updates to tensorflow code and processing additionsHEADmaster

1 files changed, 32 insertions, 2 deletions

diff --git a/Code/utils.py b/Code/utils.py
index 39a7e11..d5c5d05 100644
--- a/Code/utils.py
+++ b/Code/utils.py
@@ -90,6 +90,36 @@ def get_full_clips(data_dir, num_clips, num_rec_out=1):
 
     return clips
 
+def get_all_clips(data_dir):
+    """
+    Loads all clips from a directory.
+
+    @param data_dir: The directory of the data to read. Should be either c.TRAIN_DIR or c.TEST_DIR.
+    @param num_clips: The number of clips to read.
+    @param num_rec_out: The number of outputs to predict. Outputs > 1 are computed recursively,
+                        using the previously-generated frames as input. Default = 1.
+
+    @return: An array of shape
+             [num_clips, c.TRAIN_HEIGHT, c.TRAIN_WIDTH, (3 * (c.HIST_LEN + num_rec_out))].
+             A batch of frame sequences with values normalized in range [-1, 1].
+    """
+    # get all the clips
+    clip_frame_paths = sorted(glob(os.path.join(data_dir, '*')))
+
+    clips = np.empty([len(clip_frame_paths),
+                      c.FULL_HEIGHT,
+                      c.FULL_WIDTH,
+                      (3 * (c.HIST_LEN + num_rec_out))])
+
+    # read in frames
+    for frame_num, frame_path in enumerate(clip_frame_paths):
+        frame = imread(frame_path, mode='RGB')
+        norm_frame = normalize_frames(frame)
+
+        clips[clip_num, :, :, frame_num * 3:(frame_num + 1) * 3] = norm_frame
+
+    return clips
+
 def process_clip():
     """
     Gets a clip from the train dataset, cropped randomly to c.TRAIN_HEIGHT x c.TRAIN_WIDTH.
@@ -193,8 +223,8 @@ def sharp_diff_error(gen_frames, gt_frames):
     # TODO: Could this be simplified with one filter [[-1, 2], [0, -1]]?
     pos = tf.constant(np.identity(3), dtype=tf.float32)
     neg = -1 * pos
-    filter_x = tf.expand_dims(tf.pack([neg, pos]), 0)  # [-1, 1]
-    filter_y = tf.pack([tf.expand_dims(pos, 0), tf.expand_dims(neg, 0)])  # [[1],[-1]]
+    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'