Skip to content

💡 Repo of learning notes in DRL and DL, theory, codes, models and notes maybe.

License

Notifications You must be signed in to change notification settings

Ceruleanacg/Learning-Notes

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

79 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

License Platform Python

Learning Notes of DRL & DL

A repo of Learning notes of DRL & DL, theory, codes, models and notes maybe.

Content

Notes

Deep Learning Basic

Natural Language Processing

Deep Reinforcement Learning

Deep Learning Engineering

Docker

Codes

Requirements

  • numpy
  • scipy
  • sklearn
  • matplotlib
  • tensorflow==1.8

Instructions for codes

  1. Load your data, for example, iris data set.
from sklearn.datasets import load_iris
iris = load_iris()
  1. Standardize your data.
scaler = StandardScaler()
scaler.fit(iris.data)

x_data = scaler.transform(iris.data)
y_data = np.zeros((150, 3))
y_data[np.arange(150), iris.target] = 1
  1. Initialize activations, which are configurable.
activation_funcs = [function.relu] * 1
# activation_funcs = [function.tanh] * 1
# activation_funcs = [function.sigmoid] * 1
activation_funcs.append(function.linear)
  1. Initialize model, option parameters are configurable.
dense = Dense(x_space=4, y_space=3, neuron_count_list=[10], **{
    "loss_func": function.softmax_cross_entropy,
    "activation_funcs": activation_funcs,
    "learning_rate": 0.01,
    "enable_logger": True,
    "model_name": 'iris',
    "batch_size": 30,
    'model': 'train'
)
  1. Train or Restore & Evaluate.
dense.train(x_data, y_data)
# dense.restore()
dense.evaluate(x_data, y_data)

About

💡 Repo of learning notes in DRL and DL, theory, codes, models and notes maybe.

Topics

Resources

License

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published