Comments (3)
1
from tensorflow-pokemon-course.
That's right! And now that we have our labels extracted from the data, let's normalize the data so everything is on the same scale:
def data_normalizer(train_data, test_data):
train_data = preprocessing.MinMaxScaler().fit_transform(train_data)
test_data = preprocessing.MinMaxScaler().fit_transform(test_data)
return(train_data, test_data)
train_data, test_data = data_normalizer(train_data, test_data)
Now we can get to the machine learning! Let's create the model using Keras. Keras is an API for Tensorflow. We have a few options for doing this, but we'll keep it simple for now. A model is built upon layers. We'll add two fully connected neural layers.
The number associated with the layer is the number of neurons in it. The first layer we'll use is a 'ReLU' (Rectified Linear Unit)' activation function. Since this is also the first layer, we need to specify input_size
, which is the shape of an entry in our dataset.
After that, we'll finish with a softmax layer. Softmax is a type of logistic regression done for situations with multiple cases, like our 2 possible groups: 'Legendary' and 'Not Legendary'. With this we delineate the possible identities of the Pokémon into 2 probability groups corresponding to the possible labels:
length = train_data.shape[1]
model = keras.Sequential()
model.add(keras.layers.Dense(500, activation='relu', input_shape=[length,]))
model.add(keras.layers.Dense(2, activation='softmax'))
Close this issue when you are finished normalizing the data.
from tensorflow-pokemon-course.
Awesome! We are moving right along.
In the next issue we will compile our model and evaluate it.
from tensorflow-pokemon-course.
Related Issues (3)
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflow-pokemon-course.