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) #Esta linea para solo blanco y negro org_image = util.convert_rgb_to_y(org_image) util.save_image(output_folder + filename + "_y" + 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) 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 + "_residual_y" + extension, image) final_image = scaled_image + image util.save_image(output_folder + filename + "_result" + extension, final_image)
def do_util(src, dest): with Timer('util: load'): inp = util.load_image(src) with Timer('util: resize'): resized = util.resize_image_by_pil(inp, 2) with Timer('util: extract Y'): only_y = util.convert_rgb_to_y(inp) only_y = util.convert_rgb_to_y(resized) # simulate upscale with Timer('util: rgb => YCbCr'): scaled_ycbcr_image = util.convert_rgb_to_ycbcr(resized) with Timer('util: Y + YCbCr -> rgb'): image = util.convert_y_and_cbcr_to_rgb(only_y, scaled_ycbcr_image[:, :, 1:3]) with Timer('util: save'): util.save_image(dest, image)
def build_input_image(image, width=0, height=0, channels=1, scale=1, alignment=0, convert_ycbcr=True): """ build input image from file. crop, adjust the image alignment for the scale factor, resize, convert color space. """ if width != 0 and height != 0: if image.shape[0] != height or image.shape[1] != width: x = (image.shape[1] - width) // 2 y = (image.shape[0] - height) // 2 image = image[y:y + height, x:x + width, :] if alignment > 1: image = util.set_image_alignment(image, alignment) if channels == 1 and image.shape[2] == 3: if convert_ycbcr: image = util.convert_rgb_to_y(image) else: if convert_ycbcr: image = util.convert_rgb_to_ycbcr(image) if scale != 1: image = util.resize_image_by_pil(image, 1.0 / scale) return image
def do_for_evaluate(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: # for color images input_y_image = loader.build_input_image(true_image, channels=self.channels, scale=self.scale, alignment=self.scale, convert_ycbcr=True) 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) mse = util.compute_mse(true_y_image, output_y_image, border_size=self.psnr_calc_border_size) 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=self.psnr_calc_border_size) else: mse = 0 if print_console: print("MSE:%f, PSNR:%f" % (mse, util.get_psnr(mse))) return mse
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 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) 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: 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 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 doframe(self, org_image): 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) output_y_image = self.do(input_y_image) scaled_ycbcr_image = util.convert_rgb_to_ycbcr( util.resize_image_by_pil(org_image, self.scale, self.resampling_method)) return util.convert_y_and_cbcr_to_rgb(output_y_image, scaled_ycbcr_image[:, :, 1:3])
def load_batch_image(self, max_value): image = None file_path = None while image is None: file_path = self.filenames[self.get_next_image_no()] if self.image_maker.patch_scale_max > 1.0: patch_scale_value = random.randrange(100, self.image_maker.patch_scale_max * 100) / 100. else: patch_scale_value = 1. image = self.load_random_patch(file_path, patch_scale_value) input_image = self.image_maker.make_input_image(file_path, image, scale=self.scale, print_console=False) flip = random.randrange(0, 4) if flip == 1 or flip == 3: input_image = np.flipud(input_image) image = np.flipud(image) if flip == 2 or flip == 3: input_image = np.fliplr(input_image) image = np.fliplr(image) rot90 = random.randrange(0, 2) if rot90 == 1: input_image = np.rot90(input_image) image = np.rot90(image) input_image = util.convert_rgb_to_y(input_image) input_bicubic_image = util.resize_image_by_pil(input_image, self.scale) if max_value != 255: scale = max_value / 255.0 input_image = np.multiply(input_image, scale) input_bicubic_image = np.multiply(input_bicubic_image, scale) image = np.multiply(image, scale) image = util.convert_rgb_to_y(image) return input_image, input_bicubic_image, image
def predict_im(self, 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) output_y_image = self.do(input_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: image = self.do(org_image) return image
def do_for_evaluate(self, file_path, output_directory="output", output=True, print_console=True): filename, extension = os.path.splitext(file_path) output_directory += "/" true_image = util.set_image_alignment(util.load_image(file_path), 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) 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=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) output_y_image = self.do(input_y_image) mse = util.compute_mse(true_y_image, output_y_image, border_size=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) output_image = self.do(input_image) mse = util.compute_mse(true_image, output_image, border_size=self.scale) if output: util.save_image(output_directory + file_path, true_image) util.save_image(output_directory + filename + "_result" + extension, output_image) if print_console: print("MSE:%f PSNR:%f" % (mse, util.get_psnr(mse))) return mse
def upscale(self, org_image): assert 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) big_blurry_input_image = util.resize_image_by_pil( org_image, self.scale) big_blurry_input_ycbcr_image = util.convert_rgb_to_ycbcr( big_blurry_input_image) bbi_input_y_image, bbi_input_cbcr_image = util.convert_ycbcr_to_y_cbcr( big_blurry_input_ycbcr_image) output_y_image = self.do(input_y_image, bbi_input_y_image) output_image = util.convert_y_and_cbcr_to_rgb(output_y_image, bbi_input_cbcr_image) return output_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 do_for_file(self, file_path, output_folder="output"): org_image = cv2.imread(file_path) assert 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) big_blurry_input_image = util.resize_image_by_pil( org_image, self.scale) big_blurry_input_ycbcr_image = util.convert_rgb_to_ycbcr( big_blurry_input_image) bbi_input_y_image, bbi_input_cbcr_image = util.convert_ycbcr_to_y_cbcr( big_blurry_input_ycbcr_image) output_y_image = self.do(input_y_image, bbi_input_y_image) output_image = util.convert_y_and_cbcr_to_rgb(output_y_image, bbi_input_cbcr_image) target_path = os.path.basename(file_path) cv2.imwrite(os.path.join(output_folder, target_path), output_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 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