How to do FPGA inference of deblur GAN network using deep learning HDL tool box?

I want to implement Deblur GAN on Zync FPGA. I have already trained the dataset on google colab and the weights have been generated. How can I load the trained model in deep learning HDL tool box for inferencing using FPGA?

Answer 1

[Tarunbir Gambhir]

You have various options to import a trained model into MATLAB. If your model is a pretrained TensorFlow-Keras network, you can use importKerasNetwork to import the model into MATLAB. You can also import a model of a ONNX (Open Neural Network Exchange) model format using importONNXNetwork. You can refer this documentation for the list of supported Deep Learning model Import and Export options.

After importing the neural network, you can load it into the deep learning HDL workflow. Refer this example on how to deploy a pretrained deep learning network to a target board.