling a layer
        • Learning parameters
    • CNN2SNN toolkit
      • Overview
        • Conversion Workflow
        • Compatibility Constraints
        • Typical training scenario
      • Layers Considerations
        • Supported layer types
        • Quantization-aware layers
        • Training-Only Layers
        • First Layers
        • Final Layers
      • Layer Blocks
        • Overview
        • conv_block
        • dense_block
        • separable_conv_block
      • Tips and Tricks
    • Hardware constraints
      • Input layer
      • Data-Processing layers
        • Convolutional layer
        • Fully connected layer
  • API reference
    • Akida Execution Engine
      • Model
      • Layer
      • LayerStatistics
      • Observer
      • InputData
      • InputConvolutional
      • FullyConnected
      • Convolutional
      • SeparableConvolutional
      • Dense
      • Sparse
      • coords_to_sparse
      • dense_to_sparse
      • BackendType
      • ConvolutionMode
      • PoolingType
      • LearningType
    • CNN2SNN
      • convert
      • check_model_compatibility
      • WeightQuantizer
      • TrainableWeightQuantizer
      • WeightFloat
      • QuantizedConv2D
      • QuantizedDepthwiseConv2D
      • QuantizedDense
      • QuantizedSeparableConv2D
      • ActivationDiscreteRelu
      • QuantizedReLU
    • Akida models
      • Quantization blocks
        • conv_block
        • separable_conv_block
        • dense_block
      • Model zoo
        • Mobilenet
        • DS-CNN
        • VGG
  • Examples
    • GXNOR/MNIST inference
      • 1. Loading the MNIST dataset
      • 2. Look at some images from the test dataset
      • 3. Load the pre-trained Akida model
      • 4. Classify a single image
      • 5. Check performance across a number of samples
    • Regression tutorial
      • 1. Load dependencies
      • 2. Load the dataset
      • 3. Create a Keras model satisfying Akida NSoC requirements
      • 4. Check performance
      • 5. Conversion to Akida
        • 5.1 Convert the trained Keras model to Akida
        • 5.2 Check Akida model accuracy
      • 6. Estimate age on a single image
    • DS-CNN/KWS inference
      • 1. Load CNN2SNN tool dependencies
      • 2. Load the preprocessed dataset
      • 3. Create a Keras model satisfying Akida NSoC requirements
      • 4. Check performance
      • 5. Conversion to Akida
        • 5.1 Convert the trained Keras model to Akida
        • 5.2 Check prediction accuracy
        • 5.3 Confusion matrix
    • VGG and DS-CNN/CIFAR10 inference
      • 1. Load CNN2SNN tool dependencies
      • 2. Load and reshape CIFAR10 dataset
      • 3. Create a quantized Keras VGG model
        • 3.A Instantiate Keras model
        • 3.B Check performance
      • 4. Conversion to Akida
        • 4.A Convert to Akida model
        • 4.B Check hardware compliancy
        • 4.C Check performance
      • 5. Create a quantized Keras DS-CNN model
        • 5.A Instantiate Keras DS-CNN model
        • 5.B Check performance
      • 6. Conversion to Akida
        • 6.A Convert to Akida model
        • 6.B Check hardware compliancy
        • 6.C Check performance
        • 6D. Show predictions for a random image
    • Transfer learning with MobileNet for cats vs. dogs
      • 1. Transfer learning process
      • 2. Load and preprocess data
        • 2.A - Load and split data
        • 2.B - Preprocess the test set
        • 2.C - Get labels
      • 3. Convert a quantized Keras model to Akida
        • 3.A - Instantiate a Keras base model
        • 3.B - Modify the network and load pre-trained weights
        • 3.C - Convert to Akida
      • 4. Classify test images
        • 4.A Classify test images
        • 4.B Compare results
    • MobileNet/ImageNet inference
      • 1. Load CNN2SNN tool dependencies
      • 2. Load test images from ImageNet
        • 2.1 Load test images and preprocess test images
        • 2.2 Load labels
      • 3. Create a quantized Keras model
        • 3.1 Instantiate Keras model
        • 3.2 Check performance of the Keras model
      • 4. Convert Keras model for Akida NSoC
        • 4.1 Convert Keras model to an Akida compatible model
        • 4.2 Test performance of the Akida model
        • 4.3 Show predictions for a random test image
    • CNN conversion flow tutorial
      • 1. System configuration
        • 1.1 Load CNN2SNN tool dependencies
        • 1.2 Load and reshape MNIST dataset
        • 1.3 Set training parameters
      • 2. Model creation and performance check
        • 2.1 Model creation
        • 2.2 Performance check
      • 3. Model Akida-compatibility check and changes
        • 3.1 Compatibility check
        • 3.2 Model adaptation
        • 3.3 Performance check
      • 4. Model quantization and training
        • 4.1 Quantize the model
        • 4.2 Performance check
      • 5. Convert trained model for Akida and test
        • 5.1 Final conversion
        • 5.2 Performances check with the Akida Execution Engine
  • Changelog
  • Support
  • License
Akida Examples
  • Docs »
  • Akida examples

Akida examples¶

To learn how to use the Akida Execution Engine, the CNN2SNN toolkit and check the Akida processor performance against MNIST, CIFAR10, ImageNet and Google Speech Commands (KWS) datasets please refer to the sections below.

../_images/sphx_glr_plot_gxnor_mnist_thumb.png

GXNOR/MNIST inference¶

../_images/sphx_glr_plot_regression_thumb.png

Regression tutorial¶

../_images/sphx_glr_plot_ds_cnn_kws_thumb.png

DS-CNN/KWS inference¶

../_images/sphx_glr_plot_vgg_ds_cnn_cifar10_thumb.png

VGG and DS-CNN/CIFAR10 inference¶

../_images/sphx_glr_plot_transfer_learning_thumb.png

Transfer learning with MobileNet for cats vs. dogs¶

../_images/sphx_glr_plot_mobilenet_imagenet_thumb.png

MobileNet/ImageNet inference¶

../_images/sphx_glr_plot_cnn_flow_thumb.png

CNN conversion flow tutorial¶

Download all examples in Python source code: examples_python.zip

Download all examples in Jupyter notebooks: examples_jupyter.zip

Gallery generated by Sphinx-Gallery

Next Previous

© Copyright Copyright 2020, BrainChip Holdings Ltd. All Rights Reserved.