Question

我正在尝试对神经网络中的多类问题进行网格搜索。我无法获得最佳参数，内核继续编译。我的代码有问题吗？请帮忙

import keras

from keras.models import Sequential
from keras.layers import Dense

# defining the baseline model:

def neural(output_dim=10,init_mode='glorot_uniform'):
    model = Sequential()
    model.add(Dense(output_dim=output_dim,
                    input_dim=2,
                    activation='relu',
                    kernel_initializer= init_mode))
    model.add(Dense(output_dim=output_dim,
                    activation='relu',
                    kernel_initializer= init_mode))
    model.add(Dense(output_dim=3,activation='softmax'))

    # Compile model
    model.compile(loss='sparse_categorical_crossentropy', 
                  optimizer='adam', 
                  metrics=['accuracy'])
    return model

from keras.wrappers.scikit_learn import KerasClassifier
from sklearn.model_selection import cross_val_score
from sklearn.model_selection import KFold
from sklearn.model_selection import GridSearchCV
estimator = KerasClassifier(build_fn=neural, 
                            epochs=5, 
                            batch_size=5, 
                            verbose=0)

# define the grid search parameters
batch_size = [10, 20, 40, 60, 80, 100]
epochs = [10, 50, 100]
init_mode = ['uniform', 'lecun_uniform', 'normal', 'zero', 
             'glorot_normal', 'glorot_uniform', 'he_normal', 'he_uniform']
output_dim = [10, 15, 20, 25, 30,40]

param_grid = dict(batch_size=batch_size, 
                  epochs=epochs,
                  output_dim=output_dim,
                  init_mode=init_mode)

grid = GridSearchCV(estimator=estimator, 
                    scoring= 'accuracy',
                    param_grid=param_grid, 
                    n_jobs=-1,cv=5)

grid_result = grid.fit(X_train, Y_train)

# summarize results

print("Best: %f using %s" % (grid_result.best_score_, 
                             grid_result.best_params_))
means = grid_result.cv_results_['mean_test_score']
stds = grid_result.cv_results_['std_test_score']
params = grid_result.cv_results_['params']
for mean, stdev, param in zip(means, stds, params):
    print("%f (%f) with: %r" % (mean, stdev, param))

Answer 1

您的代码中没有错误。

您当前的参数网格有864种不同的参数组合。

（'batch_size'中的'epochs'×3值'init_mode'×8 'output_dim'×6 cv=5中的6个值= 864

GridSearchCV将迭代所有这些可能性，您的估算器将被多次克隆。由于您已设置verbose，因此再次重复5次。

因此，您的模型将被克隆（编译并根据可能性设置参数）总共864 x 5 = 4320次。

因此，您会在输出中看到模型正在多次编译。

要检查GridSearchCV是否正常工作，请使用其grid = GridSearchCV(estimator=estimator, scoring= 'accuracy', param_grid=param_grid, n_jobs=1,cv=5, verbose=3)参数。

    import mysql.connector
    import sys
    from PIL import Image
    import base64
    import six
    import io
    import PIL.Image
    import pymysql

    from flask import Flask,render_template,request,flash
    app=Flask(__name__)
    app.secret_key = 'dont tell anyone'

    @app.route('/')
    def index():
        db = mysql.connector.connect(user='root', password='tejA@1612',
                                      host='localhost',
                                      database='students')
        #photo = request.form['inputFile']
        image = Image.open('statics/rohan2.jpg')
        blob_value = open('statics/rohan2.jpg', 'rb').read()
        sql = 'INSERT INTO images(photo) VALUES(%s)'
        args = (blob_value, )
        cursor=db.cursor()
        cursor.execute(sql,args)
        sql1='select photo from images'
        db.commit()
        cursor.execute(sql1)
        data=cursor.fetchall()
        #print type(data[0][0])
        file_like=io.BytesIO(data[0][0])
        img=PIL.Image.open(file_like)
        #img.show()
        db.close()
        return render_template("home.html",result=img)
    if __name__=="__main__":
        app.run(debug=True)

这将打印当前可能尝试的参数，cv迭代，适合它的时间，当前准确度等。

基于神经网络的多类分类问题中的网格搜索

1 个答案: