Not a member of Pastebin yet?
Sign Up,
it unlocks many cool features!
- import tensorflow as tf
- import numpy as np
- from sklearn.datasets import load_breast_cancer
- from sklearn.model_selection import train_test_split
- dadosBreastCancer = load_breast_cancer()
- entradaDeDadosBreastCancer, saidaDeDadosBreastCancer = dadosBreastCancer.data, dadosBreastCancer.target
- entradaDeDadosBreastCancerTreino, entradaDeDadosBreastCancerTeste, saidaDeDadosBreastCancerTreinamento, saidaDeDadosBreastCancerTeste = train_test_split(entradaDeDadosBreastCancer, saidaDeDadosBreastCancer, test_size=0.3, random_state=1)
- print(entradaDeDadosBreastCancer.shape[0])
- model = tf.keras.models.Sequential([
- tf.keras.Input(shape=(entradaDeDadosBreastCancer.shape[1],)),
- tf.keras.layers.Dense(32, activation='relu'),
- tf.keras.layers.Dropout(0.2),
- tf.keras.layers.Dense(32, activation='relu'),
- tf.keras.layers.Dropout(0.2),
- tf.keras.layers.Dense(2, activation='softmax')
- ])
- model.compile(optimizer='adam',
- loss='sparse_categorical_crossentropy',
- metrics=['accuracy'])
- model.fit(entradaDeDadosBreastCancer, saidaDeDadosBreastCancer, epochs=100)
- print("Acuracia no treinamento",model.evaluate(entradaDeDadosBreastCancerTreino, saidaDeDadosBreastCancerTreinamento, verbose=2)
- )
- print("Acuracia no test", model.evaluate(entradaDeDadosBreastCancerTeste, saidaDeDadosBreastCancerTeste, verbose=2)
- )
Add Comment
Please, Sign In to add comment