user122861

Most recent activity

• Tflite input data type (int8) conversion in javascript

  @user122861 started

  • 6 comments
  • 1,857 views

  @Gordon replied
• Tflite input data type (int8) conversion in javascript

  in Bangle.js • 3 years, 3 months

  

  var tf = require("tensorflow").create(3072, model);
  
  function get_data(a){
  
  var d = [Math.round(a.x*100),Math.round(a.y*100)­,Math.round(a.z*100)];
    
  input_array.push(d);
  
  
  if (input_array.length > SAMPLE_SIZE-1){
  
  
  var row_array = [];
  var time_step_array = [];
  var final_input = [];
  var depth_array = [];
  
  for (i=0; i<input_array.length;i++){
      row_array = [];
      depth_array = [];
  
  for (j=0;j<input_array[0].length;j++){
      depth_array.push(input_array[i][j]);  
  }
  row_array.push(depth_array);
  time_step_array.push(row_array);
  }
  
  final_input.push(time_step_array);
  
  
  tf.getInput().set(final_input);
  
  //Terminal.println(tf.getInput());
  
  tf.invoke();
  
  Terminal.println(tf.getOutput());
  
  input_array = [];
  
  }
  
  
  }
  
  
  Bangle.on('accel', get_data);
  
  

  This is my code and my model takes input as array i am always getting the same output when printed. I am pretty sure there is no problem in model as i loaded the tflite model and tested the output in my desktop and it is working fine.

• Tflite input data type (int8) conversion in javascript

  in Bangle.js • 3 years, 3 months

  

  Hi @Gordon thanks for the reply
  so you mean my model input should be always a flat 1D array and then internal conversion should be made while creating model. Currently the my input_array is 4D array so can i directly input this to the model or should i recreate my model to take only 1D array inputs.

• Tflite input data type (int8) conversion in javascript

  in Bangle.js • 3 years, 3 months

  

  I have a tflite model which expects the input to be in int8 datatype

  var tf = require("tensorflow").create(2048, model);
  tf.getInput()[0] = input_array;
  tf.invoke();
  print(tf.getOutput()[0]);
  

  I have loaded my data in the same shape as my model expects but when i print (tf.getInput()[0] ) it always shows zero even when input_array has values. I have encoded my model with base64. Can anyone help me out @Gordon please help me out here

  Also tflite has standard get_tensor and set_tensor functions in interpreter to set the input data in proper format. I cannot see those functions in banglejs after loading the tflite model.

• Tensorflow lite for other things thant gesture

  in Bangle.js • 3 years, 3 months

  

  I followed the https://github.com/espruino/Espruino/tre­e/master/libs/tensorflow#actually-using-­it and it created a tflite model, my model has less 1024 parameters.
  However i get an error

  
  Uncaught Error: Didn't find op for builtin opcode 'ADD' version '1'
  

  I used tensorflow 2.0 to create model

  @Gordon can you please suggest way forward

• Tensorflow lite for other things thant gesture

  in Bangle.js • 3 years, 3 months

  

  Hi ,
  I have created my custom gesture recognition model and converted to tflite model but my input to model is a array of 4D how can we actually convert input stream into the format

  tf.getInput()[0] = x;