I am trying to make a binary classification using Keras' Conv2D classes based on this blog. I have many files with a matrix of floating point numbers in each one (these matrices are not pixels values). They are stored in separate folders that are named after each class. The problem is that don't really know:
- can or should I treat these matrices as images?
- Each matrix is of constant rows number and varying number of columns and I don't know how to feed a CNN with such data, but to transform it to an image and then resize. I found this How to train a CNN with non-squared data? but I don't know how to apply this.
The matrices are coefficients values. You can think of those values as if you were trying to make a height map of some piece of land. You'd make a mesh out if this land, measure the height (let's say that you take 300 m.a.s.l as a reference point) in each corner of each square of the mesh and then put that value into an array. At the end, if you plot that array you'd obtain a rough 3D land map. Then you feed a CNN with that data and make a binary classification whether such a terrain is hilly or lowland. I can transform that data into an image (although I think I'll lose some relevant information then) and then feed a CNN with these images.
What I've done so far
I grabbed some lines from keras.preprocessing.image.NumpyArrayIterator and keras.preprocessing.image.DirectoryIterator classes and combined them together so that I could read Matlab's .mat files:
import multiprocessing.pool
import os
from functools import partial
import h5py
import numpy as np
from keras import backend as K
from keras.preprocessing.image import Iterator, _count_valid_files_in_directory, _list_valid_filenames_in_directory, \
ImageDataGenerator
class MatFileIterGenerator(object):
def __init__(self):
self.image_data_generator = ImageDataGenerator()
def flow_from_directory(self, directory, variable,
target_size=(256, 256), classes=None, class_mode='categorical',
batch_size=32, shuffle=True, seed=None,
follow_links=False,
interpolation='nearest'):
return MatFilesIterator(
directory, variable, self.image_data_generator,
classes=classes, class_mode=class_mode,
batch_size=batch_size, shuffle=shuffle, seed=seed,
follow_links=follow_links,
interpolation=interpolation)
class MatFilesIterator(Iterator):
def __init__(self, directory, variable, image_data_generator, classes=None, class_mode="categorical",
batch_size=32, shuffle=True, seed=None, interpolation='nearest', follow_links=False):
self.variable = variable
self.directory = directory
self.image_data_generator = image_data_generator
self.data_format = K.image_data_format()
self.classes = classes
if class_mode not in {'categorical', 'binary', 'sparse',
'input', None}:
raise ValueError('Invalid class_mode:', class_mode,
'; expected one of "categorical", '
'"binary", "sparse", "input"'
' or None.')
self.class_mode = class_mode
self.interpolation = interpolation
white_list_formats = {"mat"}
# first, count the number of samples and classes
self.samples = 0
if not classes:
classes = []
for subdir in sorted(os.listdir(directory)):
if os.path.isdir(os.path.join(directory, subdir)):
classes.append(subdir)
self.num_classes = len(classes)
self.class_indices = dict(zip(classes, range(len(classes))))
pool = multiprocessing.pool.ThreadPool()
function_partial = partial(_count_valid_files_in_directory,
white_list_formats=white_list_formats,
follow_links=follow_links)
self.samples = sum(pool.map(function_partial,
(os.path.join(directory, subdir)
for subdir in classes)))
print('Found %d files belonging to %d classes.' % (self.samples, self.num_classes))
# second, build an index of the images in the different class subfolders
results = []
self.filenames = []
self.classes = np.zeros((self.samples,), dtype='int32')
i = 0
for dirpath in (os.path.join(directory, subdir) for subdir in classes):
results.append(pool.apply_async(_list_valid_filenames_in_directory,
(dirpath, white_list_formats,
self.class_indices, follow_links)))
for res in results:
classes, filenames = res.get()
self.classes[i:i + len(classes)] = classes
self.filenames += filenames
i += len(classes)
pool.close()
pool.join()
super(MatFilesIterator, self).__init__(self.samples, batch_size, shuffle, seed)
def _get_batches_of_transformed_samples(self, index_array):
# The script fails here with mentioned error
# 60 is the mentioned constant row numbers
batch_x = np.zeros(tuple([len(index_array)] + [60]), dtype=K.floatx())
# build batch of numpy data
for i, j in enumerate(index_array):
fname = self.filenames[j]
arr = np.array(h5py.File(os.path.join(self.directory, fname), "r").get(self.variable))
arr = self.image_data_generator.random_transform(arr.astype(K.floatx()))
arr = self.image_data_generator.standardize(arr)
batch_x[i] = arr
# build batch of labels
if self.class_mode == 'input':
batch_y = batch_x.copy()
elif self.class_mode == 'sparse':
batch_y = self.classes[index_array]
elif self.class_mode == 'binary':
batch_y = self.classes[index_array].astype(K.floatx())
elif self.class_mode == 'categorical':
batch_y = np.zeros((len(batch_x), self.num_classes), dtype=K.floatx())
for i, label in enumerate(self.classes[index_array]):
batch_y[i, label] = 1.
else:
return batch_x
return batch_x, batch_y
def next(self):
"""For python 2.x.
# Returns
The next batch.
"""
with self.lock:
index_array = next(self.index_generator)
# The transformation of images is not under thread lock
# so it can be done in parallel
return self._get_batches_of_transformed_samples(index_array)
I also coded simple CNN:
from keras.layers import Activation, Conv2D, MaxPooling2D, GlobalMaxPooling2D, Dense, Dropout
from keras.models import Sequential
from matfileiter import MatFileIterGenerator
class CNN2D:
def __init__(self):
self._model = Sequential()
self._model.add(Conv2D(60, (3, 3), input_shape=(60, None , 1)))
self._model.add(Activation("relu"))
self._model.add(MaxPooling2D(pool_size=(3, 3)))
self._model.add(Conv2D(60, (3, 3)))
self._model.add(Activation("relu"))
self._model.add(MaxPooling2D(pool_size=(3, 3)))
self._model.add(Conv2D(120, (3, 3)))
self._model.add(Activation("relu"))
self._model.add(MaxPooling2D(pool_size=(3, 3)))
self._model.add(GlobalMaxPooling2D())
self._model.add(Dense(120))
self._model.add(Activation('relu'))
self._model.add(Dropout(0.2))
self._model.add(Dense(1))
self._model.add(Activation('sigmoid'))
self._model.compile(loss='binary_crossentropy', optimizer='rmsprop', metrics=['accuracy'])
def createGenerators(self, train_path, variable, test_path, batch_size):
train_datagen = MatFileIterGenerator()
self._train_generator = train_datagen.flow_from_directory(
train_path,
variable,
shuffle=True,
batch_size=batch_size,
class_mode="binary")
test_datagen = MatFileIterGenerator()
self._test_generator = test_datagen.flow_from_directory(
test_path,
variable,
shuffle=True,
batch_size=batch_size,
class_mode="binary")
def train_model(self, batch_size):
self._model.fit_generator(
self._train_generator,
steps_per_epoch=2000 // batch_size,
epochs=50,
validation_data=self._test_generator,
validation_steps=800 // batch_size,
workers=2,
use_multiprocessing=True)
if __name__ == '__main__':
cnn = CNN2D()
cnn.createGenerators("/home/wilson/Documents/Data/_train_mat", "coeffs",
"/home/wilosn/Documents/Data/_eval_mat", 20)
cnn.train_model(20)
Currently the scipt fails with an error could not broadcast input array from shape (212,60) into shape (60) where the 212 is columns number of some randomly selected file (shuffled). I can transform these matrices into images in Matlab and then use standard DirectoryIterator on them but I want to try raw numbers first.
