How can I get rid of getting error through test generator?

user_14219882 0
Viewed 651

My train_generator and valid_generator works but when i try to predict I get some kind of error, which I think is from test_genarator.

train_datagen = ImageDataGenerator(rotation_range=15,
                                rescale=1./255,
                                shear_range=0.1,
                                zoom_range=0.2,
                                horizontal_flip=True,
                                width_shift_range=0.1,
                                height_shift_range=0.1
                                )
train_generator = train_datagen.flow_from_dataframe(train_df,
                                                 "./dogs-vs-cats/train/",x_col='filename',y_col='category',
                                                 target_size=Image_Size,
                                                 class_mode='categorical',
                                                 batch_size=batch_size)
validation_datagen = ImageDataGenerator(rescale=1./255)
validation_generator = validation_datagen.flow_from_dataframe(
    validate_df, 
    "./dogs-vs-cats/train/", 
    x_col='filename',
    y_col='category',
    target_size=Image_Size,
    class_mode='categorical',
    batch_size=batch_size
)

This is my train and validation generator, but my test generator does not work?

test_datagen = ImageDataGenerator(rotation_range=15,
                                rescale=1./255,
                                shear_range=0.1,
                                zoom_range=0.2,
                                horizontal_flip=True,
                                width_shift_range=0.1,
                                height_shift_range=0.1)
test_generator = train_datagen.flow_from_dataframe(train_df,
                                                 "./dogs-vs-cats/test/",x_col='filename',y_col='category',
                                                 target_size=Image_Size,
                                                 class_mode='categorical',
                                                 batch_size=batch_size)

As well,

test_filenames = os.listdir("./dogs-vs-cats/test1")
test_df = pd.DataFrame({
    'filename': test_filenames
})
nb_samples = test_df.shape[0]
predict = model.predict_generator(test_generator, steps=np.ceil(nb_samples/batch_size))

ValueError: Asked to retrieve element 0, but the Sequence has length 0

data-science keras tensorflow machine-learning python
1 Answers

The reason for your error is that the there are no Image files inside the Folders, cats and dogs, inside test folder.

Some more observations from your code:

  1. It should be

    test_generator = test_datagen.flow_from_dataframe(train_df,..... instead of

    test_generator = train_datagen.flow_from_dataframe(train_df, ...

  2. In the below line of code, you have used the folder, test

test_generator = train_datagen.flow_from_dataframe(train_df, "./dogs-vs-cats/test/",...........

but in the below line of code you have used the folder, test1. Why?

test_filenames = os.listdir("./dogs-vs-cats/test1")

  1. Please use model.predict instead of model.predict_generator as the latter is deprecated.
user_115304620
Related