Styjun

Generic method to call API functions with simple retrial on errors

Create a list of snaking numbers under 50,000

Are spot colors limited and why CMYK mix is not treated same as spot color mix?

Why is there not a willingness from the world to step in between Pakistan and India?

How to determine the convexity of my problem and categorize it?

Convert shapefille to KML

Is it alright to add scenes that don’t move the plot forwards much but develop relationships/character?

How do I portray irrational anger in first person?

How can I fix cracks between the bathtub and the wall surround?

Which polygons can be turned inside out by a smooth deformation?

What is the sound/audio equivalent of "unsightly"?

Defending Castle from Zombies

Is there a word or phrase that means "use other people's wifi or Internet service without consent"?

Wrong Stamping of UK Visa

Scaling arrows.meta with tranform shape

How can I throw a body?

Is "survival" paracord with fire starter strand dangerous

Moscow SVO airport, how to avoid scam taxis without pre-booking?

Did the Apollo Guidance Computer really use 60% of the world's ICs in 1963?

Under GDPR, can I give permission once to allow everyone to store and process my data?

How can weighted averages be calculated for a Dataset summarized with GroupBy

Why does `buck` mean `step-down`?

Why is "I let him to sleep" incorrect (or is it)?

How to save money by shopping at a variety of grocery stores?

Is there a way to assign the input of a Python Tensorflow Keras model to a variable?

TensorFlow You must feed a value for placeholder tensor 'Placeholder_2' with dtype floattflearn throws invalid argument error in CNN trainingProviding output from one model to another modeltensor flow input variable errorWhat is the simplest way of deploying a Keras/Tensorflow CNN available as .model .json and .h5 on Google ML Engine?couldn't run embedding network Keras with multiplue inputTensorflow 1.10 with python 3.5.6( InvalidArgumentError: You must feed a value for placeholder tensor 'input_8/InputX' with dtype float)How to implement a custom loss function including GAN generator in Keras?

.everyoneloves__top-leaderboard:empty,.everyoneloves__mid-leaderboard:empty,.everyoneloves__bot-mid-leaderboard:empty margin-bottom:0;

0

I'm building a Keras model and I have defined a class containing it. I need to "store" the input of the model in something like self.stored_input = input_of_the_model

I'm using Python 3.6.7, Tensorflow 2.1.6 and Keras 2.2.4 I've done a tentative but without good results. This is what I do:

'''

class AutoEncoder:
def init(self, input_shape=[224, 224]):

 self.models_dir = '../model'


 # Input
 img = Input(shape=(224, 224, 1))

 ..... Convolutional neural network layers here.....

 self.img = img

'''

I want to use self.img in a function of the class AutoEncoder but I obtain this error when I use it:

InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,224,224,1]
[[node input_1 = Placeholderdtype=DT_FLOAT, shape=[?,224,224,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

python-3.x tensorflow neural-network conv-neural-network tf.keras

share|improve this question

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

add a comment | 

0

I'm building a Keras model and I have defined a class containing it. I need to "store" the input of the model in something like self.stored_input = input_of_the_model

I'm using Python 3.6.7, Tensorflow 2.1.6 and Keras 2.2.4 I've done a tentative but without good results. This is what I do:

'''

class AutoEncoder:
def init(self, input_shape=[224, 224]):

 self.models_dir = '../model'


 # Input
 img = Input(shape=(224, 224, 1))

 ..... Convolutional neural network layers here.....

 self.img = img

'''

I want to use self.img in a function of the class AutoEncoder but I obtain this error when I use it:

InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,224,224,1]
[[node input_1 = Placeholderdtype=DT_FLOAT, shape=[?,224,224,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

python-3.x tensorflow neural-network conv-neural-network tf.keras

share|improve this question

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

add a comment | 

I'm building a Keras model and I have defined a class containing it. I need to "store" the input of the model in something like self.stored_input = input_of_the_model

I'm using Python 3.6.7, Tensorflow 2.1.6 and Keras 2.2.4 I've done a tentative but without good results. This is what I do:

'''

class AutoEncoder:
def init(self, input_shape=[224, 224]):

 self.models_dir = '../model'


 # Input
 img = Input(shape=(224, 224, 1))

 ..... Convolutional neural network layers here.....

 self.img = img

'''

I want to use self.img in a function of the class AutoEncoder but I obtain this error when I use it:

InvalidArgumentError: You must feed a value for placeholder tensor 'input_1' with dtype float and shape [?,224,224,1]
[[node input_1 = Placeholderdtype=DT_FLOAT, shape=[?,224,224,1], _device="/job:localhost/replica:0/task:0/device:CPU:0"]]

python-3.x tensorflow neural-network conv-neural-network tf.keras

share|improve this question

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

 self.models_dir = '../model'


 # Input
 img = Input(shape=(224, 224, 1))

 ..... Convolutional neural network layers here.....

 self.img = img

share|improve this question

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

share|improve this question

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge

asked Mar 27 at 22:04

CuriousMindCuriousMind

1411 bronze badge