The results after each training keras model are different

I'm a newbie in Machine Learning. I want to build a keras model which will be used for facial recognition. I am currently using the model at:

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',

             input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Conv2D(64, (3, 3), padding='same'))

model.add(Activation('relu'))

model.add(Conv2D(64, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Flatten())

model.add(Dense(512))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(num_classes))

model.add(Activation('softmax'))



# initiate RMSprop optimizer

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)



# Let's train the model using RMSprop

model.compile(loss='categorical_crossentropy',

          optimizer=opt,

           metrics=['accuracy'])

I trained with the same data and parameters the same, but the training results are very different.There are 100% results or 28% results.
What made that difference?

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

1

Each training iteration would cause a weight update in the model. A change in weights would cause the model to perform differently which caused the difference in the training result.

– Edwin
Nov 13 '18 at 9:08

Thank for your suggestion @Edwin

– Pythoner
Nov 13 '18 at 9:18

1

The model is initialized with random weights at the beginning of training, so each time you train, you will arrive at a different local minima, producing different results. This is normal and not a programming problem.

– Matias Valdenegro
Nov 13 '18 at 10:09

add a comment |

I'm a newbie in Machine Learning. I want to build a keras model which will be used for facial recognition. I am currently using the model at:

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',

             input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Conv2D(64, (3, 3), padding='same'))

model.add(Activation('relu'))

model.add(Conv2D(64, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Flatten())

model.add(Dense(512))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(num_classes))

model.add(Activation('softmax'))



# initiate RMSprop optimizer

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)



# Let's train the model using RMSprop

model.compile(loss='categorical_crossentropy',

          optimizer=opt,

           metrics=['accuracy'])

I trained with the same data and parameters the same, but the training results are very different.There are 100% results or 28% results.
What made that difference?

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

1

Each training iteration would cause a weight update in the model. A change in weights would cause the model to perform differently which caused the difference in the training result.

– Edwin
Nov 13 '18 at 9:08

Thank for your suggestion @Edwin

– Pythoner
Nov 13 '18 at 9:18

1

The model is initialized with random weights at the beginning of training, so each time you train, you will arrive at a different local minima, producing different results. This is normal and not a programming problem.

– Matias Valdenegro
Nov 13 '18 at 10:09

add a comment |

I'm a newbie in Machine Learning. I want to build a keras model which will be used for facial recognition. I am currently using the model at:

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',

             input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Conv2D(64, (3, 3), padding='same'))

model.add(Activation('relu'))

model.add(Conv2D(64, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Flatten())

model.add(Dense(512))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(num_classes))

model.add(Activation('softmax'))



# initiate RMSprop optimizer

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)



# Let's train the model using RMSprop

model.compile(loss='categorical_crossentropy',

          optimizer=opt,

           metrics=['accuracy'])

I trained with the same data and parameters the same, but the training results are very different.There are 100% results or 28% results.
What made that difference?

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

I'm a newbie in Machine Learning. I want to build a keras model which will be used for facial recognition. I am currently using the model at:

model = Sequential()

model.add(Conv2D(32, (3, 3), padding='same',

             input_shape=x_train.shape[1:]))

model.add(Activation('relu'))

model.add(Conv2D(32, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Conv2D(64, (3, 3), padding='same'))

model.add(Activation('relu'))

model.add(Conv2D(64, (3, 3)))

model.add(Activation('relu'))

model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Dropout(0.25))



model.add(Flatten())

model.add(Dense(512))

model.add(Activation('relu'))

model.add(Dropout(0.5))

model.add(Dense(num_classes))

model.add(Activation('softmax'))



# initiate RMSprop optimizer

opt = keras.optimizers.rmsprop(lr=0.0001, decay=1e-6)



# Let's train the model using RMSprop

model.compile(loss='categorical_crossentropy',

          optimizer=opt,

           metrics=['accuracy'])

I trained with the same data and parameters the same, but the training results are very different.There are 100% results or 28% results.
What made that difference?

python machine-learning keras

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

edited Nov 13 '18 at 9:13

asked Nov 13 '18 at 9:01

Pythoner

228

asked Nov 13 '18 at 9:01

Pythoner

228

asked Nov 13 '18 at 9:01

Pythoner

228

1

Each training iteration would cause a weight update in the model. A change in weights would cause the model to perform differently which caused the difference in the training result.

– Edwin
Nov 13 '18 at 9:08

Thank for your suggestion @Edwin

– Pythoner
Nov 13 '18 at 9:18

1

The model is initialized with random weights at the beginning of training, so each time you train, you will arrive at a different local minima, producing different results. This is normal and not a programming problem.

– Matias Valdenegro
Nov 13 '18 at 10:09

add a comment |

1

Each training iteration would cause a weight update in the model. A change in weights would cause the model to perform differently which caused the difference in the training result.

– Edwin
Nov 13 '18 at 9:08

Thank for your suggestion @Edwin

– Pythoner
Nov 13 '18 at 9:18

1

The model is initialized with random weights at the beginning of training, so each time you train, you will arrive at a different local minima, producing different results. This is normal and not a programming problem.

– Matias Valdenegro
Nov 13 '18 at 10:09

Each training iteration would cause a weight update in the model. A change in weights would cause the model to perform differently which caused the difference in the training result.

– Edwin
Nov 13 '18 at 9:08

Thank for your suggestion @Edwin

– Pythoner
Nov 13 '18 at 9:18

The model is initialized with random weights at the beginning of training, so each time you train, you will arrive at a different local minima, producing different results. This is normal and not a programming problem.

– Matias Valdenegro
Nov 13 '18 at 10:09

add a comment |

1 Answer
1

active

oldest

votes

Setting the seed, when training the model will solve the problem. This will give you the repeatability.

np.random.seed(10)

tf.set_random_seed(10)

Also make sure train and test split also does not change ever instance. Hence, you can set the seed for data splitting also.

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

1

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

2

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

1

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

add a comment |

Your Answer

StackExchange.ifUsing("editor", function () {
StackExchange.using("externalEditor", function () {
StackExchange.using("snippets", function () {
StackExchange.snippets.init();
});
});
}, "code-snippets");

StackExchange.ready(function() {
var channelOptions = {
tags: "".split(" "),
id: "1"
};
initTagRenderer("".split(" "), "".split(" "), channelOptions);

StackExchange.using("externalEditor", function() {
// Have to fire editor after snippets, if snippets enabled
if (StackExchange.settings.snippets.snippetsEnabled) {
StackExchange.using("snippets", function() {
createEditor();
});
}
else {
createEditor();
}
});

function createEditor() {
StackExchange.prepareEditor({
heartbeatType: 'answer',
autoActivateHeartbeat: false,
convertImagesToLinks: true,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: 10,
bindNavPrevention: true,
postfix: "",
imageUploader: {
brandingHtml: "Powered by u003ca class="icon-imgur-white" href="https://imgur.com/"u003eu003c/au003e",
contentPolicyHtml: "User contributions licensed under u003ca href="https://creativecommons.org/licenses/by-sa/3.0/"u003ecc by-sa 3.0 with attribution requiredu003c/au003e u003ca href="https://stackoverflow.com/legal/content-policy"u003e(content policy)u003c/au003e",
allowUrls: true
},
onDemand: true,
discardSelector: ".discard-answer"
,immediatelyShowMarkdownHelp:true
});

}
});

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

StackExchange.ready(
function () {
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fstackoverflow.com%2fquestions%2f53277246%2fthe-results-after-each-training-keras-model-are-different%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

1 Answer
1

active

oldest

votes

1 Answer
1

active

oldest

votes

Setting the seed, when training the model will solve the problem. This will give you the repeatability.

np.random.seed(10)

tf.set_random_seed(10)

Also make sure train and test split also does not change ever instance. Hence, you can set the seed for data splitting also.

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

1

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

2

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

1

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

add a comment |

Setting the seed, when training the model will solve the problem. This will give you the repeatability.

np.random.seed(10)

tf.set_random_seed(10)

Also make sure train and test split also does not change ever instance. Hence, you can set the seed for data splitting also.

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

1

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

2

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

1

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

add a comment |

Setting the seed, when training the model will solve the problem. This will give you the repeatability.

np.random.seed(10)

tf.set_random_seed(10)

Also make sure train and test split also does not change ever instance. Hence, you can set the seed for data splitting also.

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

Setting the seed, when training the model will solve the problem. This will give you the repeatability.

np.random.seed(10)

tf.set_random_seed(10)

Also make sure train and test split also does not change ever instance. Hence, you can set the seed for data splitting also.

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

edited Nov 13 '18 at 9:22

desertnaut

17.1k63668

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

answered Nov 13 '18 at 9:10

AI_Learning

3,3112933

1

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

2

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

1

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

add a comment |

1

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

2

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

1

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

It seems my knowledge is too little about machine learning. Thanks for your suggesstion @AILearning

– Pythoner
Nov 13 '18 at 9:20

@Pythoner Welcome to SO; if the answer resolved your issue, kindly accept it (see What should I do when someone answers my question?).

– desertnaut
Nov 13 '18 at 9:23

If you do not mind, Can you recommend me a python and keras training model for applying face recognition to reality? The model I was looking for and tried unidentifiable use of my face and it always confused with other people in the data. My data is only three people –

– Pythoner
Nov 13 '18 at 9:26

@desertnaut I'm looking for related theories and try to fix them under suggestions. If this is the answer I will go back and confirm

– Pythoner
Nov 13 '18 at 9:27

pypi.org/project/face_recognition

– AI_Learning
Nov 13 '18 at 9:28

add a comment |

draft saved

draft discarded

Thanks for contributing an answer to Stack Overflow!

Please be sure to answer the question. Provide details and share your research!

But avoid …

Asking for help, clarification, or responding to other answers.

Making statements based on opinion; back them up with references or personal experience.

To learn more, see our tips on writing great answers.

draft saved

draft discarded

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Sign up or log in

StackExchange.ready(function () {
StackExchange.helpers.onClickDraftSave('#login-link');
});

Post as a guest

Name

Required, but never shown

Name

Required, but never shown

Name

Required, but never shown

This page is only for reference, If you need detailed information, please check here

搜尋此網誌

Nrthugu