What is the problem with this architecture ? I am getting error negative dimensions. I want to avoid dense layers and dropouts The Next CEO of Stack Overflow2019 Community Moderator Electioncounting number of parameters kerasValueError: Error when checking target: expected dense_2 to have shape (1,) but got array with shape (0,)Recreating ResNet50Padding in Keras with output half sized inputTraining Accuracy stuck in KerasHow to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?Value error in Merging two different models in kerasQuery regarding (.output_shape) parameters used in CNN modelSteps taking too long to completeNumpy Python deep learning framework
Complex fractions
Science fiction short story involving a paper written by a schizophrenic
Rotate a column
Would this house-rule that treats advantage as a +1 to the roll instead (and disadvantage as -1) and allows them to stack be balanced?
How to make a variable always equal to the result of some calculations?
Why didn't Theresa May consult with Parliament before negotiating a deal with the EU?
How to be diplomatic in refusing to write code that breaches the privacy of our users
Is there a way to save my career from absolute disaster?
Can the Reverse Gravity spell affect the Meteor Swarm spell?
If the heap is initialized for security, then why is the stack uninitialized?
What happens if you roll doubles 3 times then land on "Go to jail?"
Does it take more energy to get to Venus or to Mars?
How do I construct this japanese bowl?
Extracting names from filename in bash
How do you know when two objects are so called entangled?
Oh, one short ode of love
Shade part of a Venn diagram
Why is there a PLL in CPU?
Inappropriate reference requests from Journal reviewers
If Nick Fury and Coulson already knew about aliens (Kree and Skrull) why did they wait until Thor's appearance to start making weapons?
How to make a software documentation "officially" citable?
How should I support this large drywall patch?
Is a stroke of luck acceptable after a series of unfavorable events?
How do we know the LHC results are robust?
What is the problem with this architecture ? I am getting error negative dimensions. I want to avoid dense layers and dropouts
The Next CEO of Stack Overflow2019 Community Moderator Electioncounting number of parameters kerasValueError: Error when checking target: expected dense_2 to have shape (1,) but got array with shape (0,)Recreating ResNet50Padding in Keras with output half sized inputTraining Accuracy stuck in KerasHow to use LeakyRelu as activation function in sequence DNN in keras?When it perfoms better than Relu?Value error in Merging two different models in kerasQuery regarding (.output_shape) parameters used in CNN modelSteps taking too long to completeNumpy Python deep learning framework
2
$begingroup$
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
machine-learning neural-network deep-learning
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
$endgroup$
add a comment |
2
$begingroup$
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
machine-learning neural-network deep-learning
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
$endgroup$
add a comment |
2
2
2
$begingroup$
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
machine-learning neural-network deep-learning
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
$endgroup$
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
machine-learning neural-network deep-learning
machine-learning neural-network deep-learning
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
edited Mar 22 at 12:31
Vipul Gaurav
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
asked Mar 22 at 12:28
Vipul GauravVipul Gaurav
113
113
add a comment |
add a comment |
1 Answer
1
active
oldest
votes
2
$begingroup$
You are using too many layers and you run out of spatial space.
Most of your convolutional layers use "valid" padding, meaning that the convolution is performed only on actual "pixels" without any padding and as a result the spatial dimensions of the output are smaller than the input.
I've marked down where it happens in your script:
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.summary() # This is where it happens - The output of this layer is of shape (1,1,128)
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
You can use the Keras "summary" method to investigate your model. For example, the output from the script I've written here is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 64, 64, 64) 256
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 102464
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 15, 15, 64) 4160
_________________________________________________________________
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
_________________________________________________________________
conv2d_5 (Conv2D) (None, 13, 13, 64) 4160
_________________________________________________________________
conv2d_6 (Conv2D) (None, 11, 11, 64) 36928
_________________________________________________________________
conv2d_7 (Conv2D) (None, 11, 11, 64) 4160
_________________________________________________________________
conv2d_8 (Conv2D) (None, 9, 9, 64) 36928
_________________________________________________________________
conv2d_9 (Conv2D) (None, 5, 5, 128) 8320
_________________________________________________________________
conv2d_10 (Conv2D) (None, 3, 3, 128) 147584
_________________________________________________________________
conv2d_11 (Conv2D) (None, 3, 3, 128) 16512
_________________________________________________________________
conv2d_12 (Conv2D) (None, 1, 1, 128) 147584
_________________________________________________________________
conv2d_13 (Conv2D) (None, 1, 1, 128) 16512
=================================================================
Total params: 562,496
Trainable params: 562,496
Non-trainable params: 0
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
$endgroup$
add a comment |
Your Answer
StackExchange.ifUsing("editor", function ()
return StackExchange.using("mathjaxEditing", function ()
StackExchange.MarkdownEditor.creationCallbacks.add(function (editor, postfix)
StackExchange.mathjaxEditing.prepareWmdForMathJax(editor, postfix, [["$", "$"], ["\\(","\\)"]]);
);
);
, "mathjax-editing");
StackExchange.ready(function()
var channelOptions =
tags: "".split(" "),
id: "557"
;
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: false,
noModals: true,
showLowRepImageUploadWarning: true,
reputationToPostImages: null,
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');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47784%2fwhat-is-the-problem-with-this-architecture-i-am-getting-error-negative-dimensi%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
1 Answer
1
active
oldest
votes
1 Answer
1
active
oldest
votes
active
oldest
votes
active
oldest
votes
2
$begingroup$
You are using too many layers and you run out of spatial space.
Most of your convolutional layers use "valid" padding, meaning that the convolution is performed only on actual "pixels" without any padding and as a result the spatial dimensions of the output are smaller than the input.
I've marked down where it happens in your script:
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.summary() # This is where it happens - The output of this layer is of shape (1,1,128)
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
You can use the Keras "summary" method to investigate your model. For example, the output from the script I've written here is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 64, 64, 64) 256
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 102464
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 15, 15, 64) 4160
_________________________________________________________________
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
_________________________________________________________________
conv2d_5 (Conv2D) (None, 13, 13, 64) 4160
_________________________________________________________________
conv2d_6 (Conv2D) (None, 11, 11, 64) 36928
_________________________________________________________________
conv2d_7 (Conv2D) (None, 11, 11, 64) 4160
_________________________________________________________________
conv2d_8 (Conv2D) (None, 9, 9, 64) 36928
_________________________________________________________________
conv2d_9 (Conv2D) (None, 5, 5, 128) 8320
_________________________________________________________________
conv2d_10 (Conv2D) (None, 3, 3, 128) 147584
_________________________________________________________________
conv2d_11 (Conv2D) (None, 3, 3, 128) 16512
_________________________________________________________________
conv2d_12 (Conv2D) (None, 1, 1, 128) 147584
_________________________________________________________________
conv2d_13 (Conv2D) (None, 1, 1, 128) 16512
=================================================================
Total params: 562,496
Trainable params: 562,496
Non-trainable params: 0
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
$endgroup$
add a comment |
2
$begingroup$
You are using too many layers and you run out of spatial space.
Most of your convolutional layers use "valid" padding, meaning that the convolution is performed only on actual "pixels" without any padding and as a result the spatial dimensions of the output are smaller than the input.
I've marked down where it happens in your script:
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.summary() # This is where it happens - The output of this layer is of shape (1,1,128)
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
You can use the Keras "summary" method to investigate your model. For example, the output from the script I've written here is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 64, 64, 64) 256
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 102464
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 15, 15, 64) 4160
_________________________________________________________________
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
_________________________________________________________________
conv2d_5 (Conv2D) (None, 13, 13, 64) 4160
_________________________________________________________________
conv2d_6 (Conv2D) (None, 11, 11, 64) 36928
_________________________________________________________________
conv2d_7 (Conv2D) (None, 11, 11, 64) 4160
_________________________________________________________________
conv2d_8 (Conv2D) (None, 9, 9, 64) 36928
_________________________________________________________________
conv2d_9 (Conv2D) (None, 5, 5, 128) 8320
_________________________________________________________________
conv2d_10 (Conv2D) (None, 3, 3, 128) 147584
_________________________________________________________________
conv2d_11 (Conv2D) (None, 3, 3, 128) 16512
_________________________________________________________________
conv2d_12 (Conv2D) (None, 1, 1, 128) 147584
_________________________________________________________________
conv2d_13 (Conv2D) (None, 1, 1, 128) 16512
=================================================================
Total params: 562,496
Trainable params: 562,496
Non-trainable params: 0
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
$endgroup$
add a comment |
2
2
2
$begingroup$
You are using too many layers and you run out of spatial space.
Most of your convolutional layers use "valid" padding, meaning that the convolution is performed only on actual "pixels" without any padding and as a result the spatial dimensions of the output are smaller than the input.
I've marked down where it happens in your script:
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.summary() # This is where it happens - The output of this layer is of shape (1,1,128)
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
You can use the Keras "summary" method to investigate your model. For example, the output from the script I've written here is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 64, 64, 64) 256
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 102464
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 15, 15, 64) 4160
_________________________________________________________________
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
_________________________________________________________________
conv2d_5 (Conv2D) (None, 13, 13, 64) 4160
_________________________________________________________________
conv2d_6 (Conv2D) (None, 11, 11, 64) 36928
_________________________________________________________________
conv2d_7 (Conv2D) (None, 11, 11, 64) 4160
_________________________________________________________________
conv2d_8 (Conv2D) (None, 9, 9, 64) 36928
_________________________________________________________________
conv2d_9 (Conv2D) (None, 5, 5, 128) 8320
_________________________________________________________________
conv2d_10 (Conv2D) (None, 3, 3, 128) 147584
_________________________________________________________________
conv2d_11 (Conv2D) (None, 3, 3, 128) 16512
_________________________________________________________________
conv2d_12 (Conv2D) (None, 1, 1, 128) 147584
_________________________________________________________________
conv2d_13 (Conv2D) (None, 1, 1, 128) 16512
=================================================================
Total params: 562,496
Trainable params: 562,496
Non-trainable params: 0
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
$endgroup$
You are using too many layers and you run out of spatial space.
Most of your convolutional layers use "valid" padding, meaning that the convolution is performed only on actual "pixels" without any padding and as a result the spatial dimensions of the output are smaller than the input.
I've marked down where it happens in your script:
model = Sequential()
model.add(Conv2D(64, (1, 1), activation='relu', input_shape=(64,64,3)))
model.add(Conv2D(64, (5,5), strides=(2,2), padding='same'))
model.add(MaxPooling2D(pool_size=3, strides=(2,2)))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(64, (3, 3),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (1,1),
strides=(2,2),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1, 1),
strides=(1,1),
activation='relu',
padding='valid' ))
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.summary() # This is where it happens - The output of this layer is of shape (1,1,128)
model.add(Conv2D(128, (3,3),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (1,1),
strides=(1,1),
activation='relu',
padding='valid'))
model.add(Conv2D(128, (3,3),
strides=(1,1),
padding='valid'))
model.add(AveragePooling2D(pool_size=2, strides=(2,2), padding='valid'))
model.add(Conv2D(1,1,200))
model.add(Flatten())
model.add(Activation('softmax'))
You can use the Keras "summary" method to investigate your model. For example, the output from the script I've written here is:
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 64, 64, 64) 256
_________________________________________________________________
conv2d_2 (Conv2D) (None, 32, 32, 64) 102464
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 15, 15, 64) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 15, 15, 64) 4160
_________________________________________________________________
conv2d_4 (Conv2D) (None, 13, 13, 64) 36928
_________________________________________________________________
conv2d_5 (Conv2D) (None, 13, 13, 64) 4160
_________________________________________________________________
conv2d_6 (Conv2D) (None, 11, 11, 64) 36928
_________________________________________________________________
conv2d_7 (Conv2D) (None, 11, 11, 64) 4160
_________________________________________________________________
conv2d_8 (Conv2D) (None, 9, 9, 64) 36928
_________________________________________________________________
conv2d_9 (Conv2D) (None, 5, 5, 128) 8320
_________________________________________________________________
conv2d_10 (Conv2D) (None, 3, 3, 128) 147584
_________________________________________________________________
conv2d_11 (Conv2D) (None, 3, 3, 128) 16512
_________________________________________________________________
conv2d_12 (Conv2D) (None, 1, 1, 128) 147584
_________________________________________________________________
conv2d_13 (Conv2D) (None, 1, 1, 128) 16512
=================================================================
Total params: 562,496
Trainable params: 562,496
Non-trainable params: 0
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
answered Mar 22 at 13:10
Mark.FMark.F
1,0241421
1,0241421
add a comment |
add a comment |
draft saved
draft discarded
Thanks for contributing an answer to Data Science Stack Exchange!
- 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.
Use MathJax to format equations. MathJax reference.
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');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f47784%2fwhat-is-the-problem-with-this-architecture-i-am-getting-error-negative-dimensi%23new-answer', 'question_page');
);
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Sign up or log in
StackExchange.ready(function ()
StackExchange.helpers.onClickDraftSave('#login-link');
);
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Sign up using Google
Sign up using Facebook
Sign up using Email and Password
Post as a guest
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
Required, but never shown
