def build_image_set(file_path,
channels=1,
scale=1,
convert_ycbcr=True,
resampling_method="bicubic",
print_console=True):
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=print_console), scale)
if channels == 1 and true_image.shape[2] == 3 and convert_ycbcr:
true_image = util.convert_rgb_to_y(true_image)
input_image = util.resize_image_by_pil(true_image,
1.0 / scale,
resampling_method=resampling_method)
input_interpolated_image = util.resize_image_by_pil(
input_image, scale, resampling_method=resampling_method)
return input_image, input_interpolated_image, true_image
def do_for_file(self, file_path, output_folder="output"):
filename, extension = os.path.splitext(file_path)
output_folder += "/"
org_image = util.load_image(file_path)
util.save_image(output_folder + file_path, org_image)
if len(org_image.shape
) >= 3 and org_image.shape[2] == 3 and self.channels == 1:
input_y_image = util.convert_rgb_to_y(org_image,
jpeg_mode=self.jpeg_mode)
scaled_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
util.save_image(
output_folder + filename + "_bicubic_y" + extension,
scaled_image)
output_y_image = self.do(input_y_image)
util.save_image(output_folder + filename + "_result_y" + extension,
output_y_image)
scaled_ycbcr_image = util.convert_rgb_to_ycbcr(
util.resize_image_by_pil(org_image, self.scale,
self.resampling_method),
jpeg_mode=self.jpeg_mode)
image = util.convert_y_and_cbcr_to_rgb(output_y_image,
scaled_ycbcr_image[:, :,
1:3],
jpeg_mode=self.jpeg_mode)
else:
scaled_image = util.resize_image_by_pil(
org_image,
self.scale,
resampling_method=self.resampling_method)
util.save_image(
output_folder + filename + "_bicubic_y" + extension,
scaled_image)
image = self.do(org_image)
util.save_image(output_folder + filename + "_result" + extension,
image)
def evaluate_bicubic(self, file_path, print_console=False):
true_image = util.set_image_alignment(util.load_image(file_path, print_console=False), self.scale)
if true_image.shape[2] == 3 and self.channels == 1:
input_image = loader.build_input_image(true_image, channels=self.channels, scale=self.scale,
alignment=self.scale, convert_ycbcr=True)
true_image = util.convert_rgb_to_y(true_image)
elif true_image.shape[2] == 1 and self.channels == 1:
input_image = loader.build_input_image(true_image, channels=self.channels, scale=self.scale,
alignment=self.scale)
else:
return None, None
input_bicubic_image = util.resize_image_by_pil(input_image, self.scale, resampling_method=self.resampling_method)
psnr, ssim = util.compute_psnr_and_ssim(true_image, input_bicubic_image, border_size=self.psnr_calc_border_size)
if print_console:
print("PSNR:%f, SSIM:%f" % (psnr, ssim))
return psnr, ssim
def do_for_file(self, file_path, output_folder="output"):
org_image = util.load_image(file_path)
filename, extension = os.path.splitext(os.path.basename(file_path))
output_folder += "/" + self.name + "/"
util.save_image(output_folder + filename + extension, org_image)
if len(org_image.shape
) >= 3 and org_image.shape[2] == 3 and self.channels == 1:
input_y_image = util.convert_rgb_to_y(org_image)
util.save_image(output_folder + filename + '_input_y' + extension,
input_y_image)
scaled_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
util.save_image(
output_folder + filename + "_bicubic_y" + extension,
scaled_image)
output_y_image = self.do(input_y_image)
util.save_image(output_folder + filename + "_result_y" + extension,
output_y_image)
scaled_ycbcr_image = util.convert_rgb_to_ycbcr(
util.resize_image_by_pil(org_image, self.scale,
self.resampling_method))
_, scaled_cbcr = util.convert_ycbcr_to_y_cbcr(scaled_ycbcr_image)
image = util.convert_y_and_cbcr_to_rgb(output_y_image, scaled_cbcr)
else:
scaled_image = util.resize_image_by_pil(
org_image,
self.scale,
resampling_method=self.resampling_method)
util.save_image(
output_folder + filename + "_bicubic_y" + extension,
scaled_image)
image = self.do(org_image)
util.save_image(output_folder + filename + "_result" + extension,
image)
def main(not_parsed_args):
if len(not_parsed_args) > 1:
print("Unknown args:%s" % not_parsed_args)
exit()
print("Building Y channel data...")
training_filenames = util.get_files_in_directory(FLAGS.data_dir + "/" +
FLAGS.dataset + "/")
target_dir = FLAGS.data_dir + "/" + FLAGS.dataset + "_y/"
util.make_dir(target_dir)
for file_path in training_filenames:
org_image = util.load_image(file_path)
if org_image.shape[2] == 3:
org_image = util.convert_rgb_to_y(org_image)
filename = os.path.basename(file_path)
filename, extension = os.path.splitext(filename)
new_filename = target_dir + filename
util.save_image(new_filename + ".bmp", org_image)
def do_for_file(self, file_path, output_folder="output"):
org_image = util.load_image(file_path)
filename, extension = os.path.splitext(os.path.basename(file_path))
output_folder += "/" + self.name + "/"
# util.save_image(output_folder + filename + extension, org_image)
if os.path.exists(output_folder + filename + extension):
print("File already exists in the target directory")
return
if org_image.shape[0] + org_image.shape[1] >= 1024:
print("Image is too big: ", org_image.shape)
image = org_image
elif len(org_image.shape
) >= 3 and org_image.shape[2] == 3 and self.channels == 1:
input_y_image = util.convert_rgb_to_y(org_image)
# scaled_image = util.resize_image_by_pil(input_y_image, self.scale, resampling_method=self.resampling_method)
# util.save_image(output_folder + filename + "_bicubic_y" + extension, scaled_image)
output_y_image = self.do(input_y_image)
# util.save_image(output_folder + filename + "_result_y" + extension, output_y_image)
scaled_ycbcr_image = util.convert_rgb_to_ycbcr(
util.resize_image_by_pil(org_image, self.scale,
self.resampling_method))
image = util.convert_y_and_cbcr_to_rgb(
output_y_image, scaled_ycbcr_image[:, :, 1:3])
else:
# scaled_image = util.resize_image_by_pil(org_image, self.scale, resampling_method=self.resampling_method)
# util.save_image(output_folder + filename + "_bicubic_y" + extension, scaled_image)
image = self.do(org_image)
# util.save_image(output_folder + filename + "_result" + extension, image)
file_path = output_folder + filename + extension
util.save_image(file_path, image)
print("Saved at ", file_path)
def main(not_parsed_args):
if len(not_parsed_args) > 1:
print("Unknown args:%s" % not_parsed_args)
exit()
print("Building x%d augmented data." % FLAGS.augment_level)
training_filenames = util.get_files_in_directory(
"/media/data3/ww/sr_data/DIV2K_train_HR/")
target_dir = "/media/data3/ww/sr_data/DIV2K_train_HR" + (
"_%d/" % FLAGS.augment_level)
util.make_dir(target_dir)
writer = tf.python_io.TFRecordWriter("DIV2K_org.tfrecords")
writer2 = tf.python_io.TFRecordWriter("DIV2K_aug.tfrecords")
for file_path in training_filenames:
org_image = util.load_image(file_path)
org_raw = org_image.tobytes() #convert image to bytes
train_object = tf.train.Example(features=tf.train.Features(
feature={
'org_raw':
tf.train.Feature(bytes_list=tf.train.BytesList(
value=[org_raw]))
}))
writer.write(train_object.SerializeToString())
ud_image = np.flipud(org_image)
ud_raw = ud_image.tobytes() # convert image to bytes
train_object2 = tf.train.Example(features=tf.train.Features(
feature={
'org_raw':
tf.train.Feature(bytes_list=tf.train.BytesList(value=[ud_raw]))
}))
writer2.write(train_object2.SerializeToString())
writer.close()
def load_random_patch(self, filename):
image = util.load_image(filename, print_console=False)
height, width = image.shape[0:2]
load_batch_size = self.batch_image_size * self.scale
if height < load_batch_size or width < load_batch_size:
print("Error: %s should have more than %d x %d size." % (filename, load_batch_size, load_batch_size))
return None
if height == load_batch_size:
y = 0
else:
y = random.randrange(height - load_batch_size)
if width == load_batch_size:
x = 0
else:
x = random.randrange(width - load_batch_size)
image = image[y:y + load_batch_size, x:x + load_batch_size, :]
image = build_input_image(image, channels=self.channels, convert_ycbcr=True)
return image
def do_for_evaluate_with_output(self,
file_path,
output_directory,
print_console=False):
filename, extension = os.path.splitext(file_path)
output_directory += "/" + self.name + "/"
util.make_dir(output_directory)
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=False), self.scale)
if true_image.shape[2] == 3 and self.channels == 3:
# for color images
input_image = util.build_input_image(true_image,
scale=self.scale,
alignment=self.scale)
input_bicubic_image = util.resize_image_by_pil(
input_image,
self.scale,
resampling_method=self.resampling_method)
output_image, spend_time = self.do(input_image) # SR
SR_y = eva.convert_rgb_to_y(output_image)
HR_y = eva.convert_rgb_to_y(true_image)
psnr_predicted = eva.PSNR(np.uint8(HR_y),
np.uint8(SR_y),
shave_border=self.psnr_calc_border_size)
ssim_predicted = eva.compute_ssim(np.squeeze(HR_y),
np.squeeze(SR_y))
mse = util.compute_mse(HR_y,
SR_y,
border_size=self.psnr_calc_border_size)
loss_image = util.get_loss_image(
HR_y, SR_y, border_size=self.psnr_calc_border_size)
util.save_image(output_directory + file_path[29:], true_image)
util.save_image(
output_directory + filename[28:] + "_input" + extension,
input_image)
util.save_image(
output_directory + filename[28:] + "_input_bicubic" +
extension, input_bicubic_image)
util.save_image(
output_directory + filename[28:] + "_sr" + extension,
output_image)
util.save_image(
output_directory + filename[28:] + "_loss" + extension,
loss_image)
elif true_image.shape[2] == 1 and self.channels == 1:
# for monochrome images
input_image = util.build_input_image(true_image,
scale=self.scale,
alignment=self.scale)
output_image, spend_time = self.do(input_image)
psnr_predicted = eva.PSNR(np.uint8(true_image),
np.uint8(output_image),
shave_border=self.psnr_calc_border_size)
ssim_predicted = eva.compute_ssim(np.squeeze(true_image),
np.squeeze(output_image))
mse = util.compute_mse(true_image,
output_image,
border_size=self.psnr_calc_border_size)
util.save_image(output_directory + file_path, true_image)
util.save_image(output_directory + filename + "_sr" + extension,
output_image)
else:
psnr_predicted = 0.0
ssim_predicted = 0.0
mse = 0.0
spend_time = 0.0
if print_console:
print("[%s] psnr:%f, ssim:%f, time:%f" %
(filename, psnr_predicted, ssim_predicted, spend_time))
return mse, psnr_predicted, ssim_predicted, spend_time
def log_to_tensorboard(self, test_filename, psnr, save_meta_data=True):
if self.enable_log is False:
return
# todo
save_meta_data = False
org_image = util.set_image_alignment(
util.load_image(test_filename, print_console=False), self.scale)
if len(org_image.shape
) >= 3 and org_image.shape[2] == 3 and self.channels == 1:
org_image = util.convert_rgb_to_y(org_image)
input_image = util.resize_image_by_pil(
org_image,
1.0 / self.scale,
resampling_method=self.resampling_method)
bicubic_image = util.resize_image_by_pil(
input_image, self.scale, resampling_method=self.resampling_method)
if self.max_value != 255.0:
input_image = np.multiply(input_image, self.max_value /
255.0) # type: np.ndarray
bicubic_image = np.multiply(bicubic_image, self.max_value /
255.0) # type: np.ndarray
org_image = np.multiply(org_image,
self.max_value / 255.0) # type: np.ndarray
feed_dict = {
self.x:
input_image.reshape([
1, input_image.shape[0], input_image.shape[1],
input_image.shape[2]
]),
self.x2:
bicubic_image.reshape([
1, bicubic_image.shape[0], bicubic_image.shape[1],
bicubic_image.shape[2]
]),
self.y:
org_image.reshape([
1, org_image.shape[0], org_image.shape[1], org_image.shape[2]
]),
self.dropout:
1.0,
self.is_training:
0
}
if save_meta_data:
# profiler = tf.profiler.Profile(self.sess.graph)
run_metadata = tf.RunMetadata()
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
summary_str, _ = self.sess.run([self.summary_op, self.loss],
feed_dict=feed_dict,
options=run_options,
run_metadata=run_metadata)
self.test_writer.add_run_metadata(run_metadata,
"step%d" % self.epochs_completed)
filename = self.checkpoint_dir + "/" + self.name + "_metadata.txt"
with open(filename, "w") as out:
out.write(str(run_metadata))
# filename = self.checkpoint_dir + "/" + self.name + "_memory.txt"
# tf.profiler.write_op_log(
# tf.get_default_graph(),
# log_dir=self.checkpoint_dir,
# #op_log=op_log,
# run_meta=run_metadata)
tf.contrib.tfprof.model_analyzer.print_model_analysis(
tf.get_default_graph(),
run_meta=run_metadata,
tfprof_options=tf.contrib.tfprof.model_analyzer.
PRINT_ALL_TIMING_MEMORY)
else:
summary_str, _ = self.sess.run([self.summary_op, self.loss],
feed_dict=feed_dict)
self.train_writer.add_summary(summary_str, self.epochs_completed)
if not self.use_l1_loss:
if self.training_step != 0:
util.log_scalar_value(
self.train_writer, 'PSNR',
self.training_psnr_sum / self.training_step,
self.epochs_completed)
util.log_scalar_value(self.train_writer, 'LR', self.lr,
self.epochs_completed)
self.train_writer.flush()
util.log_scalar_value(self.test_writer, 'PSNR', psnr,
self.epochs_completed)
self.test_writer.flush()
def load_input_batch_image(batch_dir, image_number): return util.load_image(batch_dir + "/" + INPUT_IMAGE_DIR + "/%06d.bmp" % image_number, print_console=False)
def do_for_evaluate(self,
file_path,
output_directory=None,
print_console=False,
save_output_images=True):
if save_output_images:
filename, extension = os.path.splitext(file_path)
output_directory += "/" + self.name + "/"
util.make_dir(output_directory)
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=False), self.scale)
if true_image.shape[2] == 3 and self.channels == 1:
# for color images
input_y_image = loader.build_input_image(true_image,
channels=self.channels,
scale=self.scale,
alignment=self.scale,
convert_ycbcr=True)
input_bicubic_y_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
true_ycbcr_image = util.convert_rgb_to_ycbcr(true_image)
start = time.time()
output_y_image = self.do(input_y_image, input_bicubic_y_image)
end = time.time()
psnr, ssim = util.compute_psnr_and_ssim(
true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=self.psnr_calc_border_size)
loss_image = util.get_loss_image(
true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=self.psnr_calc_border_size)
output_color_image = util.convert_y_and_cbcr_to_rgb(
output_y_image, true_ycbcr_image[:, :, 1:3])
if save_output_images:
util.save_image(output_directory + file_path, true_image)
util.save_image(
output_directory + filename + "_input" + extension,
input_y_image)
util.save_image(
output_directory + filename + "_input_bicubic" + extension,
input_bicubic_y_image)
util.save_image(
output_directory + filename + "_true_y" + extension,
true_ycbcr_image[:, :, 0:1])
util.save_image(
output_directory + filename + "_result" + extension,
output_y_image)
util.save_image(
output_directory + filename + "_result_c" + extension,
output_color_image)
util.save_image(
output_directory + filename + "_loss" + extension,
loss_image)
elif true_image.shape[2] == 1 and self.channels == 1:
# for monochrome images
input_image = loader.build_input_image(true_image,
channels=self.channels,
scale=self.scale,
alignment=self.scale)
input_bicubic_y_image = util.resize_image_by_pil(
input_image,
self.scale,
resampling_method=self.resampling_method)
start = time.time()
output_image = self.do(input_image, input_bicubic_y_image)
end = time.time()
psnr, ssim = util.compute_psnr_and_ssim(
true_image,
output_image,
border_size=self.psnr_calc_border_size)
if save_output_images:
util.save_image(output_directory + file_path, true_image)
util.save_image(
output_directory + filename + "_result" + extension,
output_image)
else:
return None, None
if print_console:
print("[%s] PSNR:%f, SSIM:%f" % (filename, psnr, ssim))
elapsed_time = end - start
return psnr, ssim, elapsed_time
def load_input_image(filename, width=0, height=0, channels=1, scale=1, alignment=0, convert_ycbcr=True,
print_console=True):
image = util.load_image(filename, print_console=print_console)
return build_input_image(image, width, height, channels, scale, alignment, convert_ycbcr)
def do_for_evaluate_with_output(self,
file_path,
output_directory=None,
print_console=False):
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=False), self.scale)
# Assuming the image is color
assert true_image.shape[
2] == 3 and self.channels == 1, "Only 3-channel images are supported"
input_image = loader.build_input_image(true_image,
scale=self.scale,
alignment=self.scale)
input_y_image = util.convert_rgb_to_y(input_image)
true_y_image = util.convert_rgb_to_y(true_image)
input_bicubic_y_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
output_y_image = self.do(input_y_image, input_bicubic_y_image)
psnr, ssim = util.compute_psnr_and_ssim(
true_y_image,
output_y_image,
border_size=self.psnr_calc_border_size)
if output_directory:
true_ycbcr_image = util.convert_rgb_to_ycbcr(true_image)
_, true_cbcr = util.convert_ycbcr_to_y_cbcr(true_ycbcr_image)
output_color_image = util.convert_y_and_cbcr_to_rgb(
output_y_image, true_cbcr)
loss_image = util.get_loss_image(
true_y_image,
output_y_image,
border_size=self.psnr_calc_border_size)
filename, extension = os.path.splitext(file_path)
output_directory += "/" + self.name + "/"
util.make_dir(output_directory)
util.save_image(output_directory + file_path, true_image)
util.save_image(output_directory + filename + "_input" + extension,
input_y_image)
util.save_image(
output_directory + filename + "_input_bicubic" + extension,
input_bicubic_y_image)
util.save_image(
output_directory + filename + "_true_y" + extension,
true_ycbcr_image[:, :, 0:1])
util.save_image(
output_directory + filename + "_result" + extension,
output_y_image)
util.save_image(
output_directory + filename + "_result_c" + extension,
output_color_image)
util.save_image(output_directory + filename + "_loss" + extension,
loss_image)
if print_console:
print("[%s] PSNR:%f, SSIM:%f" % (filename, psnr, ssim))
return psnr, ssim
def load_interpolated_batch_image(batch_dir, image_number): return util.load_image(batch_dir + "/" + INTERPOLATED_IMAGE_DIR + "/%06d.bmp" % image_number, print_console=False)
def log_to_tensorboard(self, test_filename, psnr, save_meta_data=True):
# todo
save_meta_data = False
org_image = util.set_image_alignment(
util.load_image(test_filename, print_console=False), self.scale)
if len(org_image.shape
) >= 3 and org_image.shape[2] == 3 and self.channels == 1:
org_image = util.convert_rgb_to_y(org_image)
input_image = util.resize_image_by_pil(
org_image,
1.0 / self.scale,
resampling_method=self.resampling_method)
feed_dict = {
self.x:
input_image.reshape([
1, input_image.shape[0], input_image.shape[1],
input_image.shape[2]
]),
self.y:
org_image.reshape([
1, org_image.shape[0], org_image.shape[1], org_image.shape[2]
]),
self.is_training:
0
}
if save_meta_data:
run_metadata = tf.RunMetadata()
run_options = tf.RunOptions(trace_level=tf.RunOptions.FULL_TRACE)
summary_str, _ = self.sess.run([self.summary_op, self.mae],
feed_dict=feed_dict,
options=run_options,
run_metadata=run_metadata)
self.test_writer.add_run_metadata(run_metadata,
"step%d" % self.epochs_completed)
filename = self.checkpoint_dir + "/" + self.name + "_metadata.txt"
with open(filename, "w") as out:
out.write(str(run_metadata))
tf.contrib.tfprof.model_analyzer.print_model_analysis(
tf.get_default_graph(),
run_meta=run_metadata,
tfprof_options=tf.contrib.tfprof.model_analyzer.
PRINT_ALL_TIMING_MEMORY)
else:
summary_str, _ = self.sess.run([self.summary_op, self.mae],
feed_dict=feed_dict)
self.train_writer.add_summary(summary_str, self.epochs_completed)
util.log_scalar_value(self.train_writer, 'training_PSNR',
self.training_psnr_sum / self.training_step,
self.epochs_completed)
util.log_scalar_value(self.train_writer, 'LR', self.lr,
self.epochs_completed)
self.train_writer.flush()
util.log_scalar_value(self.test_writer, 'PSNR', psnr,
self.epochs_completed)
self.test_writer.flush()
def load_true_batch_image(batch_dir, image_number): return util.load_image(batch_dir + "/" + TRUE_IMAGE_DIR + "/%06d.bmp" % image_number, print_console=False)
def do_for_evaluate(self,
file_path,
output_directory="output",
output=True,
print_console=False):
filename, extension = os.path.splitext(file_path)
output_directory += "/" + self.name + "/"
util.make_dir(output_directory)
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=False), self.scale)
if true_image.shape[2] == 3 and self.channels == 1:
input_y_image = loader.build_input_image(true_image,
channels=self.channels,
scale=self.scale,
alignment=self.scale,
convert_ycbcr=True,
jpeg_mode=self.jpeg_mode)
# for color images
if output:
input_bicubic_y_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
true_ycbcr_image = util.convert_rgb_to_ycbcr(
true_image, jpeg_mode=self.jpeg_mode)
output_y_image = self.do(input_y_image, input_bicubic_y_image)
mse = util.compute_mse(true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=6 + self.scale)
loss_image = util.get_loss_image(true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=self.scale)
output_color_image = util.convert_y_and_cbcr_to_rgb(
output_y_image,
true_ycbcr_image[:, :, 1:3],
jpeg_mode=self.jpeg_mode)
util.save_image(output_directory + file_path, true_image)
util.save_image(
output_directory + filename + "_input" + extension,
input_y_image)
util.save_image(
output_directory + filename + "_input_bicubic" + extension,
input_bicubic_y_image)
util.save_image(
output_directory + filename + "_true_y" + extension,
true_ycbcr_image[:, :, 0:1])
util.save_image(
output_directory + filename + "_result" + extension,
output_y_image)
util.save_image(
output_directory + filename + "_result_c" + extension,
output_color_image)
util.save_image(
output_directory + filename + "_loss" + extension,
loss_image)
else:
true_y_image = util.convert_rgb_to_y(true_image,
jpeg_mode=self.jpeg_mode)
input_bicubic_y_image = util.resize_image_by_pil(
input_y_image,
self.scale,
resampling_method=self.resampling_method)
output_y_image = self.do(input_y_image, input_bicubic_y_image)
mse = util.compute_mse(true_y_image,
output_y_image,
border_size=6 + self.scale)
elif true_image.shape[2] == 1 and self.channels == 1:
# for monochrome images
input_image = loader.build_input_image(true_image,
channels=self.channels,
scale=self.scale,
alignment=self.scale)
input_bicubic_y_image = util.resize_image_by_pil(
input_image,
self.scale,
resampling_method=self.resampling_method)
output_image = self.do(input_image, input_bicubic_y_image)
mse = util.compute_mse(true_image,
output_image,
border_size=6 + self.scale)
if output:
util.save_image(output_directory + file_path, true_image)
util.save_image(
output_directory + filename + "_result" + extension,
output_image)
else:
mse = 0
if print_console:
print("MSE:%f, PSNR:%f" % (mse, util.get_psnr(mse)))
return mse
def load_and_evaluate_tflite_graph(
output_dir,
data_dir,
test_data,
model_path=os.path.join(os.getcwd(),
'model_to_freeze/converted_model.tflite')):
# https://stackoverflow.com/questions/50443411/how-to-load-a-tflite-model-in-script
# https://www.tensorflow.org/lite/convert/python_api#tensorflow_lite_python_interpreter_
output_directory = output_dir
output_directory += "/" + "tflite" + "/"
util.make_dir(output_directory)
test_filepaths = util.get_files_in_directory(data_dir + "/" + test_data)
total_psnr = total_ssim = total_time = 0
# Load TFLite model and allocate tensors.
interpreter = tf.lite.Interpreter(model_path=model_path)
# interpreter = tf.contrib.lite.Interpreter(model_path=model_path)
interpreter.allocate_tensors()
# Get input and output tensors.
input_details = interpreter.get_input_details()
output_details = interpreter.get_output_details()
for file_path in test_filepaths:
# split filename from extension
filename, extension = os.path.splitext(file_path)
# prepare true image
true_image = util.set_image_alignment(
util.load_image(file_path, print_console=False), FLAGS.scale)
# start the timer
if true_image.shape[2] == 3 and FLAGS.channels == 1:
# prepare input and ground truth images
input_y_image = loader.build_input_image(true_image,
channels=FLAGS.channels,
scale=FLAGS.scale,
alignment=FLAGS.scale,
convert_ycbcr=True)
input_bicubic_y_image = util.resize_image_by_pil(
input_y_image,
FLAGS.scale,
resampling_method=FLAGS.resampling_method)
true_ycbcr_image = util.convert_rgb_to_ycbcr(true_image)
# pass inputs through the model (need to recast and reshape inputs)
input_y_image_reshaped = input_y_image.astype('float32')
input_y_image_reshaped = input_y_image_reshaped.reshape(
1, input_y_image.shape[0], input_y_image.shape[1],
FLAGS.channels)
input_bicubic_y_image_reshaped = input_bicubic_y_image.astype(
'float32')
input_bicubic_y_image_reshaped = input_bicubic_y_image_reshaped.reshape(
1, input_bicubic_y_image.shape[0],
input_bicubic_y_image.shape[1], FLAGS.channels)
interpreter.set_tensor(input_details[0]['index'],
input_y_image_reshaped) # pass x
interpreter.set_tensor(input_details[1]['index'],
input_bicubic_y_image_reshaped) # pass x2
start = time.time()
interpreter.invoke()
end = time.time()
output_y_image = interpreter.get_tensor(
output_details[0]['index']) # get y
# resize the output into an image
output_y_image = output_y_image.reshape(output_y_image.shape[1],
output_y_image.shape[2],
FLAGS.channels)
# calculate psnr and ssim for the output
psnr, ssim = util.compute_psnr_and_ssim(
true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=FLAGS.psnr_calc_border_size)
# get the loss image
loss_image = util.get_loss_image(
true_ycbcr_image[:, :, 0:1],
output_y_image,
border_size=FLAGS.psnr_calc_border_size)
# get output color image
output_color_image = util.convert_y_and_cbcr_to_rgb(
output_y_image, true_ycbcr_image[:, :, 1:3])
# save all images
util.save_image(output_directory + file_path, true_image)
util.save_image(output_directory + filename + "_input" + extension,
input_y_image)
util.save_image(
output_directory + filename + "_input_bicubic" + extension,
input_bicubic_y_image)
util.save_image(
output_directory + filename + "_true_y" + extension,
true_ycbcr_image[:, :, 0:1])
util.save_image(
output_directory + filename + "_result" + extension,
output_y_image)
util.save_image(
output_directory + filename + "_result_c" + extension,
output_color_image)
util.save_image(output_directory + filename + "_loss" + extension,
loss_image)
elapsed_time = end - start
total_psnr += psnr
total_ssim += ssim
total_time += elapsed_time
testSize = len(test_filepaths)
print("Model Average [%s] PSNR:%f, SSIM:%f, Elapsed Time:%f" %
(test_data, total_psnr / testSize, total_ssim / testSize,
total_time / testSize))
