Trjtdtk

Airbnb - host wants to reduce rooms, can we get refund?

Why is Arya visibly scared in the library in S8E3?

Selecting a secure PIN for building access

555 IC - Transistor Tester

ContentVersion: System.DmlException: Insert failed. STRING_TOO_LONG, Body: data value too large

Independent, post-Brexit Scotland - would there be a hard border with England?

I caught several of my students plagiarizing. Could it be my fault as a teacher?

Ubuntu 19.04 python 3.6 is not working

What are the spoon bit of a spoon and fork bit of a fork called?

Can't remove one character of space in my environment

What is the name of this hexagon/pentagon polyhedron?

Automatically use long arrows in display mode

Limit of this definite integral

What is a "listed natural gas appliance"?

Understanding trademark infringements in a world where many dictionary words are trademarks?

CRT Oscilloscope - part of the plot is missing

I drew a randomly colored grid of points with tikz, how do I force it to remember the first grid from then on?

How wide is a neg symbol, how to get the width for alignment?

How to model the curly cable part of the phone

SQL Server Always On File Share Witness (Quorum vote) on different subnet to other nodes

Moving the subject of the sentence into a dangling participle

Is there a legal ground for stripping the UK of its UN Veto if Scotland and/or N.Ireland split from the UK?

Why wasn't the Night King naked in S08E03?

Upside-Down Pyramid Addition...REVERSED!

ValueError: Tensor Tensor(“activation_5/Softmax:0”, shape=(?, 2), dtype=float32) is not an element of this graph

Tensorflow regression predicting 1 for all inputsKeras LSTM: use weights from Keras model to replicate predictions using numpyVisualizing ConvNet filters using my own fine-tuned network resulting in a “NoneType” when running: K.gradients(loss, model.input)[0]Simple prediction with KerasValueError: Error when checking target: expected dense_2 to have shape (1,) but got array with shape (0,)How to set input for proper fit with lstm?Training Accuracy stuck in KerasValue error in Merging two different models in kerasCannot interpret feed_dict key as Tensor: Tensor Tensor(“Placeholder:0”, shape=(3, 3, 3, 32), dtype=float32) is not an element of this graphWhat is the meaning of ValueError in Keras? - 'Tensor conversion requested dtype complex64 for Tensor with dtype float32'

0

$begingroup$

There seem to be an issue with predicting using my keras model. I had trained it using the following keras code:

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(150, 150,3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(32, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2))
model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

However when i predict it on my local system after training with the shape (1,150,150,3) . It predicts accurately with an accuracy over 90%. however when i load my model on my raspberry pi and input the image of the same shape (1,150,150,3) it returns an error. Below is the code loaded on the raspberry pi to predict from the keras model.

 data = numpy.fromstring(stream.getvalue() , dtype = numpy.uint8)
 image5 = cv.imdecode(data , 1)
 print(image5.shape)
 #cv.imwrite('uhhu.png',image5)
 img = cv.resize(image5,(150,150))
 x = img_to_array(img)
 x = x.reshape((1,) + x.shape)
 x = x/255
 x = numpy.float32(x)
 print(x.shape)
 score = loaded_model.predict(x)
 print(score)

neural-network deep-learning keras

share|improve this question

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

$endgroup$

add a comment | 

0

$begingroup$

There seem to be an issue with predicting using my keras model. I had trained it using the following keras code:

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(150, 150,3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(32, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2))
model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

However when i predict it on my local system after training with the shape (1,150,150,3) . It predicts accurately with an accuracy over 90%. however when i load my model on my raspberry pi and input the image of the same shape (1,150,150,3) it returns an error. Below is the code loaded on the raspberry pi to predict from the keras model.

 data = numpy.fromstring(stream.getvalue() , dtype = numpy.uint8)
 image5 = cv.imdecode(data , 1)
 print(image5.shape)
 #cv.imwrite('uhhu.png',image5)
 img = cv.resize(image5,(150,150))
 x = img_to_array(img)
 x = x.reshape((1,) + x.shape)
 x = x/255
 x = numpy.float32(x)
 print(x.shape)
 score = loaded_model.predict(x)
 print(score)

neural-network deep-learning keras

share|improve this question

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

$endgroup$

add a comment | 

$begingroup$

There seem to be an issue with predicting using my keras model. I had trained it using the following keras code:

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(150, 150,3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(32, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2))
model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

However when i predict it on my local system after training with the shape (1,150,150,3) . It predicts accurately with an accuracy over 90%. however when i load my model on my raspberry pi and input the image of the same shape (1,150,150,3) it returns an error. Below is the code loaded on the raspberry pi to predict from the keras model.

 data = numpy.fromstring(stream.getvalue() , dtype = numpy.uint8)
 image5 = cv.imdecode(data , 1)
 print(image5.shape)
 #cv.imwrite('uhhu.png',image5)
 img = cv.resize(image5,(150,150))
 x = img_to_array(img)
 x = x.reshape((1,) + x.shape)
 x = x/255
 x = numpy.float32(x)
 print(x.shape)
 score = loaded_model.predict(x)
 print(score)

neural-network deep-learning keras

share|improve this question

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

$endgroup$

model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=(150, 150,3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(32, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(64, (3, 3),padding='same'))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Flatten()) # this converts our 3D feature maps to 1D feature vectors
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(2))
model.add(Activation('softmax'))

model.compile(loss='binary_crossentropy',
 optimizer='rmsprop',
 metrics=['accuracy'])

 data = numpy.fromstring(stream.getvalue() , dtype = numpy.uint8)
 image5 = cv.imdecode(data , 1)
 print(image5.shape)
 #cv.imwrite('uhhu.png',image5)
 img = cv.resize(image5,(150,150))
 x = img_to_array(img)
 x = x.reshape((1,) + x.shape)
 x = x/255
 x = numpy.float32(x)
 print(x.shape)
 score = loaded_model.predict(x)
 print(score)

share|improve this question

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

share|improve this question

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

asked Apr 9 at 18:13

Zahid AhmedZahid Ahmed

64

1 Answer
1

active

oldest

votes

0

$begingroup$

The solution to this issue is predict from the keras model when running a tensorflow graph as default.

import tensorflow as tf
graph = tf.get_default_graph()

global graph
with graph.as_default():
 result = loaded_model.predict(x)

share|improve this answer

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

$endgroup$

add a comment | 

Your Answer

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

Name

Email

Required, but never shown

StackExchange.ready(
function ()
StackExchange.openid.initPostLogin('.new-post-login', 'https%3a%2f%2fdatascience.stackexchange.com%2fquestions%2f48984%2fvalueerror-tensor-tensoractivation-5-softmax0-shape-2-dtype-float32%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

$begingroup$

The solution to this issue is predict from the keras model when running a tensorflow graph as default.

import tensorflow as tf
graph = tf.get_default_graph()

global graph
with graph.as_default():
 result = loaded_model.predict(x)

share|improve this answer

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

$endgroup$

add a comment | 

0

$begingroup$

The solution to this issue is predict from the keras model when running a tensorflow graph as default.

import tensorflow as tf
graph = tf.get_default_graph()

global graph
with graph.as_default():
 result = loaded_model.predict(x)

share|improve this answer

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

$endgroup$

add a comment | 

$begingroup$

The solution to this issue is predict from the keras model when running a tensorflow graph as default.

import tensorflow as tf
graph = tf.get_default_graph()

global graph
with graph.as_default():
 result = loaded_model.predict(x)

share|improve this answer

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

$endgroup$

import tensorflow as tf
graph = tf.get_default_graph()

global graph
with graph.as_default():
 result = loaded_model.predict(x)

share|improve this answer

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64

answered Apr 10 at 7:30

Zahid AhmedZahid Ahmed

64