def pil_imagenet_loader(path, imsize, bounding_box=None, preprocess=True):
"""Pillow loader for the images.
Args:
path: Path to image to be loaded.
imsize: Integer, defines the maximum size of longer image side.
bounding_box: (x1,y1,x2,y2) tuple to crop the query image.
preprocess: Bool, whether to preprocess the images in respect to the
ImageNet dataset.
Returns:
image: `Tensor`, image in ImageNet suitable format.
"""
img = image_loading_utils.RgbLoader(path)
if bounding_box is not None:
imfullsize = max(img.size)
img = img.crop(bounding_box)
imsize = imsize * max(img.size) / imfullsize
# Unlike `resize`, `thumbnail` resizes to the largest size that preserves
# the aspect ratio, making sure that the output image does not exceed the
# original image size and the size specified in the arguments of thumbnail.
img.thumbnail((imsize, imsize), Image.ANTIALIAS)
img = np.array(img)
if preprocess:
# Preprocessing for ImageNet data. Converts the images from RGB to BGR,
# then zero-centers each color channel with respect to the ImageNet
# dataset, without scaling.
tf.keras.applications.imagenet_utils.preprocess_input(img,
mode='caffe')
return img
def main(unused_argv):
# Read list of images.
print('Reading list of images...')
image_paths = _ReadImageList(cmd_args.list_images_path)
num_images = len(image_paths)
print(f'done! Found {num_images} images')
# Parse DelfConfig proto.
config = delf_config_pb2.DelfConfig()
with tf.io.gfile.GFile(cmd_args.config_path, 'r') as f:
text_format.Merge(f.read(), config)
# Create output directory if necessary.
if not tf.io.gfile.exists(cmd_args.output_dir):
tf.io.gfile.makedirs(cmd_args.output_dir)
# Tell TensorFlow that the model will be built into the default Graph.
with tf.Graph().as_default():
with tf.compat.v1.Session() as sess:
init_op = tf.compat.v1.global_variables_initializer()
sess.run(init_op)
extractor_fn = extractor.MakeExtractor(sess, config)
start = time.clock()
for i in range(num_images):
# Write to log-info once in a while.
if i == 0:
print('Starting to extract DELF features from images...')
elif i % _STATUS_CHECK_ITERATIONS == 0:
elapsed = (time.clock() - start)
print(
f'Processing image {i} out of {num_images}, last '
f'{_STATUS_CHECK_ITERATIONS} images took {elapsed} seconds'
)
start = time.clock()
# If descriptor already exists, skip its computation.
out_desc_filename = os.path.splitext(os.path.basename(
image_paths[i]))[0] + _DELF_EXT
out_desc_fullpath = os.path.join(cmd_args.output_dir, out_desc_filename)
if tf.io.gfile.exists(out_desc_fullpath):
print(f'Skipping {image_paths[i]}')
continue
im = np.array(utils.RgbLoader(image_paths[i]))
# Extract and save features.
extracted_features = extractor_fn(im)
locations_out = extracted_features['local_features']['locations']
descriptors_out = extracted_features['local_features']['descriptors']
feature_scales_out = extracted_features['local_features']['scales']
attention_out = extracted_features['local_features']['attention']
feature_io.WriteToFile(out_desc_fullpath, locations_out,
feature_scales_out, descriptors_out,
attention_out)
def main(delf_config_path, dataset_file_path, images_dir, output_features_dir):
image_list = []
image_list.append(dataset_file_path)
num_images = len(image_list)
print('done! Found %d images' % num_images)
# Parse DelfConfig proto.
config = delf_config_pb2.DelfConfig()
with tf.io.gfile.GFile(delf_config_path, 'r') as f:
text_format.Parse(f.read(), config)
extractor_fn = extractor.MakeExtractor(config)
start = time.time()
for i in range(num_images):
if i == 0:
print('Starting to extract features...')
elif i % _STATUS_CHECK_ITERATIONS == 0:
elapsed = (time.time() - start)
print('Processing image %d out of %d, last %d '
'images took %f seconds' %
(i, num_images, _STATUS_CHECK_ITERATIONS, elapsed))
start = time.time()
image_name = image_list[i]
input_image_filename = os.path.join(images_dir,
image_name + _IMAGE_EXTENSION)
if config.use_local_features:
output_local_feature_filename = os.path.join(
output_features_dir, image_name + _DELG_LOCAL_EXTENSION)
if not tf.io.gfile.exists(output_local_feature_filename):
should_skip_local = False
pil_im = utils.RgbLoader(input_image_filename)
resize_factor = 1.0
im = np.array(pil_im)
# Extract and save features.
extracted_features = extractor_fn(im, resize_factor)
#if config.use_global_features:
# global_descriptor = extracted_features['global_descriptor']
# datum_io.WriteToFile(global_descriptor, output_global_feature_filename)
if config.use_local_features:
locations = extracted_features['local_features']['locations']
descriptors = extracted_features['local_features']['descriptors']
feature_scales = extracted_features['local_features']['scales']
attention = extracted_features['local_features']['attention']
feature_io.WriteToFile(output_local_feature_filename, locations,
feature_scales, descriptors, attention)
def main(argv):
if len(argv) > 1:
raise RuntimeError('Too many command-line arguments.')
# Read list of query images from dataset file.
print('Reading list of query images and boxes from dataset file...')
query_list, _, ground_truth = dataset.ReadDatasetFile(
cmd_args.dataset_file_path)
num_images = len(query_list)
print(f'done! Found {num_images} images')
# Parse DelfConfig proto.
config = delf_config_pb2.DelfConfig()
with tf.io.gfile.GFile(cmd_args.delf_config_path, 'r') as f:
text_format.Merge(f.read(), config)
# Create output directory if necessary.
if not tf.io.gfile.exists(cmd_args.output_features_dir):
tf.io.gfile.makedirs(cmd_args.output_features_dir)
extractor_fn = extractor.MakeExtractor(config)
start = time.time()
for i in range(num_images):
query_image_name = query_list[i]
input_image_filename = os.path.join(
cmd_args.images_dir, query_image_name + _IMAGE_EXTENSION)
output_feature_filename = os.path.join(
cmd_args.output_features_dir, query_image_name + _DELF_EXTENSION)
if tf.io.gfile.exists(output_feature_filename):
print(f'Skipping {query_image_name}')
continue
# Crop query image according to bounding box.
bbox = [int(round(b)) for b in ground_truth[i]['bbx']]
im = np.array(utils.RgbLoader(input_image_filename).crop(bbox))
# Extract and save features.
extracted_features = extractor_fn(im)
locations_out = extracted_features['local_features']['locations']
descriptors_out = extracted_features['local_features']['descriptors']
feature_scales_out = extracted_features['local_features']['scales']
attention_out = extracted_features['local_features']['attention']
feature_io.WriteToFile(output_feature_filename, locations_out,
feature_scales_out, descriptors_out,
attention_out)
elapsed = (time.time() - start)
print('Processed %d query images in %f seconds' % (num_images, elapsed))
def main(argv):
if len(argv) > 1:
raise RuntimeError('Too many command-line arguments.')
# Read list of images.
print('Reading list of images...')
image_paths = _ReadImageList(FLAGS.list_images_path)
num_images = len(image_paths)
print(f'done! Found {num_images} images')
# Load images in memory.
print('Loading images, %d times per image...' % FLAGS.repeat_per_image)
im_array = []
for filename in image_paths:
im = np.array(utils.RgbLoader(filename))
for _ in range(FLAGS.repeat_per_image):
im_array.append(im)
np.random.shuffle(im_array)
print('done!')
# Parse DelfConfig proto.
config = delf_config_pb2.DelfConfig()
with tf.io.gfile.GFile(FLAGS.delf_config_path, 'r') as f:
text_format.Parse(f.read(), config)
extractor_fn = extractor.MakeExtractor(config)
start = time.time()
for i, im in enumerate(im_array):
if i == 0:
print('Starting to extract DELF features from images...')
elif i % _STATUS_CHECK_ITERATIONS == 0:
elapsed = (time.time() - start)
print(f'Processing image {i} out of {len(im_array)}, last '
f'{_STATUS_CHECK_ITERATIONS} images took {elapsed} seconds,'
f'ie {elapsed/_STATUS_CHECK_ITERATIONS} secs/image.')
start = time.time()
# Extract and save features.
extracted_features = extractor_fn(im)