Keras how do I predict after I trained a model

Question

I m playing with the reuters-example dataset and it runs fine  my model is trained    I read about how to save a model  so I could load it later to use again   But how do I use this saved model to predict a new text   Do I use models predict     Do I have to prepare this text in a special way   I tried it with  import keras preprocessing text  text   np array   this is just some random  stupid text    print text shape   tk   keras preprocessing text Tokenizer          nb words 2000          filters keras preprocessing text base filter            lower True          split       tk fit on texts text  pred   tk texts to sequences text  print pred   model predict pred    But I always get   1L     2  4  1  6  5  7  3   --------------------------------------------------------------------------- AttributeError                            Traceback  most recent call last   lt ipython-input-83-42d744d811fb gt  in  lt module gt          7 print pred        8  ---- gt  9 model predict pred   C  Users bkey Anaconda2 lib site-packages keras models pyc in predict self  x  batch size  verbose      457         if self model is None      458             self build   -- gt  459         return self model predict x  batch size batch size  verbose verbose      460      461     def predict on batch self  x    C  Users bkey Anaconda2 lib site-packages keras engine training pyc in predict self  x  batch size  verbose     1132         x   standardize input data x  self input names     1133                                    self internal input shapes  - gt  1134                                    check batch dim False     1135         if self stateful     1136             if x 0  shape 0   gt  batch size and x 0  shape 0    batch size    0   C  Users bkey Anaconda2 lib site-packages keras engine training pyc in standardize input data data  names  shapes  check batch dim  exception prefix       79     for i in range len names         80         array   arrays i  --- gt  81         if len array shape     1       82             array   np expand dims array  1       83             arrays i    array  AttributeError   list  object has no attribute  shape    Do you have any recommendations as to how to make predictions with a trained model

User · Answer

I trained a neural network in Keras to perform non linear regression on some data  This is some part of my code for testing on new data using previously saved model configuration and weights   fname   r C  Users tauseef Desktop keras tutorials BestWeights hdf5  modelConfig   joblib load  modelConfig pkl   recreatedModel   Sequential from config modelConfig  recreatedModel load weights fname  unseenTestData   np genfromtxt r C  Users tauseef Desktop keras arrayOf100Rows257Columns txt  delimiter      X test   unseenTestData standard scalerX   StandardScaler   standard scalerX fit X test  X test std   standard scalerX transform X test  X test std   X test std astype  float32   unseenData predictions   recreatedModel predict X test std

User · Answer

You must use the same Tokenizer you used to build your model   Else this will give different vector to each word   Then  I am using   phrase    not good  tokens   myTokenizer texts to matrix  phrase    model predict np array tokens

User · Answer

model predict   expects the first parameter to be a numpy array  You supply a list  which does not have the shape attribute a numpy array has   Otherwise your code looks fine  except that you are doing nothing with the prediction  Make sure you store it in a variable  for example like this   prediction   model predict np array tk texts to sequences text    print prediction

User · Answer

You can just  quot call quot  your model with an array of the correct shape  model np array   6 7  3 3  5 7  2 5      Full example  from sklearn datasets import load iris from tensorflow keras layers import Dense from tensorflow keras models import Sequential import numpy as np  X  y   load iris return X y True   model   Sequential       Dense 16  activation  relu        Dense 32  activation  relu        Dense 1     model compile loss  mean absolute error   optimizer  adam    history   model fit X  y  epochs 10  verbose 0   print model np array   6 7  3 3  5 7  2 5        lt tf Tensor  shape  1  1   dtype float64  numpy array   1 92517677    gt

User · Answer

Your can use your tokenizer and pad sequencing for a new piece of text  This is followed by model prediction  This will return the prediction as a numpy array plus the label itself  For example  new complaint     Your service is not good   seq   tokenizer texts to sequences new complaint  padded   pad sequences seq  maxlen maxlen  pred   model predict padded  print pred  labels np argmax pred

User · Answer

model predict classes  lt numpy array gt     Sample https   gist github com alexcpn 0683bb940cae510cf84d5976c1652abd

[python] Keras, how do I predict after I trained a model?

Examples related to python

Examples related to theano

Examples related to deep-learning

Examples related to keras