keras model only predicts one class for all the test images

I am trying to build an image classification model with 2 classes with (1) or without (0). I can build the model and get an accuracy of 1. which is too good to be true (which is an issue) but when I use predict_generator as I have my images in folders, it only returns 1 class 0 (without class). There seems to be an issue but I can't work it out, i have looked at a number of articles but I still can't fix the issue.

image_shape = (220, 525, 3) #height, width, channels

img_width = 96

img_height = 96

channels = 3



epochs = 10



no_train_images = 11957              #!ls ../data/train/* | wc -l

no_test_images = 652                 #!ls ../data/test/* | wc -l

no_valid_images = 6156               #!ls ../data/test/* | wc -l



train_dir = '../data/train/'

test_dir = '../data/test/'

valid_dir = '../data/valid/'



classification_model = Sequential()



# First layer with 2D convolution (32 filters, (3, 3) kernel size 3x3, input_shape=(img_width, img_height, channels))

classification_model.add(Conv2D(32, (3, 3), input_shape=input_shape))

# Activation Function = ReLu increases the non-linearity

classification_model.add(Activation('relu'))

# Max-Pooling layer with the size of the grid 2x2

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

# Randomly disconnets some nodes between this layer and the next 

classification_model.add(Dropout(0.2))



classification_model.add(Conv2D(32, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.2))



classification_model.add(Conv2D(64, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.25))



classification_model.add(Conv2D(64, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.3))



classification_model.add(Flatten())

classification_model.add(Dense(64))

classification_model.add(Activation('relu'))

classification_model.add(Dropout(0.5))

classification_model.add(Dense(1))

classification_model.add(Activation('sigmoid'))



# Using binary_crossentropy as we only have 2 classes

classification_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])







batch_size = 32



# this is the augmentation configuration we will use for training

train_datagen = ImageDataGenerator(

    rescale=1. / 255,

    zoom_range=0.2)



# this is the augmentation configuration we will use for testing:

# only rescaling

valid_datagen = ImageDataGenerator(rescale=1. / 255)

test_datagen = ImageDataGenerator()



train_generator = train_datagen.flow_from_directory(

    train_dir,

    target_size = (img_width, img_height),

    batch_size = batch_size,

    class_mode = 'binary',

    shuffle = True)



valid_generator = valid_datagen.flow_from_directory(

    valid_dir,

    target_size = (img_width, img_height),

    batch_size = batch_size,

    class_mode = 'binary',

    shuffle = False)



test_generator = test_datagen.flow_from_directory(

    test_dir,

    target_size = (img_width, img_height),

    batch_size = 1,

    class_mode = None,

    shuffle = False)



mpd = classification_model.fit_generator(

    train_generator,

    steps_per_epoch = no_train_images // batch_size,         # number of images per epoch

    epochs = epochs,                                         # number of iterations over the entire data

    validation_data = valid_generator,

    validation_steps = no_valid_images // batch_size)

Epoch 1/10
373/373 [==============================] - 119s 320ms/step - loss: 0.5214 - acc: 0.7357 - val_loss: 0.2720 - val_acc: 0.8758

Epoch 2/10
373/373 [==============================] - 120s 322ms/step - loss: 0.2485 - acc: 0.8935 - val_loss: 0.0568 - val_acc: 0.9829

Epoch 3/10
373/373 [==============================] - 130s 350ms/step - loss: 0.1427 - acc: 0.9435 - val_loss: 0.0410 - val_acc: 0.9796

Epoch 4/10
373/373 [==============================] - 127s 341ms/step - loss: 0.1053 - acc: 0.9623 - val_loss: 0.0197 - val_acc: 0.9971

Epoch 5/10
373/373 [==============================] - 126s 337ms/step - loss: 0.0817 - acc: 0.9682 - val_loss: 0.0136 - val_acc: 0.9948

Epoch 6/10
373/373 [==============================] - 123s 329ms/step - loss: 0.0665 - acc: 0.9754 - val_loss: 0.0116 - val_acc: 0.9985

Epoch 7/10
373/373 [==============================] - 140s 376ms/step - loss: 0.0518 - acc: 0.9817 - val_loss: 0.0035 - val_acc: 0.9997

Epoch 8/10
373/373 [==============================] - 144s 386ms/step - loss: 0.0539 - acc: 0.9832 - val_loss: 8.9459e-04 - val_acc: 1.0000

Epoch 9/10
373/373 [==============================] - 122s 327ms/step - loss: 0.0434 - acc: 0.9850 - val_loss: 0.0023 - val_acc: 0.9997

Epoch 10/10
373/373 [==============================] - 125s 336ms/step - loss: 0.0513 - acc: 0.9844 - val_loss: 0.0014 - val_acc: 1.0000

valid_generator.batch_size=1

score = classification_model.evaluate_generator(valid_generator, 

                                                no_test_images/batch_size, pickle_safe=False)

test_generator.reset()

scores=classification_model.predict_generator(test_generator, len(test_generator))



print("Loss: ", score[0], "Accuracy: ", score[1])



predicted_class_indices=np.argmax(scores,axis=1)

print(predicted_class_indices)



labels = (train_generator.class_indices)

labelss = dict((v,k) for k,v in labels.items())

predictions = [labelss[k] for k in predicted_class_indices]



filenames=test_generator.filenames

results=pd.DataFrame({"Filename":filenames,

                      "Predictions":predictions})



print(results)

Loss: 5.404246180551993e-06 Accuracy: 1.0

print(predicted_class_indices) - ALL 0

[0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]

                              Filename Predictions

0      test_folder/video_3_frame10.jpg   without

1    test_folder/video_3_frame1001.jpg   without

2    test_folder/video_3_frame1006.jpg   without

3    test_folder/video_3_frame1008.jpg   without

4    test_folder/video_3_frame1009.jpg   without

5    test_folder/video_3_frame1010.jpg   without

6    test_folder/video_3_frame1013.jpg   without

7    test_folder/video_3_frame1014.jpg   without

8    test_folder/video_3_frame1022.jpg   without

9    test_folder/video_3_frame1023.jpg   without

10    test_folder/video_3_frame103.jpg   without

11   test_folder/video_3_frame1036.jpg   without

12   test_folder/video_3_frame1039.jpg   without

13    test_folder/video_3_frame104.jpg   without

14   test_folder/video_3_frame1042.jpg   without

15   test_folder/video_3_frame1043.jpg   without

16   test_folder/video_3_frame1048.jpg   without

17    test_folder/video_3_frame105.jpg   without

18   test_folder/video_3_frame1051.jpg   without

19   test_folder/video_3_frame1052.jpg   without

20   test_folder/video_3_frame1054.jpg   without

21   test_folder/video_3_frame1055.jpg   without

22   test_folder/video_3_frame1057.jpg   without

23   test_folder/video_3_frame1059.jpg   without

24   test_folder/video_3_frame1060.jpg   without

...just some of the outputs but all 650+ are without class.

This is the output and as you can see all the predicted values are 0 for the without class.

This is my first attempt at using Keras and CNN so any help would be really appreciated.

asked yesterday

vis7

New contributor

$begingroup$
You are overfitting badly(data is scarce I assume, use Augmentations or download similar images and expand)
$endgroup$
– Aditya
yesterday

$begingroup$
@Aditya I have augmented my images using cv2 in a different script such as flipping images, brightness and this was before I knew you could do the same using the ImageDataGenerator but thanks. Any idea why there is only one class being predicted. I have more than 13000 images for training and 6000 for valid.
$endgroup$
– vis7
yesterday

$begingroup$
What do your images represent? Are your images separated into folders for train and val splits?
$endgroup$
– Antonio Jurić
20 hours ago

$begingroup$
@AntonioJurić The images represent someone with and without a football. The directory structure for both train and valid is the following. Train->without->image1, image2 ->with->image4, image5 Valid->without->image3, image6 ->with->image0, image7
$endgroup$
– vis7
18 hours ago

add a comment |

image_shape = (220, 525, 3) #height, width, channels

img_width = 96

img_height = 96

channels = 3



epochs = 10



no_train_images = 11957              #!ls ../data/train/* | wc -l

no_test_images = 652                 #!ls ../data/test/* | wc -l

no_valid_images = 6156               #!ls ../data/test/* | wc -l



train_dir = '../data/train/'

test_dir = '../data/test/'

valid_dir = '../data/valid/'



classification_model = Sequential()



# First layer with 2D convolution (32 filters, (3, 3) kernel size 3x3, input_shape=(img_width, img_height, channels))

classification_model.add(Conv2D(32, (3, 3), input_shape=input_shape))

# Activation Function = ReLu increases the non-linearity

classification_model.add(Activation('relu'))

# Max-Pooling layer with the size of the grid 2x2

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

# Randomly disconnets some nodes between this layer and the next 

classification_model.add(Dropout(0.2))



classification_model.add(Conv2D(32, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.2))



classification_model.add(Conv2D(64, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.25))



classification_model.add(Conv2D(64, (3, 3)))

classification_model.add(Activation('relu'))

classification_model.add(MaxPooling2D(pool_size=(2, 2)))

classification_model.add(Dropout(0.3))



classification_model.add(Flatten())

classification_model.add(Dense(64))

classification_model.add(Activation('relu'))

classification_model.add(Dropout(0.5))

classification_model.add(Dense(1))

classification_model.add(Activation('sigmoid'))



# Using binary_crossentropy as we only have 2 classes

classification_model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])







batch_size = 32



# this is the augmentation configuration we will use for training

train_datagen = ImageDataGenerator(

    rescale=1. / 255,

    zoom_range=0.2)



# this is the augmentation configuration we will use for testing:

# only rescaling

valid_datagen = ImageDataGenerator(rescale=1. / 255)

test_datagen = ImageDataGenerator()



train_generator = train_datagen.flow_from_directory(

    train_dir,

    target_size = (img_width, img_height),

    batch_size = batch_size,

    class_mode = 'binary',

    shuffle = True)



valid_generator = valid_datagen.flow_from_directory(

    valid_dir,

    target_size = (img_width, img_height),

    batch_size = batch_size,

    class_mode = 'binary',

    shuffle = False)



test_generator = test_datagen.flow_from_directory(

    test_dir,

    target_size = (img_width, img_height),

    batch_size = 1,

    class_mode = None,

    shuffle = False)



mpd = classification_model.fit_generator(

    train_generator,

    steps_per_epoch = no_train_images // batch_size,         # number of images per epoch

    epochs = epochs,                                         # number of iterations over the entire data

    validation_data = valid_generator,

    validation_steps = no_valid_images // batch_size)