model.predict() having a strange output - tensorflow

Question

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.]]
Update:
I have changed the code according to the suggestions but it is predicting the exact same thing every time
Edit to training file
inputs = keras.Input(shape=(50, 50, 1))
x = layers.Conv2D(16, 3)(inputs)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)
x = layers.Conv2D(32, 3)(x)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)
x = layers.Conv2D(64, 3)(x)
x = layers.BatchNormalization()(x)
x = keras.activations.relu(x)
x = layers.Flatten()(x)
outputs = layers.Dense(1, activation='sigmoid')(x)
model = keras.Model(inputs=inputs, outputs=outputs)
print(model.summary())
model.compile(
loss='binary_crossentropy',
optimizer=keras.optimizers.Adam(3e-4),
metrics=['accuracy']
)
model.fit(x_train, y_train, batch_size=2, epochs=100, validation_split=0.1)
model.save('saved_model')
Edits for testing file
import os
os.environ['TF_CPP_MIN_LOG_LEVEL'] = '2'
import cv2
import tensorflow as tf
CATEGORIES = ['Bird', 'Cat', 'Dog']
def format(file_path):
size = 50
img = cv2.imread(file_path, cv2.IMREAD_GRAYSCALE)
new_img = cv2.resize(img, (size, size))
return new_img.reshape(-1, 50, 50, 1)
model = tf.keras.models.load_model('saved_model')
prediction = model.predict([format('cat.jpg')])
prediction2 = model.predict([format('dog.jpg')])
prediction3 = model.predict([format('bird.jpg')])
print(CATEGORIES[int(prediction[0][0])])
print(CATEGORIES[int(prediction2[0][0])])
print(CATEGORIES[int(prediction3[0][0])])
the output is now showing even though the images are completely different.
Cat
Cat
Cat

Answer 1

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.

Answer 2

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')
]
)