Steps for creating simple neural network using TensorFlow
$10-30 USD
Завершено
Опублікований almost 6 years ago
$10-30 USD
Оплачується при отриманні
I am building an Android application that takes decision with the help of a TensorFlow that takes data collected from device sensors.
What I need is the DETAILED steps to create a TensorFlow Light module and to import it into my Android project which is built using Android Studio.
I have already installed Python 3.6.5 (64-bit) on my PC, and installed TensorFlow using the following command:
C:\> pip3 install --upgrade tensorflow
The needed steps should CLEARLY cover the following:
______________________________________________________
1. How to create a Neural Network with 8 inputs, 6 neurons in hidden layer and 2 outputs.
2. How to feed the Neural Network with data:
a. How to train it (4000 samples, each with 8 real-number parameters)
b. How to test it (500 sample, each with 8 real-number parameters)
3. How to convert the created Neural Network to TensorFlow Light.
4. How to Import that TensorFlow Light into my Android studio project.
Note:
As I have no previous experience in both Python and TensorFlow, each step must be explained in detail.
I am currently working with these kind of algorithms in tensorflow and especially building neural networks of different kinds which includes deep neural nets(which you have mentioned in your project description) and you can also try Recurrent neural networks with all the specifications kept the same i.e. nodes in layers and other stuff but its just that RNNs can be more effecient and effective. I am not so good with android however, but Tensorflow light conversion and inclusion in android studio we can work that out. ;)
$25 USD за 2 дні(-в)
4,8 (1 відгук)
1,0
1,0
5 фрілансерів(-и) готові виконати цю роботу у середньому за $34 USD