Qfyilyi

I am trying to build an image classifier with keras and the size of my dataset requires me to use the ImageDataGenerator class along with its flow_from_dataframe method. This is the code I am using.

train_datagen = keras.preprocessing.image.ImageDataGenerator(

        rescale=1./255,

        shear_range=0.2,

        zoom_range=0.2,

        horizontal_flip=True)

train_generator = train_datagen.flow_from_dataframe(

        directory='stage_1_train_images/',

        dataframe=box.drop(labels=['patientId'], axis=1).replace(to_replace=float('nan'),value=0),

        target_size=(1024, 1024))

model = Sequential()

model.add(Conv2D(32, kernel_size=(3, 3),activation='linear',input_shape=(28,28,1),padding='same'))

model.add(LeakyReLU(alpha=0.1))

model.add(MaxPooling2D((2, 2),padding='same'))

model.add(Conv2D(64, (3, 3), activation='linear',padding='same'))

model.add(LeakyReLU(alpha=0.1))

model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Conv2D(128, (3, 3), activation='linear',padding='same'))

model.add(LeakyReLU(alpha=0.1))                  

model.add(MaxPooling2D(pool_size=(2, 2),padding='same'))

model.add(Flatten())

model.add(Dense(128, activation='linear'))

model.add(LeakyReLU(alpha=0.1))                  

model.add(Dense(num_classes, activation='softmax'))

model.compile(loss=keras.losses.categorical_crossentropy,

              optimizer=keras.optimizers.Adam(lr=1000,decay=.99),

              metrics=['accuracy'])

model.fit_generator(trainGen, steps_per_epoch=1024/16, epochs=317)

However, when I run this code, I get the following error

KeyError                                  Traceback (most recent call last)

<ipython-input-7-5a88afda8de5> in <module>

      7         directory='stage_1_train_images/',

      8         dataframe=box.drop(labels=['patientId'], axis=1).replace(to_replace=float('nan'),value=0),

----> 9         target_size=(1024, 1024))

     10 model = Sequential()

     11 model.add(Conv2D(32, kernel_size=(3, 3),activation='linear',input_shape=(28,28,1),padding='same'))



/opt/conda/lib/python3.6/site-packages/keras_preprocessing/image.py in flow_from_dataframe(self, dataframe, directory, x_col, y_col, has_ext, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, save_to_dir, save_prefix, save_format, subset, interpolation)

   1105                                  save_format=save_format,

   1106                                  subset=subset,

-> 1107                                  interpolation=interpolation)

   1108 

   1109     def standardize(self, x):



/opt/conda/lib/python3.6/site-packages/keras_preprocessing/image.py in __init__(self, dataframe, directory, image_data_generator, x_col, y_col, has_ext, target_size, color_mode, classes, class_mode, batch_size, shuffle, seed, data_format, save_to_dir, save_prefix, save_format, follow_links, subset, interpolation, dtype)

   2056             raise ValueError("has_ext must be either True if filenames in"

   2057                              " x_col has extensions,else False.")

-> 2058         self.df = dataframe.drop_duplicates(x_col)

   2059         self.df[x_col] = self.df[x_col].astype(str)

   2060         self.directory = directory



/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in drop_duplicates(self, subset, keep, inplace)

   4329         """

   4330         inplace = validate_bool_kwarg(inplace, 'inplace')

-> 4331         duplicated = self.duplicated(subset, keep=keep)

   4332 

   4333         if inplace:



/opt/conda/lib/python3.6/site-packages/pandas/core/frame.py in duplicated(self, subset, keep)

   4379         diff = Index(subset).difference(self.columns)

   4380         if not diff.empty:

-> 4381             raise KeyError(diff)

   4382 

   4383         vals = (col.values for name, col in self.iteritems()



KeyError: Index(['filename'], dtype='object')

What is going wrong? I have tried multiple things to fix this but cannot figure out why this is happening.

As per the documentation here, you need to specify x_col and y_col as arguments in the flow_from_dataframe method. The defaults for x_col and y_col are 'filename' and 'class', respectively. From the error, I'm guessing that you don't have a column named "filename" in your DataFrame which is what causes the KeyError. To fix this, specify the following two arguments in the flow_from_dataframe method.

x_col: string, column in the dataframe that contains
the filenames of the target images.

y_col: string or list of strings,columns in
the dataframe that will be the target data.