nbortolotti

package main

import (
	"fmt"
	"log"

	"github.com/nbortolotti/tflitego"
)

// topSpecie provide the name of the specia infered by the model

nbortolotti

import os
import argparse

os.environ['TF_CPP_MIN_LOG_LEVEL'] = '3'


def fun(x):
    return x + 1

nbortolotti

import numpy as np
import tflite_runtime.interpreter as tflite


interpreter = tflite.Interpreter(model_path="converted_model.tflite") # change the tflite model
interpreter.allocate_tensors()

input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()

nbortolotti

#converting to tflite from keras
converter = tf.lite.TFLiteConverter.from_keras_model(model)
tflite_model = converter.convert()
open ("iris_lite.tflite" , "wb") .write(tflite_model)

nbortolotti

import pandas as pd
import numpy as np

import tensorflow as tf


train_ds_url = "http://download.tensorflow.org/data/iris_training.csv"
test_ds_url = "http://download.tensorflow.org/data/iris_test.csv"
ds_columns = ['SepalLength', 'SepalWidth','PetalLength', 'PetalWidth', 'Plants']
species = np.array(['Setosa', 'Versicolor', 'Virginica'], dtype=np.object)

nbortolotti

model = tf.keras.Sequential([
  tf.keras.layers.Dense(16, input_dim=4),
  tf.keras.layers.Dense(3, activation=tf.nn.softmax),
])
model.compile(loss='categorical_crossentropy',
              optimizer='sgd',
              metrics=['accuracy'])

nbortolotti

#tensorflow and tensorflow_probability imports
import tensorflow as tf
import tensorflow_probability as tfp

#matplotlib import for visualizations
import matplotlib.pyplot as plt;

# numpy to support transformation and visualiation
import numpy as np;

nbortolotti

new_specie = np.array([7.9,3.8,6.4,2.0])
predition = np.around(model.predict(np.expand_dims(new_specie, axis=0))).astype(np.int)[0]
print("This species should be %s" % species[predition.astype(np.bool)][0])

nbortolotti

loss, accuracy = model.evaluate(dataset_test, steps=32)
print("loss:%f"% (loss))
print("accuracy: %f"%   (accuracy))

nbortolotti

model.fit(dataset, steps_per_epoch=32, epochs=100, verbose=0)