def load_dataset_in_memory_and_resize(data_access, set, division, dataset_path, targets_path, tmp_size,
final_size, batch_size):
if data_access == "in-memory":
with timer("Loading %s data"%set):
dataset = InMemoryDataset(set, dataset_path, source_targets=targets_path, division=division)
draw_data = np.copy(dataset.dataset)
targets = np.copy(dataset.targets)
del dataset
elif data_access == "fuel":
with timer("Loading %s data"%set):
dataset = FuelDataset(set, tmp_size, batch_size=batch_size, shuffle=False, division=division)
draw_data,targets = dataset.return_whole_dataset()
del dataset
else:
raise Exception("Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."%data_access)
if tmp_size != final_size:
# Resize images from the validset
out = np.zeros((draw_data.shape[0], final_size[0], final_size[1], final_size[2]), dtype="float32")
with timer("Resizing %s images"%set):
for i in range(draw_data.shape[0]):
out[i] = resize_pil(draw_data[i], final_size[0:2])
del draw_data
return out, targets
else:
return draw_data, targets
def check_preprocessed_data(data_access, dataset, targets, batch_size, tmp_size, final_size, preprocessing_func,
preprocessing_args, n=10):
if data_access=="in-memory":
train_dataset = InMemoryDataset("train", source=dataset, batch_size=batch_size, source_targets=targets)
elif data_access=="fuel":
train_dataset = FuelDataset("test", tmp_size, batch_size=batch_size, division="leaderboard", shuffle=False)
else:
raise Exception("Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."%data_access)
# Compute only one batch
start=time.time()
batch,batch_targets = train_dataset.get_batch()
batch_targets = convert_labels(batch_targets)
processed_batch = np.zeros((batch.shape[0],final_size[2],final_size[0],final_size[1]),
dtype="float32")
for k in range(batch_size):
processed_batch[k] = preprocessing_func(batch[k], *preprocessing_args).transpose(2,0,1)
end=time.time()
print "Batch Shape = ", processed_batch.shape, "with dtype =", processed_batch.dtype
print "Targets Shape =", batch_targets.shape, "with dtype =", batch_targets.dtype
for i in range(n):
plt.figure(0)
plt.gray()
plt.clf()
plt.title("(%d,%d)"%(batch_targets[i][0], batch_targets[i][1]))
if batch.shape[1]==3:
plt.imshow(processed_batch[i].transpose(1,2,0))
else:
plt.imshow(processed_batch[i,0])
plt.show()
print "Processing 1 batch took : %.5f"%(end-start)
def check_preprocessed_data(data_access,
dataset,
targets,
batch_size,
tmp_size,
final_size,
preprocessing_func,
preprocessing_args,
n=10):
if data_access == "in-memory":
train_dataset = InMemoryDataset("train",
source=dataset,
batch_size=batch_size,
source_targets=targets)
elif data_access == "fuel":
train_dataset = FuelDataset("test",
tmp_size,
batch_size=batch_size,
division="leaderboard",
shuffle=False)
else:
raise Exception(
"Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."
% data_access)
# Compute only one batch
start = time.time()
batch, batch_targets = train_dataset.get_batch()
batch_targets = convert_labels(batch_targets)
processed_batch = np.zeros(
(batch.shape[0], final_size[2], final_size[0], final_size[1]),
dtype="float32")
for k in range(batch_size):
processed_batch[k] = preprocessing_func(batch[k],
*preprocessing_args).transpose(
2, 0, 1)
end = time.time()
print "Batch Shape = ", processed_batch.shape, "with dtype =", processed_batch.dtype
print "Targets Shape =", batch_targets.shape, "with dtype =", batch_targets.dtype
for i in range(n):
plt.figure(0)
plt.gray()
plt.clf()
plt.title("(%d,%d)" % (batch_targets[i][0], batch_targets[i][1]))
if batch.shape[1] == 3:
plt.imshow(processed_batch[i].transpose(1, 2, 0))
else:
plt.imshow(processed_batch[i, 0])
plt.show()
print "Processing 1 batch took : %.5f" % (end - start)
def features_generator(data_access, dataset, targets, batch_size, tmp_size,
final_size, bagging_size, bagging_iterator,
multiple_input, preprocessing_func, preprocessing_args,
pretrained_model):
# Instantiate the dataset
if data_access == "in-memory":
train_dataset = InMemoryDataset("train",
source=dataset,
batch_size=batch_size,
source_targets=targets)
elif data_access == "fuel":
train_dataset = FuelDataset("train",
tmp_size,
batch_size=batch_size,
bagging=bagging_size,
bagging_iterator=bagging_iterator)
else:
raise Exception(
"Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."
% data_access)
# Generator loop
while 1:
# Get next batch
processed_batch, labels = get_next_batch(train_dataset, batch_size,
final_size,
preprocessing_func,
preprocessing_args)
if multiple_input == 1:
features = pretrained_model.predict(processed_batch)
yield features, labels
else:
features = pretrained_model.predict(
[processed_batch for i in range(multiple_input)])
yield features, labels
def multi_features_generator(data_access,
dataset,
targets,
batch_size,
tmp_size,
final_size,
bagging_size,
bagging_iterator,
multiple_input,
preprocessing_func,
preprocessing_args,
pretrained_models,
mode="concat"):
# Instantiate the dataset
if data_access == "in-memory":
train_dataset = InMemoryDataset("train",
source=dataset,
batch_size=batch_size,
source_targets=targets)
elif data_access == "fuel":
train_dataset = FuelDataset("train",
tmp_size,
batch_size=batch_size,
bagging=bagging_size,
bagging_iterator=bagging_iterator)
else:
raise Exception(
"Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."
% data_access)
# Generator loop
while 1:
# Get next batch
processed_batch, labels = get_next_batch(train_dataset, batch_size,
final_size,
preprocessing_func,
preprocessing_args)
if multiple_input == 1:
features = []
for pretrained_model in pretrained_models:
features.append(
pretrained_model.predict(processed_batch, batch_size=1))
if mode == "concat":
features = np.concatenate(features, axis=1)
yield features, labels
else:
raise Exception("Generator does not work with multiple inputs")
def images_generator(data_access, dataset, targets, batch_size, tmp_size,
final_size, bagging_size, bagging_iterator,
multiple_input, division, preprocessing_func,
preprocessing_args):
"""
Generator function used when using the keras function 'fit_on_generator'. Can work with InMemoryDataset, FuelDataset.
Yield a tuple to the training containing a processed batch and
targets. This can be done on the CPU, in parallel of a GPU training. See 'fit_on_generator' for more details.
:param data_access: "in-memory" or "fuel"
:param dataset: path to the dataset numpy file (not used when data_acces = "fuel")
:param targets: path to the targets numpy file (not used when data_acces = "fuel")
:param batch_size:
:param tmp_size: Used when data_access == "fuel". Datastream will return images of size equal to tmp_size.
:param final_size: size of images used for the training
:param preprocessing_func: function which will be applied to each training batch
:param preprocessing_args: arguments of the preprocessing function
:return: tuple(batch,targets)
"""
if data_access == "in-memory":
train_dataset = InMemoryDataset("train",
source=dataset,
batch_size=batch_size,
source_targets=targets,
division=division)
elif data_access == "fuel":
train_dataset = FuelDataset("train",
tmp_size,
batch_size=batch_size,
bagging=bagging_size,
bagging_iterator=bagging_iterator,
division=division)
else:
raise Exception(
"Data access not available. Must be 'fuel' or 'in-memory'. Here : %s."
% data_access)
while 1:
# Get next batch
processed_batch, labels = get_next_batch(train_dataset, batch_size,
final_size,
preprocessing_func,
preprocessing_args)
if multiple_input == 1:
yield processed_batch, labels
else:
yield [processed_batch for i in range(multiple_input)], labels
