How to predict input image using trained model in Keras

Question

I m only beginning with keras and machine learning in general   I trained a model to classify images from 2 classes and saved it using model save    Here is the code I used   from keras preprocessing image import ImageDataGenerator from keras models import Sequential from keras layers import Conv2D  MaxPooling2D from keras layers import Activation  Dropout  Flatten  Dense from keras import backend as K     dimensions of our images  img width  img height   320  240  train data dir    data train  validation data dir    data validation  nb train samples   200   total nb validation samples   10    total epochs   6 batch size   10  if K image data format       channels first       input shape    3  img width  img height  else      input shape    img width  img height  3   model   Sequential   model add Conv2D 32   3  3   input shape input shape   model add Activation  relu    model add MaxPooling2D pool size  2  2     model add Conv2D 32   3  3    model add Activation  relu    model add MaxPooling2D pool size  2  2     model add Conv2D 64   3  3    model add Activation  relu    model add MaxPooling2D pool size  2  2     model add Flatten    model add Dense 64   model add Activation  relu    model add Dropout 0 5   model add Dense 1   model add Activation  sigmoid     model compile loss  binary crossentropy                 optimizer  rmsprop                 metrics   accuracy       this is the augmentation configuration we will use for training train datagen   ImageDataGenerator      rescale 1    255      shear range 0 2      zoom range 0 2      horizontal flip True     this is the augmentation configuration we will use for testing    only rescaling test datagen   ImageDataGenerator rescale 1    255   train generator   train datagen flow from directory      train data dir      target size  img width  img height       batch size batch size      class mode  binary    validation generator   test datagen flow from directory      validation data dir      target size  img width  img height       batch size batch size      class mode  binary    model fit generator      train generator      steps per epoch nb train samples    batch size      epochs epochs      validation data validation generator      validation steps 5   model save  model h5     It successfully trained with 0 98 accuracy which is pretty good  To load and test this model on new images  I used the below code   from keras models import load model import cv2 import numpy as np  model   load model  model h5    model compile loss  binary crossentropy                 optimizer  rmsprop                 metrics   accuracy     img   cv2 imread  test jpg   img   cv2 resize img  320 240   img   np reshape img  1 320 240 3    classes   model predict classes img   print classes   It outputs        0     Why wouldn t it give out the actual name of the class and why   0     Thanks in advance

User · Answer

That s because you re getting the numeric value associated with the class  For example if you have two classes cats and dogs  Keras will associate them numeric values 0 and 1  To get the mapping between your classes and their associated numeric value  you can use   gt  gt  gt  classes   train generator class indices      gt  gt  gt  print classes        cats   0   dogs   1    Now you know the mapping between your classes and indices  So now what you can do is   if classes 0  0     1      prediction    dog  else      prediction    cat

User · Answer

keras predict classes  docs  outputs A numpy array of class predictions  Which in your model case  the index of neuron of highest activation from your last softmax  layer    0   means that your model predicted that your test data is class 0   usually you will be passing multiple image  and the result will look like   0    1    1    0      You must convert your actual label  e g   cancer    not cancer   into binary encoding  0 for  cancer   1 for  not cancer   for binary classification  Then you will interpret your sequence output of   0   as having class label  cancer

User · Answer

If someone is still struggling to make predictions on images  here is the optimized code to load the saved model and make predictions     Modify  test1 jpg  and  test2 jpg  to the images you want to predict on  from keras models import load model from keras preprocessing import image import numpy as np    dimensions of our images img width  img height   320  240    load the model we saved model   load model  model h5   model compile loss  binary crossentropy                 optimizer  rmsprop                 metrics   accuracy       predicting images img   image load img  test1 jpg   target size  img width  img height   x   image img to array img  x   np expand dims x  axis 0   images   np vstack  x   classes   model predict classes images  batch size 10  print classes    predicting multiple images at once img   image load img  test2 jpg   target size  img width  img height   y   image img to array img  y   np expand dims y  axis 0     pass the list of multiple images np vstack   images   np vstack  x  y   classes   model predict classes images  batch size 10     print the classes  the images belong to print classes print classes 0  print classes 0  0

User · Answer

Forwarding the example by  ritiek  I m a beginner in ML too  maybe this kind of formatting will help see the name instead of just class number   images   np vstack  x  y    prediction   model predict images   print prediction   i   1  for things in prediction        if things    0           print   d It is cancer   i       else          print   d Not cancer   i       i   i   1

User · Answer

You can use model predict   to predict the class of a single image as follows  doc      load model sample py from keras models import load model from keras preprocessing import image import matplotlib pyplot as plt import numpy as np import os   def load image img path  show False        img   image load img img path  target size  150  150       img tensor   image img to array img                        height  width  channels      img tensor   np expand dims img tensor  axis 0             1  height  width  channels   add a dimension because the model expects this shape   batch size  height  width  channels      img tensor    255                                         imshow expects values in the range  0  1       if show          plt imshow img tensor 0                                      plt axis  off           plt show        return img tensor   if   name         main            load model     model   load model  model aug h5          image path     img path     media data dogscats test1 3867 jpg       dog      img path     media data dogscats test1 19 jpg         cat        load a single image     new image   load image img path         check prediction     pred   model predict new image    In this example  a image is loaded as a numpy array with shape  1  height  width  channels   Then  we load it into the model and predict its class  returned as a real value in the range  0  1   binary classification in this example

[python] How to predict input image using trained model in Keras?

Examples related to python

Examples related to machine-learning

Examples related to keras

Examples related to computer-vision