Styjun

New coworker has strange workplace requirements - how should I deal with them?

What is the practical impact of using System.Random which is not cryptographically random?

How to Flip Rotation from Positive to Negative?

Why doesn't Starship have four landing legs?

Understanding data transmission rates over copper wire

Cheap oscilloscope showing 16 MHz square wave

How do I get my neighbour to stop disturbing with loud music?

Does FERPA require parental notification of disability assessment?

Can authors email you PDFs of their textbook for free?

How can I improve my formal definitions?

What's the origin of the concept of alternate dimensions/realities?

IList<T> implementation

I failed to respond to a potential advisor

What caused the end of cybernetic implants?

Quick Tilepaint Puzzles: Corridors and Corners

Is Borg adaptation only temporary?

'Horseshoes' for Deer?

Heuristic argument for the Riemann Hypothesis

Can the inductive kick be discharged without a freewheeling diode, in this example?

Do universities maintain secret textbooks?

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

Sum and average calculator

What was Captain Marvel supposed to do once she reached her destination?

Padding a column of lists

Load keras model and cache it in a variable without having to reload

ValueError: Tensor 'A' must be from the same graph as Tensor 'B'Load the model and predict with keras and tensorflowTensor is not an element of this graph; deploying Keras modelInstantiate VGG model for once only in Keras when predicting continuously?Concatening Attention layer with decoder input seq2seq model on KerasKeras load model problem using Cannot interpret feed_dict key as Tensor threadingHow to use multiple keras models in a single thread?Got error: Output tensors to a Model must be the output of a Keras `Layer`The initial state or constants of an RNN layer cannot be specified with a mix of Keras tensors and non-Keras tensorsGraph Disconnected when trying to build CNN model with Keras Functional API

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

0

Loading a model at the beggining of my Flask application and then using it for predictions in my endpoints results in an error

'ValueError: Tensor Tensor("dense/Softmax:0", shape=(?, 4), dtype=float32) is not an element of this graph.'

model = keras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])

but loading keras model every time the prediction endpoint is called seems to be working perfectly

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 model = keras.models.load_model("model.h5")

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0]) 

is there a way to fix this? this quite radically reduces the performance having to reload the model every time.

python tensorflow keras

share|improve this question

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

add a comment | 

0

Loading a model at the beggining of my Flask application and then using it for predictions in my endpoints results in an error

'ValueError: Tensor Tensor("dense/Softmax:0", shape=(?, 4), dtype=float32) is not an element of this graph.'

model = keras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])

but loading keras model every time the prediction endpoint is called seems to be working perfectly

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 model = keras.models.load_model("model.h5")

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0]) 

is there a way to fix this? this quite radically reduces the performance having to reload the model every time.

python tensorflow keras

share|improve this question

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

add a comment | 

Loading a model at the beggining of my Flask application and then using it for predictions in my endpoints results in an error

'ValueError: Tensor Tensor("dense/Softmax:0", shape=(?, 4), dtype=float32) is not an element of this graph.'

model = keras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])

but loading keras model every time the prediction endpoint is called seems to be working perfectly

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 model = keras.models.load_model("model.h5")

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0]) 

is there a way to fix this? this quite radically reduces the performance having to reload the model every time.

python tensorflow keras

share|improve this question

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

model = keras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 model = keras.models.load_model("model.h5")

 variable = preparePredictionInput(
 [variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0]) 

share|improve this question

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

share|improve this question

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

asked Mar 27 at 13:41

HigeathHigeath

3611 silver badge66 bronze badges

1 Answer
1

active

oldest

votes

0

Semms like your model variable is not global. Have a look at the below code:

def init():
 global model
 model = lkeras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 variable = preparePredictionInput([variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])


if __name__ == "__main__":
 init()
 app.run()

share|improve this answer

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  It is assigned in global context, it is global..
  
  – Higeath
  Mar 29 at 18:14
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Did you try the code?
  
  – stacklikemind
  Mar 30 at 10:48
  

  
  
  
  

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');
);

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%2fstackoverflow.com%2fquestions%2f55378692%2fload-keras-model-and-cache-it-in-a-variable-without-having-to-reload%23new-answer', 'question_page');

);

Post as a guest

Name

Email

Required, but never shown

0

Semms like your model variable is not global. Have a look at the below code:

def init():
 global model
 model = lkeras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 variable = preparePredictionInput([variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])


if __name__ == "__main__":
 init()
 app.run()

share|improve this answer

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  It is assigned in global context, it is global..
  
  – Higeath
  Mar 29 at 18:14
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Did you try the code?
  
  – stacklikemind
  Mar 30 at 10:48
  

  
  
  
  

add a comment | 

0

Semms like your model variable is not global. Have a look at the below code:

def init():
 global model
 model = lkeras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 variable = preparePredictionInput([variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])


if __name__ == "__main__":
 init()
 app.run()

share|improve this answer

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  It is assigned in global context, it is global..
  
  – Higeath
  Mar 29 at 18:14
  

  
  
  
  


• 
  
  
  

  
  

  
  
  
  
  
  

  
  
  Did you try the code?
  
  – stacklikemind
  Mar 30 at 10:48
  

  
  
  
  

add a comment | 

Semms like your model variable is not global. Have a look at the below code:

def init():
 global model
 model = lkeras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 variable = preparePredictionInput([variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])


if __name__ == "__main__":
 init()
 app.run()

share|improve this answer

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

def init():
 global model
 model = lkeras.models.load_model("model.h5")

@app.route("/predict", methods=["POST"])
def predict():
 json_data = request.get_json()
 variable = preparePredictionInput([variable], alphabetDict, maxVariableLength)
 prediction = list(model.predict(variable, steps=1, verbose=1)[0])


if __name__ == "__main__":
 init()
 app.run()

share|improve this answer

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges

answered Mar 27 at 23:32

stacklikemindstacklikemind

16611 silver badge1010 bronze badges