def create_mnist_dataset():
images, labels = get_mnist_raw_data()
mask = labels != 0
print("Pre-zero removal: Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(labels))]))
images = list(itertools.compress(images, mask))
labels = labels[mask]
images = images[3::20]
labels = labels[3::20]
print("Pre-blobify: Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(labels))]))
y = np.array(labels, 'int8')
images, mask = blobify(images)
y = y[mask]
print("Post-blobify: Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(y))]))
print("Extract features...")
X = np.array([extract_efd_features(img) for img in images])
try:
os.makedirs(os.path.expanduser('~/sudokuextract'))
except:
pass
try:
for i, (img, lbl) in enumerate(zip(images, labels)):
img = Image.fromarray(img, 'L')
with open(os.path.expanduser('~/sudokuextract/{1}_{0:04d}.jpg'.format(i + 1, lbl)), 'w') as f:
img.save(f)
except Exception as e:
print(e)
return images, labels, X, y
def create_mnist_dataset():
images, labels = get_mnist_raw_data()
mask = labels != 0
print("Pre-zero removal: Label / N : {0}".format([
(v, c) for v, c in zip(_range(10), np.bincount(labels))
]))
images = list(itertools.compress(images, mask))
labels = labels[mask]
images = images[3::20]
labels = labels[3::20]
print("Pre-blobify: Label / N : {0}".format([
(v, c) for v, c in zip(_range(10), np.bincount(labels))
]))
y = np.array(labels, 'int8')
images, mask = blobify(images)
y = y[mask]
print("Post-blobify: Label / N : {0}".format([
(v, c) for v, c in zip(_range(10), np.bincount(y))
]))
print("Extract features...")
X = np.array([extract_efd_features(img) for img in images])
try:
os.makedirs(os.path.expanduser('~/sudokuextract'))
except:
pass
try:
for i, (img, lbl) in enumerate(zip(images, labels)):
img = Image.fromarray(img, 'L')
with open(
os.path.expanduser(
'~/sudokuextract/{1}_{0:04d}.jpg'.format(i + 1, lbl)),
'w') as f:
img.save(f)
except Exception as e:
print(e)
return images, labels, X, y
def create_data_set_from_images(path_to_data_dir, force=False):
try:
import matplotlib.pyplot as plt
except ImportError:
print("This method requires matplotlib installed...")
return
images = []
labels = []
path_to_data_dir = os.path.abspath(os.path.expanduser(path_to_data_dir))
_, _, files = next(os.walk(path_to_data_dir))
for f in files:
file_name, file_ext = os.path.splitext(f)
if file_ext in ('.jpg', '.png',
'.bmp') and "{0}.txt".format(file_name) in files:
# The current file is an image and it has a corresponding text file as reference.
# Use it as data.
print("Handling {0}...".format(f))
image = Image.open(os.path.join(path_to_data_dir, f))
with open(
os.path.join(path_to_data_dir,
"{0}.txt".format(file_name)), 'rt') as f:
parsed_img = f.read().strip().split('\n')
for sudoku, subimage in _extraction_iterator_map(
np.array(image.convert('L'))):
if not force:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
ax = plt.subplot2grid((9, 9), (k, kk))
ax.imshow(sudoku[k][kk], plt.cm.gray)
ax.set_title(str(parsed_img[k][kk]))
ax.axis('off')
plt.show()
ok = raw_input("Is this OK (Y/n/a)? ")
if ok.lower() == 'a':
break
elif ok.lower() == 'n':
continue
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
for sudoku, subimage in _extraction_iterator_map(
np.array(image.convert('L')), use_local_thresholding=True):
if not force:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
ax = plt.subplot2grid((9, 9), (k, kk))
ax.imshow(sudoku[k][kk], plt.cm.gray)
ax.set_title(str(parsed_img[k][kk]))
ax.axis('off')
plt.show()
ok = raw_input("Is this OK (Y/n/a)? ")
if ok.lower() == 'a':
break
elif ok.lower() == 'n':
continue
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
try:
os.makedirs(os.path.expanduser('~/sudokuextract'))
except:
pass
try:
for i, (img, lbl) in enumerate(zip(images, labels)):
img = Image.fromarray(img, 'L')
with open(
os.path.expanduser(
'~/sudokuextract/{1}_{0:04d}.jpg'.format(i + 1, lbl)),
'w') as f:
img.save(f)
except Exception as e:
print(e)
print("Pre-blobify: Label / N : {0}".format([
(v, c) for v, c in zip(_range(10), np.bincount(labels))
]))
y = np.array(labels, 'int8')
images, mask = blobify(images)
y = y[mask]
print("Post-blobify: Label / N : {0}".format([
(v, c) for v, c in zip(_range(10), np.bincount(y))
]))
print("Extract features...")
X = np.array([extract_efd_features(img) for img in images])
return images, labels, X, y
def create_data_set_from_images(path_to_data_dir, force=False):
try:
import matplotlib.pyplot as plt
except ImportError:
print("This method requires matplotlib installed...")
return
images = []
labels = []
path_to_data_dir = os.path.abspath(os.path.expanduser(path_to_data_dir))
_, _, files = next(os.walk(path_to_data_dir))
for f in files:
file_name, file_ext = os.path.splitext(f)
if file_ext in ('.jpg', '.png', '.bmp') and "{0}.txt".format(file_name) in files:
# The current file is an image and it has a corresponding text file as reference.
# Use it as data.
print("Handling {0}...".format(f))
image = Image.open(os.path.join(path_to_data_dir, f))
with open(os.path.join(path_to_data_dir, "{0}.txt".format(file_name)), 'rt') as f:
parsed_img = f.read().strip().split('\n')
for sudoku, subimage in _extraction_iterator_map(np.array(image.convert('L'))):
if not force:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
ax = plt.subplot2grid((9, 9), (k, kk))
ax.imshow(sudoku[k][kk], plt.cm.gray)
ax.set_title(str(parsed_img[k][kk]))
ax.axis('off')
plt.show()
ok = raw_input("Is this OK (Y/n/a)? ")
if ok.lower() == 'a':
break
elif ok.lower() == 'n':
continue
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
for sudoku, subimage in _extraction_iterator_map(np.array(image.convert('L')), use_local_thresholding=True):
if not force:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
ax = plt.subplot2grid((9, 9), (k, kk))
ax.imshow(sudoku[k][kk], plt.cm.gray)
ax.set_title(str(parsed_img[k][kk]))
ax.axis('off')
plt.show()
ok = raw_input("Is this OK (Y/n/a)? ")
if ok.lower() == 'a':
break
elif ok.lower() == 'n':
continue
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
else:
for k in range(len(sudoku)):
for kk in range(len(sudoku[k])):
images.append(sudoku[k][kk].copy())
labels.append(int(parsed_img[k][kk]))
break
try:
os.makedirs(os.path.expanduser('~/sudokuextract'))
except:
pass
try:
for i, (img, lbl) in enumerate(zip(images, labels)):
img = Image.fromarray(img, 'L')
with open(os.path.expanduser('~/sudokuextract/{1}_{0:04d}.jpg'.format(i+1, lbl)), 'w') as f:
img.save(f)
except Exception as e:
print(e)
print("Pre-blobify: Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(labels))]))
y = np.array(labels, 'int8')
images, mask = blobify(images)
y = y[mask]
print("Post-blobify: Label / N : {0}".format([(v, c) for v, c in zip(_range(10), np.bincount(y))]))
print("Extract features...")
X = np.array([extract_efd_features(img) for img in images])
return images, labels, X, y
