The Ultimate Keras Cheat Sheet for Deep Learning!
0 likes13 views
The document outlines how to use Keras, a deep learning library, for building and training neural networks with examples of model creation, data preprocessing, and training. Key topics include layer addition, model compilation, and sequence padding along with the use of categorical data. Additionally, it emphasizes the importance of standardization and splitting data into training and testing sets.
![www.1stepgrow.com
Keras is a powerful and easy-to-use deep learning library for Theano
and TensorFlow that provides a high-level neural networks API to
develop and evaluate deep learning models.
>>> import numpy as np
>>> from keras.models import Sequential
>>> from keras.layers import Dense
>>> data = np.random.random((1000,100))
>>> labels = np.random.randint(2,size=(1000,1))
>>> model = Sequential()
>>> model.add(Dense(32, activation='relu', input_dim=100))
>>> model.add(Dense(1, activation='sigmoid'))
>>> model.compile(optimizer='rmsprop', loss='binary_crossentropy',
metrics=['accuracy'])
>>> model.fit(data,labels,epochs=10,batch_size=32)
>>> predictions = model.predict(data)
A Basic Example](https://image.slidesharecdn.com/keras-250212101436-b8fe373f/85/The-Ultimate-Keras-Cheat-Sheet-for-Deep-Learning-2-320.jpg)
The Ultimate Keras Cheat Sheet for Deep Learning!
- 1. KERAS www.1stepgrow.com PYTHON FOR PYTHON FOR DATA SCIENCE DATA SCIENCE CHEAT SHEET PART- 1
- 2. www.1stepgrow.com Keras is a powerful and easy-to-use deep learning library for Theano and TensorFlow that provides a high-level neural networks API to develop and evaluate deep learning models. >>> import numpy as np >>> from keras.models import Sequential >>> from keras.layers import Dense >>> data = np.random.random((1000,100)) >>> labels = np.random.randint(2,size=(1000,1)) >>> model = Sequential() >>> model.add(Dense(32, activation='relu', input_dim=100)) >>> model.add(Dense(1, activation='sigmoid')) >>> model.compile(optimizer='rmsprop', loss='binary_crossentropy', metrics=['accuracy']) >>> model.fit(data,labels,epochs=10,batch_size=32) >>> predictions = model.predict(data) A Basic Example
- 3. www.1stepgrow.com >>> from keras.preprocessing import sequence >>> x_train4 = sequence.pad_sequences(x_train4,maxlen=80) >>> x_test4 = sequence.pad_sequences(x_test4,maxlen=80) >>> from keras.models import Sequential >>> model = Sequential() >>> model2 = Sequential() >>> model3 = Sequential() >>> from keras.utils import to_categorical >>> Y_train = to_categorical(y_train, num_classes) >>> Y_test = to_categorical(y_test, num_classes) >>> Y_train3 = to_categorical(y_train3, num_classes) >>> Y_test3 = to_categorical(y_test3, num_classes) Sequence Padding Sequential Model One-Hot Encoding Preprocessing Model Architecture
- 4. www.1stepgrow.com >>> from sklearn.model_selection import train_test_split >>> X_train5,X_test5,y_train5,y_test5 = train_test_split (X, y,test_size=0.33,random_state=42) >>> from sklearn.preprocessing import StandardScaler >>> scaler = StandardScaler().fit(x_train2) >>> standardized_X = scaler.transform(x_train2) >>> standardized_X_test = scaler.transform(x_test2) Train and Test Sets Standardization/Normalization Preprocessing
- 5. Build your career story with 1stepGrow Academy Follow 1stepGrow Academy Save the Post Share your Comments www.1stepgrow.com