Keras. VGG16 training

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty{ height:90px;width:728px;box-sizing:border-box;
}

I fit model from keras (VGG16) without top layers (I create my top layers and add in sequential). I set VGG16 layers as non-trainable and fit my model with checkpoint save.

vgg16_net.trainable = False



model = Sequential()



model.add(vgg16_net)

model.add(Flatten())

model.add(Dense(1024, activation='relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation=softmax, name='predictions'))

checkpointer = ModelCheckpoint(monitor='val_acc',filepath='Keras_VGG16_Best_Weights.hpf5', verbose=1, save_best_only=True)

In continue, when I fit this top layers, I want to fit last conv layers:

i = 1

for layers in VGG16_net.layers:

    if i <= 15:

        layers.trainable = False

    else:

        layers.trainable = True

    i += 1



model = Sequential()



model.add(VGG16_net)

model.add(Flatten())

model.add(Dense(1024, activation = 'relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation = softmax, name = 'predictions'))

And save_weights from old model and load trained weights to new model

model.load_weights('only_weights_VGG116.h5')

But I have error

Cannot feed value of shape (64, 3, 3, 3) for Tensor 'Placeholder_20:0', which has shape '(3, 3, 512, 512)'

I understand, that with error connect with trainable position in VGG16, but I don't now how fix this. If I set VGG16 all layers as non-trainable than load is succesfull. Help me please, I want to load this weights in my new model for train last conv layers. If this impossible, please, write this. Sorry for my English!)

asked Jan 3 at 13:05

Артем Дагаев

add a comment |

I fit model from keras (VGG16) without top layers (I create my top layers and add in sequential). I set VGG16 layers as non-trainable and fit my model with checkpoint save.

vgg16_net.trainable = False



model = Sequential()



model.add(vgg16_net)

model.add(Flatten())

model.add(Dense(1024, activation='relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation=softmax, name='predictions'))

checkpointer = ModelCheckpoint(monitor='val_acc',filepath='Keras_VGG16_Best_Weights.hpf5', verbose=1, save_best_only=True)

In continue, when I fit this top layers, I want to fit last conv layers:

i = 1

for layers in VGG16_net.layers:

    if i <= 15:

        layers.trainable = False

    else:

        layers.trainable = True

    i += 1



model = Sequential()



model.add(VGG16_net)

model.add(Flatten())

model.add(Dense(1024, activation = 'relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation = softmax, name = 'predictions'))

And save_weights from old model and load trained weights to new model

model.load_weights('only_weights_VGG116.h5')

But I have error

Cannot feed value of shape (64, 3, 3, 3) for Tensor 'Placeholder_20:0', which has shape '(3, 3, 512, 512)'

asked Jan 3 at 13:05

Артем Дагаев

add a comment |

I fit model from keras (VGG16) without top layers (I create my top layers and add in sequential). I set VGG16 layers as non-trainable and fit my model with checkpoint save.

vgg16_net.trainable = False



model = Sequential()



model.add(vgg16_net)

model.add(Flatten())

model.add(Dense(1024, activation='relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation=softmax, name='predictions'))

checkpointer = ModelCheckpoint(monitor='val_acc',filepath='Keras_VGG16_Best_Weights.hpf5', verbose=1, save_best_only=True)

In continue, when I fit this top layers, I want to fit last conv layers:

i = 1

for layers in VGG16_net.layers:

    if i <= 15:

        layers.trainable = False

    else:

        layers.trainable = True

    i += 1



model = Sequential()



model.add(VGG16_net)

model.add(Flatten())

model.add(Dense(1024, activation = 'relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation = softmax, name = 'predictions'))

And save_weights from old model and load trained weights to new model

model.load_weights('only_weights_VGG116.h5')

But I have error

Cannot feed value of shape (64, 3, 3, 3) for Tensor 'Placeholder_20:0', which has shape '(3, 3, 512, 512)'

asked Jan 3 at 13:05

Артем Дагаев

I fit model from keras (VGG16) without top layers (I create my top layers and add in sequential). I set VGG16 layers as non-trainable and fit my model with checkpoint save.

vgg16_net.trainable = False



model = Sequential()



model.add(vgg16_net)

model.add(Flatten())

model.add(Dense(1024, activation='relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation=softmax, name='predictions'))

checkpointer = ModelCheckpoint(monitor='val_acc',filepath='Keras_VGG16_Best_Weights.hpf5', verbose=1, save_best_only=True)

In continue, when I fit this top layers, I want to fit last conv layers:

i = 1

for layers in VGG16_net.layers:

    if i <= 15:

        layers.trainable = False

    else:

        layers.trainable = True

    i += 1



model = Sequential()



model.add(VGG16_net)

model.add(Flatten())

model.add(Dense(1024, activation = 'relu'))

model.add(Dropout(0.5))

model.add(Dense(5, activation = softmax, name = 'predictions'))

And save_weights from old model and load trained weights to new model

model.load_weights('only_weights_VGG116.h5')

But I have error

Cannot feed value of shape (64, 3, 3, 3) for Tensor 'Placeholder_20:0', which has shape '(3, 3, 512, 512)'

python tensorflow keras deep-learning

asked Jan 3 at 13:05

Артем Дагаев

asked Jan 3 at 13:05

Артем Дагаев

asked Jan 3 at 13:05

Артем Дагаев

asked Jan 3 at 13:05

Артем Дагаев

asked Jan 3 at 13:05

Артем Дагаев

add a comment |

0

active

oldest

votes

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%2f54022893%2fkeras-vgg16-training%23new-answer', 'question_page');
}
);

Post as a guest

Name

Required, but never shown

0

active

oldest

votes

0

active

oldest

votes

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

Search This Blog

Ufyukyu