Binary image classifier always predicting one class - python-3.x

Question

I am trying to design a model for binary image classification, this is my first classifier and I am following an online tutorial but the model always predicts class 0
My dataset contains 3620 and 3651 images of each class respectively, I don't suppose the problem is due to an imbalanced dataset as the model is predicting only the class with lower number of sample in the dataset.
My code
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
img_hieght, img_width = 150,150
train_data_dir = 'dataset/train'
#validation_data_dir = 'dataset/validation'
nb_train_samples = 3000
#nb_validation_samples = 500
epochs = 10
batch_size = 16
if K.image_data_format() == 'channels_first':
input_shape = (3, img_width, img_hieght)
else:
input_shape = (img_width, img_hieght, 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'])
train_datagen = ImageDataGenerator(
rescale = 1. /255,
shear_range = 0.2,
zoom_range = 0.2,
horizontal_flip = True)
train_generator = train_datagen.flow_from_directory(
train_data_dir,
target_size = (img_width,img_hieght),
batch_size = batch_size,
class_mode = 'binary')
model.fit_generator(train_generator,
steps_per_epoch = nb_train_samples//batch_size,
epochs = epochs)
model.save('classifier.h5')
I have tried checking the model summary as well, but couldn't detect anything notable
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_1 (Conv2D) (None, 148, 148, 32) 896
_________________________________________________________________
activation_1 (Activation) (None, 148, 148, 32) 0
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 (None, 74, 74, 32) 0
_________________________________________________________________
conv2d_2 (Conv2D) (None, 72, 72, 32) 9248
_________________________________________________________________
activation_2 (Activation) (None, 72, 72, 32) 0
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 (None, 36, 36, 32) 0
_________________________________________________________________
conv2d_3 (Conv2D) (None, 34, 34, 64) 18496
_________________________________________________________________
activation_3 (Activation) (None, 34, 34, 64) 0
_________________________________________________________________
max_pooling2d_3 (MaxPooling2 (None, 17, 17, 64) 0
_________________________________________________________________
flatten_1 (Flatten) (None, 18496) 0
_________________________________________________________________
dense_1 (Dense) (None, 64) 1183808
_________________________________________________________________
activation_4 (Activation) (None, 64) 0
_________________________________________________________________
dropout_1 (Dropout) (None, 64) 0
_________________________________________________________________
dense_2 (Dense) (None, 1) 65
_________________________________________________________________
activation_5 (Activation) (None, 1) 0
=================================================================
Total params: 1,212,513
Trainable params: 1,212,513
Non-trainable params: 0
_________________________________________________________________
None
I have not used validation dataset, I am using only training data and testing the model manually using:
import tensorflow as tf
from keras.preprocessing.image import ImageDataGenerator
batch_size = 16
path = 'dataset/test'
imgen = ImageDataGenerator(rescale=1/255.)
testGene = imgen.flow_from_directory(directory=path,
target_size=(150, 150,),
shuffle=False,
class_mode='binary',
batch_size=batch_size,
save_to_dir=None
)
model = tf.keras.models.load_model("classifier.h5")
pred = model.predict_generator(testGene, steps=testGene.n/batch_size)
print(pred)
Here are the accuracy and loss values per epochs:
Epoch 1/10
187/187 [==============================] - 62s 330ms/step - loss: 0.5881 - accuracy: 0.7182
Epoch 2/10
187/187 [==============================] - 99s 529ms/step - loss: 0.4102 - accuracy: 0.8249
Epoch 3/10
187/187 [==============================] - 137s 733ms/step - loss: 0.3266 - accuracy: 0.8646
Epoch 4/10
187/187 [==============================] - 159s 851ms/step - loss: 0.3139 - accuracy: 0.8620
Epoch 5/10
187/187 [==============================] - 112s 597ms/step - loss: 0.2871 - accuracy: 0.8873
Epoch 6/10
187/187 [==============================] - 60s 323ms/step - loss: 0.2799 - accuracy: 0.8847
Epoch 7/10
187/187 [==============================] - 66s 352ms/step - loss: 0.2696 - accuracy: 0.8870
Epoch 8/10
187/187 [==============================] - 57s 303ms/step - loss: 0.2440 - accuracy: 0.8947
Epoch 9/10
187/187 [==============================] - 56s 299ms/step - loss: 0.2478 - accuracy: 0.8994
Epoch 10/10
187/187 [==============================] - 53s 285ms/step - loss: 0.2448 - accuracy: 0.9047

Answer 1

You use only 3000 samples per epoch (see line nb_train_samples = 3000), while having 3620 and 3651 images for the each class. Given that model gets 90% accuracy and predicts only zeros, I suppose that you pass only class-zero images to the network during training. Consider increasing nb_train_samples.