labels_name = argv[2]
coords_name = argv[3]
AI_saved_dir = argv[5]
data, tracer, coords = astro_mnist.read_data_sets(images_name,
labels_name,
coords_name,
train_weight=0,
validation_weight=0,
test_weight=1)
print("Size of:")
print("- Training-set:\t\t{}".format(len(data.train.labels)))
print("- Test-set:\t\t{}".format(len(data.test.labels)))
print("- Validation-set:\t{}".format(len(data.validation.labels)))
data.test.cls = np.argmax(data.test.labels, axis=1)
# save arrangement and coords
failure = save_arrangement(images_name[:-4], directory, data, tracer)
if not failure:
print("tracer and data is saved.")
failure = save_coords(images_name[:-4], directory, coords)
if not failure:
print("coords are saved.")
#-----------------------------------
# Data dimension
# We know that MNIST images are 28 pixels in each dimension.
img_size = len(data.test.images[0])
print("image size = {0}".format(img_size))
# Images are stored in one-dimensional arrays of this length.
img_size_flat = img_size * 1
# Tuple with height and width of images used to reshape arrays.
img_shape = (img_size, 1)
# Number of colour channels for the images: 1 channel for gray-scale.
equal_batch = False
else:
print ("Wrong batch_format option")
exit()
#------------------------------------
# Load Data
# We should play a mask on image
print ("starting time: {0}".format(time_stamp))
data, tracer, coords = astro_mnist.read_data_sets(images_name, labels_name, coords_name)
print("Size of:")
print("- Training-set:\t\t{}".format(len(data.train.labels)))
print("- Test-set:\t\t{}".format(len(data.test.labels)))
print("- Validation-set:\t{}".format(len(data.validation.labels)))
#-----------------------------------
# save arrangement and coords
failure = save_arrangement(images_name[:-4], time_stamp, data, tracer)
if not failure:
print ("tracers and data are saved.")
failure = save_coords(images_name[:-4], time_stamp, coords)
if not failure:
print ("coords are saved.")
#-----------------------------------
# Data dimension
img_maj = imply_mask.count('0')
width_of_data = None
pick_band_array = None
if consider_error == 'yes':
width_of_data = 2
repeat_imply_mask = imply_mask + imply_mask
pick_band_array = np.where(np.array(list(repeat_imply_mask), dtype = int) == 0)
elif consider_error == 'no':
VERBOSE = 0
# measure times
start_time = time.time()
time_stamp = argv[3]
#-----------------------------------
# Load Data
images_name = argv[1]
labels_name = argv[2]
data, tracer = astro_mnist.read_data_sets(images_name, labels_name)
print("Size of:")
print("- Training-set:\t\t{}".format(len(data.train.labels)))
print("- Test-set:\t\t{}".format(len(data.test.labels)))
print("- Validation-set:\t{}".format(len(data.validation.labels)))
data.test.cls = np.argmax(data.test.labels, axis=1)
# save the distribution
if save_arrangement(argv, time_stamp, data, tracer):
print("tracer and data is saved.")
#-----------------------------------
# Data dimension
# We know that from the length of a data.
img_size = len(data.train.images[0])
print("image size = {0}".format(img_size))
# Images are stored in one-dimensional arrays of this length.
img_size_flat = img_size * 1
# Tuple with height and width of images used to reshape arrays.
img_shape = (img_size, 1)
# Number of colour channels for the images: 1 channel for gray-scale.
num_channels = 1
# Number of classes, one class for each of 10 digits.
num_classes = 3
# the number of iterations