Kaggle---DigitRecognizer（数字识别）

最新推荐文章于 2022-04-30 10:42:34 发布

shichao2018

最新推荐文章于 2022-04-30 10:42:34 发布

阅读量5.2k

点赞数 1

分类专栏： Competition 文章标签： kaggle keras 数字识别 python 计算机视觉

本文链接：https://blog.csdn.net/weixin_40241703/article/details/81001277

版权

Introduction to CNN Keras - 0.997 (top 10%)

数字识别这是kaggle上入门的一道经典题目，最近准备做计算机视觉，所以也是学习了一下，代码供参考。最后取得了0。997的成绩。首次进入kaggle的Top 10%。

import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import seaborn as sns

np.random.seed(2)
from sklearn.model_selection import train_test_split
from sklearn.metrics import confusion_matrix
import itertools
from keras.utils.np_utils import to_categorical #convert to one-hot-encoding
from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPool2D
from keras.optimizers import RMSprop
from keras.preprocessing.image import ImageDataGenerator
from keras.callbacks import ReduceLROnPlateau

# Load the data
train = pd.read_csv("./data/train.csv")
test = pd.read_csv("./data/test.csv")
Y_train = train["label"]
# Drop 'label' column
X_train = train.drop(labels = ['label'],axis=1)
del train
g = sns.countplot(Y_train)
Y_train.value_counts()
# Check the data
X_train.isnull().any().describe()
test.isnull().any().describe()
# Normalize the data
X_train = X_train / 255.0
test = test / 255.0
# Reshape image in 3 dimensions (height = 28px, width = 28px, canal = 1)
X_train = X_train.values.reshape(-1, 28, 28, 1)
test = test.values.reshape(-1, 28, 28, 1)
# Encode labels to one hot vectors (ex: 2 -> [0,0,1,0,0,0,0,0,0,0])
Y_train = to_categorical(Y_train, num_classes=10)
# Set the r