Kaggle_Digit Recognizer_MLP

最新推荐文章于 2022-08-12 18:00:36 发布

sunny0660

最新推荐文章于 2022-08-12 18:00:36 发布

阅读量251

点赞数

分类专栏：深度学习 # tutorial

本文链接：https://blog.youkuaiyun.com/sunny0660/article/details/104078682

版权

深度学习同时被 2 个专栏收录

13 篇文章

订阅专栏

tutorial

4 篇文章

订阅专栏

本文介绍了一个使用多层感知器（MLP）解决Kaggle数字识别竞赛的案例。通过预处理MNIST数据集，构建了一个包含两层隐藏层的神经网络模型，并使用RMSprop优化器训练模型。最终，模型在测试数据上生成了预测结果。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

Kaggle-Digit Recognizer-MLP

date:2019-01-22

参考网页

from keras.models import Sequential
from keras.utils import np_utils
from keras.layers.core import Dense, Activation, Dropout

import pandas as pd
import numpy as np

# Read data
train = pd.read_csv('../input/train.csv')
labels = train.ix[:,0].values.astype('int32')
X_train = (train.ix[:,1:].values).astype('float32')
X_test = (pd.read_csv('../input/test.csv').values).astype('float32')

Using TensorFlow backend.
/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py:10: DeprecationWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated
  # Remove the CWD from sys.path while we load stuff.
/usr/local/lib/python3.5/dist-packages/ipykernel_launcher.py:11: DeprecationWarning: 
.ix is deprecated. Please use
.loc for label based indexing or
.iloc for positional indexing

See the documentation here:
http://pandas.pydata.org/pandas-docs/stable/indexing.html#ix-indexer-is-deprecated
  # This is added back by InteractiveShellApp.init_path()

# convert list of labels to binary class matrix
y_train = np_utils.to_categorical(labels)

# pre-processing: divide by max and substract mean
scale = np.max(X_train)
X_train /= scale
X_test /= scale

mean = np.std(X_train)
X_train -= mean
X_test -= mean

input_dim = X_train.shape[1]
nb_classes = y_train.shape[1]

# Here's a Deep Dumb MLP (DDMLP)
model = Sequential()
model.add(Dense(128, input_dim=input_dim))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(128))
model.add(Activation('relu'))
model.add(Dropout(0.15))
model.add(Dense(nb_classes))
model.add(Activation('softmax'))

# We'll use categorical xent for the loss, and RMSprop as the optimizer
model.compile(loss='categorical_crossentropy', optimizer='rmsprop')

print("Training...")
model.fit(X_train, y_train, epochs=10, batch_size=16, validation_split=0.1, verbose=2)

print("Generating test predictions...")
preds = model.predict_classes(X_test, verbose=0)

def write_preds(preds, fname):
    pd.DataFrame({"ImageId":list(range(1, len(preds)+1)), "Label": preds}).to_csv(fname, index=False, header=True)
    
write_preds(preds, "keras-mlp.csv")

Training...
Train on 37800 samples, validate on 4200 samples
Epoch 1/10
 - 24s - loss: 0.3679 - val_loss: 0.2058
Epoch 2/10
 - 15s - loss: 0.2157 - val_loss: 0.1467
Epoch 3/10
 - 20s - loss: 0.1933 - val_loss: 0.1564
Epoch 4/10
 - 19s - loss: 0.1848 - val_loss: 0.1784
Epoch 5/10
 - 14s - loss: 0.1876 - val_loss: 0.1773
Epoch 6/10
 - 14s - loss: 0.1834 - val_loss: 0.1741
Epoch 7/10
 - 14s - loss: 0.1939 - val_loss: 0.1845
Epoch 8/10
 - 14s - loss: 0.1859 - val_loss: 0.1918
Epoch 9/10
 - 14s - loss: 0.1914 - val_loss: 0.2041
Epoch 10/10
 - 14s - loss: 0.2000 - val_loss: 0.2004
Generating test predictions...