zanz-byte Goto Github PK
Type: User
Bio: This account is created for Machine Learning study in Telkom University. Name: Abdul Aziz Marwan, NIM: 2101201024
Location: Indonesia
Type: User
Bio: This account is created for Machine Learning study in Telkom University. Name: Abdul Aziz Marwan, NIM: 2101201024
Location: Indonesia
Classification of 5 different leaf types using transfer learning
# Train a Simple TensorFlow Lite for Microcontrollers model This notebook demonstrates the process of training a 2.5 kB model using TensorFlow and converting it for use with TensorFlow Lite for Microcontrollers. Deep learning networks learn to model patterns in underlying data. Here, we're going to train a network to model data generated by a [tanh] (https://en.wikipedia.org/wiki/Tanhc_function) and [arctan] (https://en.wikipedia.org/wiki/Inverse_trigonometric_functions) function. This will result in a model that can take a value, `x`, and predict its tanh and arctan, `y`. The model created in this notebook is modified from the [hello_world](https://github.com/tensorflow/tensorflow/tree/master/tensorflow/lite/micro/examples/hello_world) example for [TensorFlow Lite for MicroControllers](https://www.tensorflow.org/lite/microcontrollers/overview). This code uses 4 scenarios of 2 function (tanh & arctan) in each model to analyze: Scenario 1: 1. Tanh function: 1 input with 8 neurons, 1 output 2. Arctan function: 1 input with 8 neurons, 1 output Scenario 2: 3. Tanh function: 1 input with 16 neurons, 1 output 4. Arctan function: 1 input with 16 neurons, 1 output Scenario 3: 5. Tanh function: 1 input with 8 neurons, 1 hidden layers with 8 neurons, 1 output 6. Arctan function: 1 input with 8 neurons, 1 hidden layers with 8 neurons, 1 output Scenario 4: 7. Tanh function: 1 input with 16 neurons, 1 hidden layer with 16 neurons, 1 output 8. Arctan function: 1 input with 16 neurons, 1 hidden layer with 16 neurons, 1 output <table class="tfo-notebook-buttons" align="left"> <td> <a target="_blank" href="https://colab.research.google.com/github/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb"><img src="https://www.tensorflow.org/images/colab_logo_32px.png" />Run in Google Colab</a> </td> <td> <a target="_blank" href="https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/examples/hello_world/train/train_hello_world_model.ipynb"><img src="https://www.tensorflow.org/images/GitHub-Mark-32px.png" />View source on GitHub</a> </td> </table>
Fauzi Abdul Rohim 2101182035
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.