model.predict() having a strange output-CodePudding

This is all the files that I used, the only one that isn't there are the images

Import the file data, my data is 20 samples of dogs and 20 samples of cats

import matplotlib.pyplot as plt
import os
import cv2
import random

DIR = 'assets'
CATEGORIES = ['Cat', 'Dog']

img_size = 50

training_data = []


def create_training_data():
    for category in CATEGORIES:
        path = os.path.join(DIR, category)
        class_num = CATEGORIES.index(category)
        for img in os.listdir(path):
            img_array = cv2.imread(os.path.join(path, img), cv2.IMREAD_GRAYSCALE)
            new_array = cv2.resize(img_array, (img_size, img_size))
            training_data.append([new_array, class_num])


create_training_data()
print(len(training_data))

# Shuffle the data
random.shuffle(training_data)

x_train = []
y_train = []

for featurs, label in training_data:
    x_train.append(featurs)
    y_train.append(label)

x_train = np.asarray(x_train).reshape(-1, img_size, img_size, 1)
y_train = np.array(y_train)

import pickle

pickle_out = open('x_train.pickle', 'wb')
pickle.dump(x_train, pickle_out)
pickle_out.close()

pickle_out = open('y_train.pickle', 'wb')
pickle.dump(y_train, pickle_out)
pickle_out.close()

Train the data


os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import pickle
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
import numpy as np
from tensorflow.keras.callbacks import TensorBoard

x_train = pickle.load(open('x_train.pickle', 'rb'))
y_train = pickle.load(open('y_train.pickle', 'rb'))

x_train = x_train / 255.0

print(x_train.shape)
model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10)
    ]
)
# inputs = keras.Input(shape=(50, 50, 1))
# x = layers.Conv2D(32, 3)(inputs)
# x = layers.BatchNormalization()(x)
# x = keras.activations.relu(x)
# x = layers.MaxPooling2D()(x)
# x = layers.Flatten()(x)
# outputs = layers.Dense(10, activation='softmax')(x)
# model = keras.Model(inputs=inputs, outputs=outputs)

model.compile(
    loss=keras.losses.SparseCategoricalCrossentropy(),
    optimizer=keras.optimizers.Adam(),
    metrics=['accuracy']
)

model.fit(x_train, y_train, batch_size=2, epochs=100, validation_split=0.1)
model.save('trained_model')

Test the data

import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import cv2
import tensorflow as tf

CATEGORIES = ['Cat', 'Dog']


def format(file_path):
    size = 50
    img_array = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
    new_array = cv2.resize(img_array, (size, size))
    return new_array.reshape(-1, size, size, 1)

model = tf.keras.models.load_model('trained_model')

prediction = model.predict([format('dog.jpg')])
print(prediction)

The above runs but the output looks like this.

[[  -36.40766  -1036.2589   -1382.8297   -1486.9949   -1403.7932
    -56.355995 -1364.2837   -1351.6316   -1385.2439   -1392.8472  ]]

Why is it giving me so many numbers instead to a simple 1 or 0? I'm expecting an output of something like [[0.]] or [[1.]]

Ask any questions if needed.

CodePudding user response：

There are two problems that I see here. First, when defining the model

model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10)
    ]
)

Since you are working with a binary classification problem, the last layer should be specified to have the sigmoid activation function like so layers.Dense(10, activation='sigmoid'). This will have the effect of restricting the range of your output from 0 to 1.

This, however, will still give you numbers in between that range. This is because when you actually make the predictions in

prediction = model.predict([format('dog.jpg')])
print(prediction)

You are not applying the threshold of 0.5 to the predictions (below 0.5 is classified as 0 and above as a 1). This can be easily adjusted prediction = (model.predict([format('dog.jpg')]) > 0.5).astype("int32"). The .astype("int32") function is necessary as otherwise your predictions would be in boolean.

CodePudding user response：

For a binary classification, your last layer should have only one outpout(instead of 10 in your case), and should use the sigmoïd activation function. Then you should add one more step to your model. That is a proposition.

model = keras.Sequential(
    [
        keras.Input(shape=(50, 50, 1)),
        layers.Conv2D(32, 3, activation='relu'),
        layers.MaxPooling2D(),
        layers.Flatten(),
        layers.Dense(10, activation='relu'),
        layers.Dense(1, activation='sigmoid')
    ]
)