我已阅读此示例 https://github.com/fchollet/keras/blob/master/examples/mnist_mlp.py并决定将这个想法应用到我的基础上,因为这是 Keras 最简单的神经网络。
这是我的基地https://drive.google.com/file/d/0B-B3QUQOzGZ7WVhzQmRsOTB0eFE/view (你可以下载我的csv文件,它只有83Kb)
基础形状 = (891, 23)
import keras
from keras.datasets import mnist
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.optimizers import RMSprop, Adam
import numpy as np
import pandas as pd
from sklearn.cross_validation import train_test_split
from keras.utils.vis_utils import model_to_dot
from IPython.display import SVG
from keras.utils import plot_model
base = pd.read_csv("mt.csv")
import pandas as pd
for col in base:
if col != "Fare" and col != "Age":
base[col]=base[col].astype(float)
X_train = base
y_train = base["Survived"]
del X_train["Survived"]
print("X_train=",X_train.shape)
print("y_train=", y_train.shape)
输出: X_train= (891, 22) y_train=(891,)
from sklearn.cross_validation import train_test_split
X_train, X_test , y_train, y_test = train_test_split(X_train, y_train, test_size=0.3, random_state=42)
batch_size = 4
num_classes = 2
epochs = 2
print(X_train.shape[1], 'train samples')
print(X_test.shape[1], 'test samples')
输出: 22 个训练样本 22个测试样本
y_train = keras.utils.to_categorical(y_train, num_classes)
y_test = keras.utils.to_categorical(y_test, num_classes)
model = Sequential()
model.add(Dense(40, activation='relu', input_shape=(21,)))
model.add(Dropout(0.2))
#model.add(Dense(20, activation='relu'))
#odel.add(Dropout(0.2))
model.add(Dense(2, activation='sigmoid'))
model.summary()
输出:
图层(类型)输出形状参数
dense_1(密集)(无,40)880
dropout_1(辍学)(无,40)0
dense_2(密集)(无,2)82
model.compile(loss='binary_crossentropy',
optimizer=Adam(),
metrics=['accuracy'])
plot_model(model, to_file='model.png')
SVG(model_to_dot(model).create(prog='dot', format='svg'))
print("X_train.shape=", X_train.shape)
print("X_test=",X_test.shape)
history = model.fit(X_train, y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_test, y_test))
回溯(最近一次调用最后一次): 文件“new.py”,第 67 行,位于 validation_data=(X_test, y_test))
文件“miniconda3/lib/python3.6/site-packages/keras/models.py”,第845行,适合 初始纪元=初始纪元)
文件“miniconda3/lib/python3.6/site-packages/keras/engine/training.py”,第 1405 行,适合 批量大小=批量大小)
文件“miniconda3/lib/python3.6/site-packages/keras/engine/training.py”,第 1295 行,位于 _standardize_user_data exception_prefix='模型输入')
文件“miniconda3/lib/python3.6/site-packages/keras/engine/training.py”,第 133 行,位于 _standardize_input_data str(数组.shape))
ValueError:检查模型输入时出错:预期密集_1_输入具有形状(无,21),但得到形状为(623,22)的数组 [在 5.1 秒内完成,退出代码为 1]
如何解决此错误?我尝试更改输入形状,例如更改为 (20,) 或 (22,) 等,但没有成功。
例如,如果 input_shape=(22,) 我遇到错误:File "miniconda3/lib/python3.6/site-packages/pandas/core/indexing.py", line 1873, in Maybe_convert_indices raise IndexError("索引越界")
最佳答案
input_shape
应与数据中的特征数量相同,并且在您的情况下应为 input_shape=(22,)
。
IndexError
是由于 pandas 数据帧中的一些不同索引造成的,因此使用 as_matrix()
将数据帧转换为 numpy 矩阵:
history = model.fit(X_train.as_matrix(), y_train,
batch_size=batch_size,
epochs=epochs,
verbose=1,
validation_data=(X_test.as_matrix(), y_test))
关于python - Keras 最简单的 NN 模型 : error in training. py 带索引,我们在Stack Overflow上找到一个类似的问题: https://stackoverflow.com/questions/43293832/