CFU Playground (3) - ML on a board (Arduino nano 33 ble )

-
I am going through this step without running Tensorflow lite micro in the Risc-V environment in the CFU Playground. It doesn't matter if you are familiar with Tensorflow lite micro, but if not like me, you need to port your own model and check if it works properly. The reason for choosing Arduino nano 33 ble is that it has luxurious specifications compared to Arduino uno. It has Cortex-M4, 64Mhz, 256KB SRAM, 1MB Flash Memory, and sensors such as a gyroscope built-in. So, you can do interesting experiments in the future. Starting with a board with too little memory and poor CPU performance can incur many complicated errors. And you have to spend a lot of effort to optimize your code for fitting into the memory.
https://store-usa.arduino.cc/products/arduino-nano-33-ble?selectedStore=us

When it comes to price, ESP32 DevKit can also be an alternative. But Tensorflow Lite Micro in ESP32 is supported only on ESP-IDE. The ESP-IDE is less convient than Arduino IDE. Above all, the advantage is that Pete Warden, an early contributor to TinyML, provides interesting examples using this board. Most of the tutorials are on Github, but it would be helpful to refer to the book.



After installing Arduino IDE, click Tools -> Manage Libraries to open a pop-up window. Then search "Arduino_TensorFlowLite" and install it. After that, open File -> Examples -> Arduino_TensorFlowLite -> hello_world and modify only the necessary parts. That's it! The hello_world example implements a regression model estimating a sine wave. Since the input of the CNN model is a periodic function, I could reuse many parts. The most important part is to insert the model.cpp file created in the previous blog and connect the input/output to the Tensorflow lite micro library.

* In the hello_world tab, edit the following part. 

- static tflite::AllOpsResolver resolver; //Reduce unnecessary memory waste by defining only necessary networks. You can check the required network with a program called Netron that parses the tflite file as shown below.



  static tflite::MicroMutableOpResolver<4> micro_op_resolver;
  micro_op_resolver.AddConv2D();
  micro_op_resolver.AddReshape();
  micro_op_resolver.AddFullyConnected();
  micro_op_resolver.AddFullyConnected();

- In hello_world, its input has only one int8_t value for an inference. But we need 36 floating numbers for our input. Also, it used the quantization option during converting the model. So, it needs some codes for handling it but we don't need it for I didn't use the quantization option for simplicity. Just replace the input code as below. If we use pointer operation, we will save more memory. But, for the stability, I chose array variables.

  for (int j=0; j<input_length; j++){
      model_input->data.f[j] = x_input[j];
  }

- After replace model.cpp, compile/upload codes into the Arduino board
- To use Tool -> Serial plotter, output is mulpiplied by 100 and casted to integer. As shown in the below figure, it performs well the inference.

Comments

Post a Comment

Popular posts from this blog

RNN (5) - FPGA System Design

-
Image
This is the last post on hardware implementation. The RTL codes of the previous post were designed for HW Accelerator IP to perform RNN, and this post describes how to design the whole system for targetting FPGA. The FPGA board used here is an FPGA Board using Xilinx ZYNQ-7000 as open hardware called Pynq-z2. (For Pynq-z2, please refer to the link below.) -  http://www.pynq.io/ -  https://www.tulembedded.com/FPGA/ProductsPYNQ-Z2.html -  https://pynq.readthedocs.io/en/latest/ First, the RNN Accelerator must open a channel to communicate with the ARM-Cortex A9 where SW is running. IP Packaging is performed using Vivado of Xilinx, and I used the AXI interface template provided by Vivado. RTL codes  on the right of the figure below  in the code window  shows how to  combine RNN IP with AXI interface. IP Packaging is possible easily through a few steps in Vivado. (Details will be posted separately.) After IP Packaging, you need to create a bit file to downl...
Read more

RNN (3) - System Simulator

-
Image
The Pytorch reference in the previous post uses the optimized library and floating point number, so the performance can be considered the most ideal. In the system simulator for Verilog design, some restrictions follow.  - Fixed Point Number: Because the range of numbers is limited, performance restrictions follow.  - Suboptimal Matrix Operation: The existing Pytorch model has been optimized for efficient and accurate operation in the Python environment. There is a difference in performance in the System Simulator that is actually implemented.  - Non-linear activation function: Here, tanh (hyperbolic tangent) is used, and linear approximation is performed for convenience of implementation.  Here, a 16-bit fixed point number is used. In fact, all 16 bits are not used and only 7 decimal places are used for easy calculation. Unused redundant bits should be optimized and removed in the future, but the truncation so that prevent overflow during every Addition/Multiplicati...
Read more

RNN (4) - RTL Design

-
Image
I designed the RTL in the same way as the System Simulator designed in the previous post. The major considerations for RTL design are as follows.  (The detailed code description will be posted in a separate post later.  Also, there are many good tutorials on how to use Intel Quartus Modelsim, so you'd better search for it. I will post the explanation of simulating this code in a separate post. ) - I/O method: The most common method is to save the input in the memory, drive the RNN, save the predicted value to output memory, and then send the completion signal. At this time, the memory can be selected in various ways. Various methods such as FIFO, Single Port, Dual Port, etc. can be used. Here, Single Port Memory is selected as the simplest.  - Timing: RTL stands for Register Transfer Level. I don't know who put it on, but it seems to have been put together relatively well. Register is a component whose output is changed at the edge of the clock. Since there is some logic ...
Read more