如果我给模型喂了五朵Setosa花,我无法让模型预测它们确实是Setosas。
这是我的代码设置:
# Load libraries
import numpy as np
import pandas as pd
from keras import models
from keras import layers
from keras.models import Sequential
from keras.layers import Dense
from sklearn.utils import shuffle
from sklearn import preprocessing
from sklearn.preprocessing import StandardScaler
from sklearn.model_selection import train_test_split, cross_val_score, GridSearchCV
# Set random seed
np.random.seed(0)
# Step 1: Load data
iris = pd.read_csv("iris.csv")
X = iris.drop('species', axis=1)
y = pd.get_dummies(iris['species']).values
# Step 2: Preprocess data
scaler = preprocessing.StandardScaler()
X = scaler.fit_transform(X)
X, y = shuffle(X, y)
X_train, X_test, y_train, y_test = train_test_split(X, y, random_state=0)
network = models.Sequential()
network.add(layers.Dense(units=8, activation="relu", input_shape=(4,)))
network.add(layers.Dense(units=3, activation="softmax"))
# Compile neural network
network.compile(loss="categorical_crossentropy",
optimizer="adam",
metrics=["accuracy"])
# Train neural network
history = network.fit(X_train, # Features
y_train, # Target
epochs= 200,
verbose= 1,
batch_size=10, # Number of observations per batch
validation_data=(X_test, y_test)) # Test data
模型训练得很好,这是最后一个时代:
Epoch 200/200
112/112 [==============================] - 0s 910us/step - loss: 0.0740 - acc: 0.9911 - val_loss: 0.1172 - val_acc: 0.9737
现在,让我们做出一些预测。
new_iris = iris.iloc[0:5, 0:4] # pull out the first five Setosas from original iris dataset;
# prediction should give me Setosa since I am feeding it Setosas
np.around(network.predict(new_iris), decimals = 2) # predicts versicolor with high probability
array([[0. , 0.95, 0.04],
[0. , 0.94, 0.06],
[0. , 0.96, 0.04],
[0. , 0.91, 0.09],
[0. , 0.96, 0.04]], dtype=float32)\
关于为什么会这样的任何想法?
答案 0 :(得分:1)
您需要应用在测试时在培训中学到的转换。
new_iris = iris.iloc[0:5, 0:4] # pull out the first five Setosas from original iris dataset;
new_iris = scaler.transform(new_iris)
np.around(network.predict(new_iris), decimals = 2)
输出
array([[1. , 0. , 0. ],
[0.99, 0.01, 0. ],
[1. , 0. , 0. ],
[0.99, 0.01, 0. ],
[1. , 0. , 0. ]], dtype=float32)