def __getitem__(self, batch_idx):
X_batch = np.zeros((self.batch_size, ) + self.target_size)
y_batch = np.zeros((self.batch_size, len(self.classes)))
filenames = []
labels = []
aux = []
current_index = batch_idx * self.batch_size
for i in range(self.batch_size):
filenames.append(self.filenames[current_index])
labels.append(self.labels[current_index])
if hasattr(self, "auxiliary"):
aux.append(self.auxiliary[current_index])
current_index += 1
color_mode = "rgb" if self.target_size[2] == 3 else "grayscale"
target_size = (self.target_size[0], self.target_size[1])
X_batch = np.array([
self.transformer.random_transform(
img_to_array(
load_img(fn,
color_mode=color_mode,
target_size=target_size))) for fn in filenames
])
y_batch = to_categorical(labels, num_classes=len(self.classes))
if hasattr(self, "auxiliary"):
return X_batch, [y_batch, aux]
else:
return X_batch, y_batch
def run(self):
model = load_model("./models/" + self.model_selected.get())
for i, img_path in enumerate(self.img_paths):
img_array = img_to_array(load_img(img_path,
color_mode="grayscale")) / 255
pred = predict(img_array, model, self.model_threshold_slider.get())
save_img(self.destination_path_field.get() + "/" + str(i) + ".png",
pred)
def _get_batches_of_transformed_samples(self, index_array):
"""Gets a batch of transformed samples.
# Arguments
index_array: Array of sample indices to include in batch.
# Returns
A batch of transformed samples.
"""
# build batch of image data
# self.filepaths is dynamic, is better to call it once outside the loop
filepaths = self.filepaths
# build batch of image data
batch_x = np.array([
load_img(filepaths[x],
color_mode=self.color_mode,
target_size=self.target_size,
interpolation=self.interpolation) for x in index_array
])
# transform the image data
batch_x = np.array(
[self.image_data_generator.transform_image(x) for x in batch_x])
# optionally save augmented images to disk for debugging purposes
if self.save_to_dir:
for i, j in enumerate(index_array):
img = array_to_img(batch_x[i], self.data_format, scale=True)
fname = '{prefix}_{index}_{hash}.{format}'.format(
prefix=self.save_prefix,
index=j,
hash=np.random.randint(1e7),
format=self.save_format)
img.save(os.path.join(self.save_to_dir, fname))
# build batch of labels
if self.class_mode == 'input':
batch_y = batch_x.copy()
elif self.class_mode in {'binary', 'sparse'}:
batch_y = np.empty(len(batch_x), dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i] = self.classes[n_observation]
elif self.class_mode == 'categorical':
batch_y = np.zeros((len(batch_x), len(self.class_indices)),
dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i, self.classes[n_observation]] = 1.
elif self.class_mode == 'multi_output':
batch_y = [output[index_array] for output in self.labels]
elif self.class_mode == 'raw':
batch_y = self.labels[index_array]
else:
return batch_x
if self.sample_weight is None:
return batch_x, batch_y
else:
return batch_x, batch_y, self.sample_weight[index_array]
def run(self):
model = load_model("./models/" + self.model_selected.get())
for img_path in self.img_paths:
img_array = img_to_array(load_img(img_path,
color_mode="grayscale")) / 255
pred = predict(img_array, model, self.model_threshold_slider.get())
save_img(
self.destination_path_field.get() + "/" +
os.path.splitext(img_path.split("/")[-1])[0] + ".png", pred)
def load(self, size=256, keep_proportions=True):
'''Load a dataset into RAM at a constant size'''
X = []
for i in glob2.glob(os.path.join(self.out_dir, '**')):
if not any([i.endswith(j) for j in self.image_extensions]):
continue
if os.path.basename(i).startswith('._'): continue
im = load_img(i)
if keep_proportions:
X.append(self.resize_to_square(im, size))
else:
X.append(im.resize(size, size))
return np.array(X)
def imagenet_generator(self):
if len(self.image_paths) == 0:
raise ValueError("Why do you not have image paths?")
indices = np.arange(len(self.image_paths))
while True:
_index = 0
# if shuffle, shuffle indices
if self.shuffle:
np.random.shuffle(indices)
# another loop keep track of generations for current epoch
while _index < len(self.image_paths) and \
_index < self.steps_per_epoch * self.batch:
# images and labels (classes) for the current batch
images_to_yield = []
labels_to_yield = []
# indices for current batch
indices_to_yield = indices[_index: _index + self.batch]
# assemble batch of images
_curr_img_paths = self.image_paths[indices_to_yield]
for _cip in _curr_img_paths:
x = img_to_array(load_img(_cip, target_size=self.img_size))
# preprocess Imagenet data
# https://github.com/keras-team/keras-applications/blob/master/keras_applications/mobilenet.py#L75-L84
pre_processed_img = iu.preprocess_input(
np.asarray(x), mode="tf")
images_to_yield.append(pre_processed_img)
# assemble batch of labels if there are any classes
if self.no_classes > 0:
for _cip in _curr_img_paths:
pl = path_leaf(_cip)[:-5]
labels_to_yield.append(self.cls_dict[pl])
_index += self.batch
yield (np.asarray(images_to_yield), np.asarray(labels_to_yield))
#!/usr/bin/python3
from keras.models import load_model
from keras_preprocessing.image.utils import load_img, img_to_array
import pandas as pd
import numpy as np
import os
ROW_TO_PREDICT = 300
df = pd.read_csv('../data_set/data.csv',
header=None,
names=['x_col', 'y_col', 'z_col'])[['x_col', 'y_col']]
model = load_model('best_model.h5')
path = os.path.join('../data_set/', df.iloc[ROW_TO_PREDICT]['x_col'])
print(path)
image = img_to_array(load_img(path, target_size=(32, 32)))
image = np.expand_dims(image, 0)
prediction = model.predict(image)
print(prediction)
horizontal_flip=True,
vertical_flip=True)
def check_dir(directory):
''' Checks if the target directory exists or not.
If it does not exist it will create one'''
if not os.path.exists(directory):
os.makedirs(directory)
def augmentation(x):
''' Here the actual data augmentation takes place'''
x = img_to_array(x)
x = x.reshape((1,) + x.shape)
i=0
for batch in datagenerator.flow(x, batch_size=1,
save_to_dir='preview', #Target directory/folder
save_prefix='images', #Name of augmented images
save_format='jpeg'): #Extension of target images
i += 1
if i > 5: #No of target images
break
x = load_img("F:/PV/canon eos 1500d/20180121213556_IMG_2535 (4).JPG") #Loading input image
check_dir('preview') #Target directory
augmentation(x)
def test_load_img(tmpdir):
filename_rgb = str(tmpdir / 'rgb_utils.png')
filename_rgba = str(tmpdir / 'rgba_utils.png')
filename_grayscale_8bit = str(tmpdir / 'grayscale_8bit_utils.png')
filename_grayscale_16bit = str(tmpdir / 'grayscale_16bit_utils.tiff')
filename_grayscale_32bit = str(tmpdir / 'grayscale_32bit_utils.tiff')
original_rgb_array = np.array(255 * np.random.rand(100, 100, 3),
dtype=np.uint8)
original_rgb = utils.array_to_img(original_rgb_array, scale=False)
original_rgb.save(filename_rgb)
original_rgba_array = np.array(255 * np.random.rand(100, 100, 4),
dtype=np.uint8)
original_rgba = utils.array_to_img(original_rgba_array, scale=False)
original_rgba.save(filename_rgba)
original_grayscale_8bit_array = np.array(255 * np.random.rand(100, 100, 1),
dtype=np.uint8)
original_grayscale_8bit = utils.array_to_img(original_grayscale_8bit_array,
scale=False)
original_grayscale_8bit.save(filename_grayscale_8bit)
original_grayscale_16bit_array = np.array(np.random.randint(
-2147483648, 2147483647, (100, 100, 1)),
dtype=np.int16)
original_grayscale_16bit = utils.array_to_img(
original_grayscale_16bit_array, scale=False, dtype='int16')
original_grayscale_16bit.save(filename_grayscale_16bit)
original_grayscale_32bit_array = np.array(np.random.randint(
-2147483648, 2147483647, (100, 100, 1)),
dtype=np.int32)
original_grayscale_32bit = utils.array_to_img(
original_grayscale_32bit_array, scale=False, dtype='int32')
original_grayscale_32bit.save(filename_grayscale_32bit)
# Test that loaded image is exactly equal to original.
loaded_im = utils.load_img(filename_rgb)
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgb_array.shape
assert np.all(loaded_im_array == original_rgb_array)
loaded_im = utils.load_img(filename_rgba, color_mode='rgba')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgba_array.shape
assert np.all(loaded_im_array == original_rgba_array)
loaded_im = utils.load_img(filename_rgb, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (original_rgb_array.shape[0],
original_rgb_array.shape[1], 1)
loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_grayscale_8bit_array.shape
assert np.all(loaded_im_array == original_grayscale_8bit_array)
loaded_im = utils.load_img(filename_grayscale_16bit,
color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == original_grayscale_16bit_array.shape
assert np.all(loaded_im_array == original_grayscale_16bit_array)
# test casting int16 image to float32
loaded_im_array = utils.img_to_array(loaded_im)
assert np.allclose(loaded_im_array, original_grayscale_16bit_array)
loaded_im = utils.load_img(filename_grayscale_32bit,
color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == original_grayscale_32bit_array.shape
assert np.all(loaded_im_array == original_grayscale_32bit_array)
# test casting int32 image to float32
loaded_im_array = utils.img_to_array(loaded_im)
assert np.allclose(loaded_im_array, original_grayscale_32bit_array)
# Test that nothing is changed when target size is equal to original.
loaded_im = utils.load_img(filename_rgb, target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgb_array.shape
assert np.all(loaded_im_array == original_rgb_array)
loaded_im = utils.load_img(filename_rgba,
color_mode='rgba',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgba_array.shape
assert np.all(loaded_im_array == original_rgba_array)
loaded_im = utils.load_img(filename_rgb,
color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (original_rgba_array.shape[0],
original_rgba_array.shape[1], 1)
loaded_im = utils.load_img(filename_grayscale_8bit,
color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_grayscale_8bit_array.shape
assert np.all(loaded_im_array == original_grayscale_8bit_array)
loaded_im = utils.load_img(filename_grayscale_16bit,
color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == original_grayscale_16bit_array.shape
assert np.all(loaded_im_array == original_grayscale_16bit_array)
loaded_im = utils.load_img(filename_grayscale_32bit,
color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == original_grayscale_32bit_array.shape
assert np.all(loaded_im_array == original_grayscale_32bit_array)
# Test down-sampling with bilinear interpolation.
loaded_im = utils.load_img(filename_rgb, target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 3)
loaded_im = utils.load_img(filename_rgba,
color_mode='rgba',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 4)
loaded_im = utils.load_img(filename_rgb,
color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_8bit,
color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_16bit,
color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_32bit,
color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == (25, 25, 1)
# Test down-sampling with nearest neighbor interpolation.
loaded_im_nearest = utils.load_img(filename_rgb,
target_size=(25, 25),
interpolation="nearest")
loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest)
assert loaded_im_array_nearest.shape == (25, 25, 3)
assert np.any(loaded_im_array_nearest != loaded_im_array)
loaded_im_nearest = utils.load_img(filename_rgba,
color_mode='rgba',
target_size=(25, 25),
interpolation="nearest")
loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest)
assert loaded_im_array_nearest.shape == (25, 25, 4)
assert np.any(loaded_im_array_nearest != loaded_im_array)
loaded_im = utils.load_img(filename_grayscale_8bit,
color_mode='grayscale',
target_size=(25, 25),
interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_16bit,
color_mode='grayscale',
target_size=(25, 25),
interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_32bit,
color_mode='grayscale',
target_size=(25, 25),
interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == (25, 25, 1)
# Check that exception is raised if interpolation not supported.
loaded_im = utils.load_img(filename_rgb, interpolation="unsupported")
with pytest.raises(ValueError):
loaded_im = utils.load_img(filename_rgb,
target_size=(25, 25),
interpolation="unsupported")
# Check that the aspect ratio of a square is the same
filename_red_square = str(tmpdir / 'red_square_utils.png')
A = np.zeros((50, 100, 3), dtype=np.uint8) # rectangle image 100x50
A[20:30, 45:55, 0] = 255 # red square 10x10
red_square_array = np.array(A)
red_square = utils.array_to_img(red_square_array, scale=False)
red_square.save(filename_red_square)
loaded_im = utils.load_img(filename_red_square,
target_size=(25, 25),
keep_aspect_ratio=True)
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 3)
red_channel_arr = loaded_im_array[:, :, 0].astype(np.bool)
square_width = np.sum(np.sum(red_channel_arr, axis=0))
square_height = np.sum(np.sum(red_channel_arr, axis=1))
aspect_ratio_result = square_width / square_height
# original square had 1:1 ratio
assert aspect_ratio_result == pytest.approx(1.0)
def _get_batches_of_transformed_samples(self, index_array):
"""Gets a batch of transformed samples.
# Arguments
index_array: Array of sample indices to include in batch.
# Returns
A batch of transformed samples.
"""
y = self.classes[index_array]
# creo una matrice indice - classe
batch = np.concatenate(
[np.expand_dims(index_array, 1),
np.expand_dims(y, 1)], axis=1)
batch = pd.DataFrame(batch, columns=['idx', 'class'])
batch = batch.groupby('class')
# Per ogni classe genero K sample
# batch totale 128
try:
batch = batch.apply(
lambda _x: _x.sample(18).reset_index(drop=True))
except ValueError:
batch = batch.apply(
lambda _x: _x.sample(18, replace=True).reset_index(drop=True))
print("This batch is garbage")
index_array = np.array(batch['idx'])
index_array = np.random.permutation(index_array)
batch_x = np.zeros((len(index_array), ) + self.image_shape,
dtype=self.dtype)
# build batch of image data
# self.filepaths is dynamic, is better to call it once outside the loop
filepaths = self.filepaths
for i, j in enumerate(index_array):
img = load_img(filepaths[j],
color_mode=self.color_mode,
target_size=self.target_size,
interpolation=self.interpolation)
x = img_to_array(img, data_format=self.data_format)
# Pillow images should be closed after `load_img`,
# but not PIL images.
if hasattr(img, 'close'):
img.close()
if self.image_data_generator:
params = self.image_data_generator.get_random_transform(
x.shape)
x = self.image_data_generator.apply_transform(x, params)
x = self.image_data_generator.standardize(x)
batch_x[i] = x
# optionally save augmented images to disk for debugging purposes
if self.save_to_dir:
for i, j in enumerate(index_array):
img = array_to_img(batch_x[i], self.data_format, scale=True)
fname = '{prefix}_{index}_{hash}.{format}'.format(
prefix=self.save_prefix,
index=j,
hash=np.random.randint(1e7),
format=self.save_format)
img.save(os.path.join(self.save_to_dir, fname))
# build batch of labels
if self.class_mode == 'input':
batch_y = batch_x.copy()
elif self.class_mode in {'binary', 'sparse'}:
batch_y = np.empty(len(batch_x), dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i] = self.classes[n_observation]
elif self.class_mode == 'categorical':
batch_y = np.zeros((len(batch_x), len(self.class_indices)),
dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i, self.classes[n_observation]] = 1.
elif self.class_mode == 'multi_output':
batch_y = [output[index_array] for output in self.labels]
elif self.class_mode == 'raw':
batch_y = self.labels[index_array]
else:
return batch_x
if self.sample_weight is None:
return [batch_x, batch_x, batch_x, np.argmax(batch_y, axis=1)],\
[np.zeros((len(batch_x), 4096), dtype='float16'), batch_y]
else:
return batch_x, batch_y, self.sample_weight[index_array]
def test_load_img_returns_image(tmpdir):
path = write_sample_image(tmpdir)
im = utils.load_img(path)
assert isinstance(im, PIL.Image.Image)
def test_image_file_handlers_close(tmpdir):
path = write_sample_image(tmpdir)
max_open_files, _ = resource.getrlimit(resource.RLIMIT_NOFILE)
for i in range(max_open_files + 1):
utils.load_img(path)
def read_np_picture(path, target_size=None, scale=1):
# img = PIL.Image.open(filename)
img = load_img(path, target_size=target_size)
img_np = np.asarray(img, dtype='uint8')
img_np = img_np * scale
return img_np
def visualize_camap(model, fold, test_imgs):
last_conv_layer = model.get_layer('block5_conv3')
iterateBE0 = get_iterates(0, 0, model, last_conv_layer)
iterateBE1 = get_iterates(0, 1, model, last_conv_layer)
iterateBE2 = get_iterates(0, 2, model, last_conv_layer)
iterateICM0 = get_iterates(1, 0, model, last_conv_layer)
iterateICM1 = get_iterates(1, 1, model, last_conv_layer)
iterateICM2 = get_iterates(1, 2, model, last_conv_layer)
iterateTE0 = get_iterates(2, 0, model, last_conv_layer)
iterateTE1 = get_iterates(2, 1, model, last_conv_layer)
iterateTE2 = get_iterates(2, 2, model, last_conv_layer)
CAM_DICT = {
"BE0": iterateBE0,
"BE1": iterateBE1,
"BE2": iterateBE2,
"ICM0": iterateICM0,
"ICM1": iterateICM1,
"ICM2": iterateICM2,
"TE0": iterateTE0,
"TE1": iterateTE1,
"TE2": iterateTE2
}
for img_name in test_imgs:
print(img_name)
img_arr = load_img(join(args.img_path, img_name),
color_mode='rgb',
target_size=(PATCH_SIZE, PATCH_SIZE))
img_arr = img_to_array(img_arr)
x = np.expand_dims(img_arr, axis=0)
# x = preprocess_input(x)
img = imread(join(args.img_path, img_name))
img = np.uint8(255 * resize(img, (img_arr.shape[1], img_arr.shape[0])))
preds = model.predict(x)
for i, grade in enumerate(['BE', 'ICM', 'TE']):
iterate = CAM_DICT["{}{}".format(grade, np.argmax(preds[i]))]
pooled_grads_value, conv_layer_output_value = iterate([x])
pooled_grads_value_resized = pooled_grads_value * np.ones(
conv_layer_output_value.shape)
temp = np.multiply(conv_layer_output_value,
pooled_grads_value_resized)
heatmap = np.mean(temp, axis=-1)
heatmap = np.maximum(heatmap, 0)
heatmap /= (np.max(heatmap) + K.epsilon())
heatmap = resize(heatmap, (img_arr.shape[1], img_arr.shape[0]))
heatmap = np.uint8(255 * heatmap)
plt.figure()
plt.imshow(heatmap, cmap=plt.get_cmap('jet'), alpha=0.4)
plt.imshow(gray2rgb(img), alpha=0.6)
cur_ax = plt.gca()
cur_ax.axes.get_xaxis().set_visible(False)
cur_ax.axes.get_yaxis().set_visible(False)
plt.savefig(join(
CAMAP_PATH,
img_name[:-4] + 'fold{}'.format(fold) + grade + img_name[-4:]),
bbox_inches='tight',
pad_inches=0)
plt.close()
def sample(self, X=None, sample_size=None, standardize=True):
""" Retrived fix-sized image tersors
Parameters
----------
X : 2D-array. Default is None
Expanded sub-index array of the dataframe.
If None, X = np.arange(n_samples)[:, np.newaxis].
sample_size : int. Default is None.
The number of samples to be retrieved.
If None, sample_size = X.shape[0]
standardize : bool. Default is True.
Whether to transform the image tersor data.
If False, return direct results of `img_to_array`.
"""
if X is None:
X = np.arange(self.dataframe.shape[0])[:, np.newaxis]
if not sample_size:
sample_size = X.shape[0]
retrieved_X = np.zeros((sample_size, ) + self.image_shape,
dtype=self.dtype)
filepaths = self.filepaths
indices = np.squeeze(X)
sample_index = self.rng_.choice(indices,
size=sample_size,
replace=False)
for i, j in enumerate(sample_index):
img = load_img(filepaths[j],
color_mode=self.color_mode,
target_size=self.target_size,
interpolation=self.interpolation)
x = img_to_array(img, data_format=self.data_format)
if hasattr(img, 'close'):
img.close()
if not standardize:
retrieved_X[i] = x
continue
params = self.get_random_transform(x.shape)
x = self.apply_transform(x, params)
x = self.standardize(x)
retrieved_X[i] = x
if self.save_to_dir:
for i, j in enumerate(sample_index):
img = array_to_img(retrieved_X[i],
self.data_format,
scale=True)
fname = '{prefix}_{index}_{hash}.{format}'.format(
prefix=self.save_prefix,
index=j,
hash=np.random.randint(1e7),
format=self.save_format)
img.save(os.path.join(self.save_to_dir, fname))
# retrieve labels
if self.class_mode == 'input':
retrieved_y = retrieved_X.copy()
elif self.class_mode in {'binary', 'sparse'}:
retrieved_y = np.empty(sample_size, dtype=self.dtype)
for i, n_observation in enumerate(sample_index):
retrieved_y[i] = self.classes[n_observation]
elif self.class_mode == 'categorical':
retrieved_y = np.zeros((sample_size, len(self.class_indices)),
dtype=self.dtype)
for i, n_observation in enumerate(sample_index):
retrieved_y[i, self.classes[n_observation]] = 1.
elif self.class_mode == 'multi_output':
retrieved_y = [output[sample_index] for output in self.labels]
elif self.class_mode == 'raw':
retrieved_y = self.labels[sample_index]
else:
return retrieved_X
return retrieved_X, retrieved_y
def _get_batches_of_transformed_samples(self, index_array):
"""Gets a batch of transformed samples.
# Arguments
index_array: Array of sample indices to include in batch.
# Returns
A batch of transformed samples in one-hot-encoded format.
"""
additional_bg_class = 0
if self.include_background:
additional_bg_class = 1
batch_x = np.zeros(
(len(index_array), ) + (self.target_size[0], self.target_size[1],
self.num_classes + additional_bg_class),
dtype=self.dtype)
# build batch of image data
# self.filepaths is dynamic, is better to call it once outside the loop
filepaths = self.filepaths
known_label_keys = self.dropped_labels_memory.keys()
known_label_drops = {}
unset_label_drops = []
for i, j in enumerate(index_array):
if j in known_label_keys:
known_label_drops[i] = j
else:
unset_label_drops.append(i)
one_hot_map = np.zeros((self.target_size[0], self.target_size[1],
self.num_classes + additional_bg_class),
dtype=np.float32)
# Iterate over all classes
params = None
reserved_pixels = None
for k in range(self.num_classes):
filepath = os.path.join(self.directory, self._mask_classes[k],
filepaths[j])
img = load_img(filepath,
color_mode=self.color_mode,
target_size=self.target_size,
interpolation=self.interpolation)
x = img_to_array(img, data_format=self.data_format)
# Pillow images should be closed after `load_img`,
# but not PIL images.
if hasattr(img, 'close'):
img.close()
if self.image_data_generator:
# Params need to be set once for every image (not for every mask)
if params is None:
params = self.image_data_generator.get_random_transform(
x.shape)
x = self.image_data_generator.apply_transform(x, params)
x = self.image_data_generator.standardize(x)
if reserved_pixels is None:
reserved_pixels = np.zeros(x.shape)
x = np.where(reserved_pixels, 0, x)
reserved_pixels += x
one_hot_map += self.get_one_hot_map(
x,
k,
background=self.background_color,
additional_bg_class=additional_bg_class)
# If one_hot_map has a max value >1 whe have overlapping classes -> prohibited
one_hot_map = one_hot_map.numpy()
if one_hot_map.max() > 1:
raise ValueError(
'Mask mismatch: classes are not mutually exclusive (multiple class definitions for '
'one pixel).')
if self.include_background:
# Background class is everywhere, where the one-hot encoding has only zeros
one_hot_map = tf.where(
tf.repeat(tf.reshape(
tf.math.count_nonzero(
one_hot_map == tf.zeros(self.num_classes + 1),
axis=2), [img.height, img.width, 1]),
self.num_classes + 1,
axis=2) == self.num_classes + 1,
tf.one_hot(
tf.constant(self.num_classes,
shape=one_hot_map.shape[:2]),
self.num_classes + 1), one_hot_map)
batch_x[i] = one_hot_map
# optionally save augmented images to disk for debugging purposes
if self.save_to_dir:
for i, j in enumerate(index_array):
img = array_to_img(batch_x[i], self.data_format, scale=True)
fname = '{prefix}_{index}_{hash}.{format}'.format(
prefix=self.save_prefix,
index=j,
hash=np.random.randint(1e7),
format=self.save_format)
img.save(os.path.join(self.save_to_dir, fname))
# Only where labels are not already known
if len(self.heterogeneously_labeled_masks) > 0:
batch_x[unset_label_drops] = self.remove_masks(
np.take(batch_x, unset_label_drops, axis=0))
# Known labels
for item in known_label_drops.items():
index_in_batch = item[0]
index_in_memory = item[1]
memory_binary_mask = self.dropped_labels_memory.get(
index_in_memory)
batch_x[index_in_batch, :, :, :][
memory_binary_mask] = DELETED_MASK_IDENTIFIER
# Extend Memory of known deletion masks.
delete_mask = np.where(batch_x == DELETED_MASK_IDENTIFIER, True,
False)
for i in range(len(index_array)):
self.dropped_labels_memory[index_array[i]] = delete_mask[
i, :, :, :]
return batch_x
def _get_batches_of_transformed_samples(self, index_array):
"""Gets a batch of transformed samples.
# Arguments
index_array: Array of sample indices to include in batch.
# Returns
A batch of transformed samples.
"""
index_array = self.X[index_array]
batch_x = np.zeros((len(index_array), ) + self.image_shape,
dtype=self.dtype)
# build batch of image data
# self.filepaths is dynamic, is better to call it once outside the loop
filepaths = self.filepaths
for i, j in enumerate(index_array):
img = load_img(filepaths[j],
color_mode=self.color_mode,
target_size=self.target_size,
interpolation=self.interpolation)
x = img_to_array(img, data_format=self.data_format)
# Pillow images should be closed after `load_img`,
# but not PIL images.
if hasattr(img, 'close'):
img.close()
if self.image_data_generator:
params = self.image_data_generator.get_random_transform(
x.shape)
x = self.image_data_generator.apply_transform(x, params)
x = self.image_data_generator.standardize(x)
batch_x[i] = x
# optionally save augmented images to disk for debugging purposes
if self.save_to_dir:
for i, j in enumerate(index_array):
img = array_to_img(batch_x[i], self.data_format, scale=True)
fname = '{prefix}_{index}_{hash}.{format}'.format(
prefix=self.save_prefix,
index=j,
hash=np.random.randint(1e7),
format=self.save_format)
img.save(os.path.join(self.save_to_dir, fname))
# build batch of labels
if self.class_mode == 'input':
batch_y = batch_x.copy()
elif self.class_mode in {'binary', 'sparse'}:
batch_y = np.empty(len(batch_x), dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i] = self.classes[n_observation]
elif self.class_mode == 'categorical':
batch_y = np.zeros((len(batch_x), len(self.class_indices)),
dtype=self.dtype)
for i, n_observation in enumerate(index_array):
batch_y[i, self.classes[n_observation]] = 1.
elif self.class_mode == 'multi_output':
batch_y = [output[index_array] for output in self.labels]
elif self.class_mode == 'raw':
batch_y = self.labels[index_array]
else:
return batch_x
if self.sample_weight is None:
return batch_x, batch_y
else:
return batch_x, batch_y, self.sample_weight[index_array]
def test_load_img(tmpdir):
filename_rgb = str(tmpdir / 'rgb_utils.png')
filename_rgba = str(tmpdir / 'rgba_utils.png')
filename_grayscale_8bit = str(tmpdir / 'grayscale_8bit_utils.png')
filename_grayscale_16bit = str(tmpdir / 'grayscale_16bit_utils.tiff')
filename_grayscale_32bit = str(tmpdir / 'grayscale_32bit_utils.tiff')
original_rgb_array = np.array(255 * np.random.rand(100, 100, 3),
dtype=np.uint8)
original_rgb = utils.array_to_img(original_rgb_array, scale=False)
original_rgb.save(filename_rgb)
original_rgba_array = np.array(255 * np.random.rand(100, 100, 4),
dtype=np.uint8)
original_rgba = utils.array_to_img(original_rgba_array, scale=False)
original_rgba.save(filename_rgba)
original_grayscale_8bit_array = np.array(255 * np.random.rand(100, 100, 1),
dtype=np.uint8)
original_grayscale_8bit = utils.array_to_img(original_grayscale_8bit_array,
scale=False)
original_grayscale_8bit.save(filename_grayscale_8bit)
original_grayscale_16bit_array = np.array(
np.random.randint(-2147483648, 2147483647, (100, 100, 1)), dtype=np.int16
)
original_grayscale_16bit = utils.array_to_img(original_grayscale_16bit_array,
scale=False, dtype='int16')
original_grayscale_16bit.save(filename_grayscale_16bit)
original_grayscale_32bit_array = np.array(
np.random.randint(-2147483648, 2147483647, (100, 100, 1)), dtype=np.int32
)
original_grayscale_32bit = utils.array_to_img(original_grayscale_32bit_array,
scale=False, dtype='int32')
original_grayscale_32bit.save(filename_grayscale_32bit)
# Test that loaded image is exactly equal to original.
loaded_im = utils.load_img(filename_rgb)
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgb_array.shape
assert np.all(loaded_im_array == original_rgb_array)
loaded_im = utils.load_img(filename_rgba, color_mode='rgba')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgba_array.shape
assert np.all(loaded_im_array == original_rgba_array)
loaded_im = utils.load_img(filename_rgb, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (original_rgb_array.shape[0],
original_rgb_array.shape[1], 1)
loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_grayscale_8bit_array.shape
assert np.all(loaded_im_array == original_grayscale_8bit_array)
loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == original_grayscale_16bit_array.shape
assert np.all(loaded_im_array == original_grayscale_16bit_array)
# test casting int16 image to float32
loaded_im_array = utils.img_to_array(loaded_im)
assert np.allclose(loaded_im_array, original_grayscale_16bit_array)
loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale')
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == original_grayscale_32bit_array.shape
assert np.all(loaded_im_array == original_grayscale_32bit_array)
# test casting int32 image to float32
loaded_im_array = utils.img_to_array(loaded_im)
assert np.allclose(loaded_im_array, original_grayscale_32bit_array)
# Test that nothing is changed when target size is equal to original.
loaded_im = utils.load_img(filename_rgb, target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgb_array.shape
assert np.all(loaded_im_array == original_rgb_array)
loaded_im = utils.load_img(filename_rgba, color_mode='rgba',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_rgba_array.shape
assert np.all(loaded_im_array == original_rgba_array)
loaded_im = utils.load_img(filename_rgb, color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (original_rgba_array.shape[0],
original_rgba_array.shape[1], 1)
loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == original_grayscale_8bit_array.shape
assert np.all(loaded_im_array == original_grayscale_8bit_array)
loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == original_grayscale_16bit_array.shape
assert np.all(loaded_im_array == original_grayscale_16bit_array)
loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale',
target_size=(100, 100))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == original_grayscale_32bit_array.shape
assert np.all(loaded_im_array == original_grayscale_32bit_array)
# Test down-sampling with bilinear interpolation.
loaded_im = utils.load_img(filename_rgb, target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 3)
loaded_im = utils.load_img(filename_rgba, color_mode='rgba',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 4)
loaded_im = utils.load_img(filename_rgb, color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale',
target_size=(25, 25))
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == (25, 25, 1)
# Test down-sampling with nearest neighbor interpolation.
loaded_im_nearest = utils.load_img(filename_rgb, target_size=(25, 25),
interpolation="nearest")
loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest)
assert loaded_im_array_nearest.shape == (25, 25, 3)
assert np.any(loaded_im_array_nearest != loaded_im_array)
loaded_im_nearest = utils.load_img(filename_rgba, color_mode='rgba',
target_size=(25, 25),
interpolation="nearest")
loaded_im_array_nearest = utils.img_to_array(loaded_im_nearest)
assert loaded_im_array_nearest.shape == (25, 25, 4)
assert np.any(loaded_im_array_nearest != loaded_im_array)
loaded_im = utils.load_img(filename_grayscale_8bit, color_mode='grayscale',
target_size=(25, 25), interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im)
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_16bit, color_mode='grayscale',
target_size=(25, 25), interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im, dtype='int16')
assert loaded_im_array.shape == (25, 25, 1)
loaded_im = utils.load_img(filename_grayscale_32bit, color_mode='grayscale',
target_size=(25, 25), interpolation="nearest")
loaded_im_array = utils.img_to_array(loaded_im, dtype='int32')
assert loaded_im_array.shape == (25, 25, 1)
# Check that exception is raised if interpolation not supported.
loaded_im = utils.load_img(filename_rgb, interpolation="unsupported")
with pytest.raises(ValueError):
loaded_im = utils.load_img(filename_rgb, target_size=(25, 25),
interpolation="unsupported")
def get_images(paths: list, WH):
"""Get resized images by <WH>"""
return np.array(
[np.array(load_img(file_name, target_size=WH)) for file_name in paths])
