diff options
Diffstat (limited to 'Codes/utils.py')
| -rw-r--r-- | Codes/utils.py | 86 |
1 files changed, 10 insertions, 76 deletions
diff --git a/Codes/utils.py b/Codes/utils.py index efeab8e..8466d08 100644 --- a/Codes/utils.py +++ b/Codes/utils.py @@ -10,6 +10,15 @@ rng = np.random.RandomState(2017) def np_load_frame(filename, resize_height, resize_width): + """ + Load image path and convert it to numpy.ndarray. Notes that the color channels are BGR and the color space + is normalized from [0, 255] to [-1, 1]. + + :param filename: the full path of image + :param resize_height: resized height + :param resize_width: resized width + :return: numpy.ndarray + """ image_decoded = cv2.imread(filename) image_resized = cv2.resize(image_decoded, (resize_width, resize_height)) image_resized = image_resized.astype(dtype=np.float32) @@ -20,7 +29,7 @@ def np_load_frame(filename, resize_height, resize_width): class DataLoader(object): def __init__(self, video_folder, resize_height=256, resize_width=256): self.dir = video_folder - self.videos = {} + self.videos = OrderedDict() self._resize_height = resize_height self._resize_width = resize_width self.setup() @@ -83,15 +92,6 @@ class DataLoader(object): return np.concatenate(batch, axis=2) - # def get_video_clips(self, video_name, start, end): - # video_idx = np.arange(start, end) - # video_clip = np.empty(shape=[self._resize_height, self._resize_height, 3*len(video_idx)], dtype=np.float32) - # for idx, v_idx in enumerate(video_idx): - # filename = self.videos[video_name]['frame'][v_idx] - # video_clip[..., idx*3:(idx+1)*3] = np_load_frame(filename, self._resize_height, self._resize_width) - # - # return video_clip - def log10(t): """ @@ -130,46 +130,6 @@ def psnr_error(gen_frames, gt_frames): return tf.reduce_mean(batch_errors) -def sharp_diff_error(gen_frames, gt_frames, channels=3): - """ - Computes the Sharpness Difference error between the generated images and the ground truth - images. - - @param gen_frames: A tensor of shape [batch_size, height, width, 3]. The frames generated by the - generator model. - @param gt_frames: A tensor of shape [batch_size, height, width, 3]. The ground-truth frames for - each frame in gen_frames. - @param channels: The number of channels, 3 is RGB and 1 is Gray, default is 3. - - @return: A scalar tensor. The Sharpness Difference error over each frame in the batch. - """ - shape = tf.shape(gen_frames) - num_pixels = tf.to_float(shape[1] * shape[2] * shape[3]) - - # gradient difference - # create filters [-1, 1] and [[1],[-1]] for diffing to the left and down respectively. - # TODO: Could this be simplified with one filter [[-1, 2], [0, -1]]? - pos = tf.constant(np.identity(channels), dtype=tf.float32) - neg = -1 * pos - filter_x = tf.expand_dims(tf.stack([neg, pos]), 0) # [-1, 1] - filter_y = tf.stack([tf.expand_dims(pos, 0), tf.expand_dims(neg, 0)]) # [[1],[-1]] - strides = [1, 1, 1, 1] # stride of (1, 1) - padding = 'SAME' - - gen_dx = tf.abs(tf.nn.conv2d(gen_frames, filter_x, strides, padding=padding)) - gen_dy = tf.abs(tf.nn.conv2d(gen_frames, filter_y, strides, padding=padding)) - gt_dx = tf.abs(tf.nn.conv2d(gt_frames, filter_x, strides, padding=padding)) - gt_dy = tf.abs(tf.nn.conv2d(gt_frames, filter_y, strides, padding=padding)) - - gen_grad_sum = gen_dx + gen_dy - gt_grad_sum = gt_dx + gt_dy - - grad_diff = tf.abs(gt_grad_sum - gen_grad_sum) - - batch_errors = 10 * log10(1 / ((1 / num_pixels) * tf.reduce_sum(grad_diff, [1, 2, 3]))) - return tf.reduce_mean(batch_errors) - - def diff_mask(gen_frames, gt_frames, min_value=-1, max_value=1): # normalize to [0, 1] delta = max_value - min_value @@ -197,31 +157,5 @@ def save(saver, sess, logdir, step): print('The checkpoint has been created.') -# if __name__ == '__main__': -# os.environ['CUDA_DEVICES_ORDER'] = "PCI_BUS_ID" -# os.environ['CUDA_VISIBLE_DEVICES'] = '0' -# -# data_loader = DataLoader('/home/liuwen/ssd/datasets/avenue/training/frames') -# dataset, epoch_size = data_loader(10, 4, 1, 3, 1) -# -# # debug -# iteration = dataset.make_one_shot_iterator() -# batch_video_clip_tensor = iteration.get_next() -# -# config = tf.ConfigProto() -# config.gpu_options.allow_growth = True -# with tf.Session(config=config) as sess: -# # batch_video_clip = sess.run(next(it)) -# -# for i in range(100): -# batch_video_clip = sess.run(batch_video_clip_tensor) -# # print(batch_video_clip.shape) -# -# for vid, video_clip in enumerate(batch_video_clip): -# for fid, frame in enumerate(video_clip): -# print(i, vid, fid) -# cv2.imshow('visualization', frame + 0.5) -# cv2.waitKey(100) - |