How do I know what the output of model.predict() correspond to? - keras

Question

I am trying to make a CNN that classifies cats and dogs and I am using flow_from_directory() to prepare my data for the model.
from keras import Sequential
from keras_preprocessing.image import ImageDataGenerator
from keras.layers import *
from keras.callbacks import ModelCheckpoint
from keras.optimizers import *
import keras
import numpy as np
import os
img_size = 250 # number of pixels for width and height
#Random Seed
np.random.seed(123456789)
training_path = os.getcwd() + "/cats and dogs images/train"
testing_path = os.getcwd() + "/cats and dogs images/test"
#Defines the Model
model = Sequential([
Conv2D(filters=128, kernel_size=(3,3), activation="relu", padding="same", input_shape=(img_size,img_size,3)),
MaxPool2D(pool_size=(2,2), strides=2),
Conv2D(filters=64, kernel_size=(3,3), activation="relu", padding="same"),
Flatten(),
Dense(32, activation="relu"),
Dense(2, activation="softmax")
])
#Scales the pixel values to between 0 to 1
datagen = ImageDataGenerator(rescale=1.0/255.0)
Batch_size = 10
#Prepares Training Data
training_dataset = datagen.flow_from_directory(directory = training_path,
target_size=(img_size,img_size),
classes = ["cat","dog"],
class_mode = "categorical",
batch_size = Batch_size)
#Prepares Testing Data
testing_dataset = datagen.flow_from_directory(directory = testing_path,
target_size=(img_size,img_size),
classes = ["cat","dog"],
class_mode = "categorical",
batch_size = Batch_size)
#Compiles the model
#model.compile(loss="categorical_crossentropy", optimizer="sgd", metrics=['accuracy'])
model.compile(loss="binary_crossentropy", optimizer="adam", metrics=['accuracy'])
#model.compile(loss="mse", optimizer="sgd", metrics=[keras.metrics.MeanSquaredError()])
#Checkpoint
filepath = os.getcwd() + "/trained_model.h5"
checkpoint = ModelCheckpoint(filepath, monitor='loss', verbose=1, save_best_only=True, mode='min', save_freq=1)
#Fitting the model to the dataset (Training the Model)
model.fit(x = training_dataset, steps_per_epoch = 400,
validation_data=testing_dataset, validation_steps=100,
epochs = 10, callbacks=[checkpoint], verbose = 1)
# evaluate model on training dataset
_,acc = model.evaluate_generator(training_dataset, steps=len(training_dataset), verbose=0)
print("Accuracy on training dataset:")
print('> %.3f' % (acc * 100.0))
#evaluate model on testing dataset
_,acc = model.evaluate_generator(testing_dataset, steps=len(testing_dataset), verbose=0)
print("Accuracy on testing dataset:")
print('> %.3f' % (acc * 100.0))
I want to know how the output of model.predict() is going to correspond to the labels cats and dogs and which one of the two numbers in the output is a cat and which is a dog?
Here's my code for loading the model and giving a prediction:
from keras.models import Sequential
from keras_preprocessing.image import *
from keras.layers import *
import tensorflow as tf
import numpy as np
from keras.layers.experimental.preprocessing import Rescaling
import os
import cv2
from keras.models import *
img_size = 250
#Load weights into new model
filepath = os.getcwd() + "/trained_model.h5"
model = load_model(filepath)
print("Loaded model from disk")
#Scales the pixel values to between 0 to 1
#datagen = ImageDataGenerator(rescale=1.0/255.0)
#Prepares Testing Data
testing_dataset = cv2.imread(os.getcwd() + "/cats and dogs images/single test sample/507.png")
#img = datagen.flow_from_directory(testing_dataset, target_size=(img_size,img_size))
img = cv2.resize(testing_dataset, (img_size,img_size))
newimg = np.asarray(img)
pixels = newimg.astype('float32')
pixels /= 255.0
print(pixels.shape)
pixels = np.expand_dims(pixels, axis=0)
print(pixels.shape)
prediction = model.predict(pixels)
print(prediction)
And here is the output from the prediction code above:
Loaded model from disk
(250, 250, 3)
(1, 250, 250, 3)
[[5.4904184e-27 1.0000000e+00]]
As you can see, the prediction gave an array of two numbers, but which one corresponds to the dog label and which to the cat label? By the way, the model isn't fully trained so I am just testing out the code to see if it works.

Answer 1

The model output depends on how you loaded the data and specified how the classes are going to be ordered/labelled in this code you provided:
training_dataset = datagen.flow_from_directory(directory = training_path,
target_size=(img_size,img_size),
classes = ["cat","dog"],
class_mode = "categorical",
batch_size = Batch_size)
#Prepares Testing Data
testing_dataset = datagen.flow_from_directory(directory = testing_path,
target_size=(img_size,img_size),
classes = ["cat","dog"],
class_mode = "categorical",
batch_size = Batch_size)
You specified during the loading of the data that the classes are going to be ordered Cat then Dog in classes argument.
Therefor the output is going to be ordered as two probabilities (summing to 1)
The first probability refers to by how % that the input image is cat and the second probability refers to by how % that the input image is dog.
You use this line:
output_class = np.argmax(prediction, axis=1)
This line will compare the elements of the list and outputs which index of the elements of the list is the greatest (In our case the list containing the two probabilities) in the form of [1] (or [0, 1] depending on the shape of the output) this means that the said image is a dog, since the 2nd element in the output list is 1 if it were [0] (or [1, 0] depending on the shape of the output) then that means that the output class of the input image is cat.