def read_and_decode(self, filename_queue):
img1_name = tf.string_join([self.img_dir, '/', filename_queue[0]])
img2_name = tf.string_join([self.img_dir, '/', filename_queue[1]])
img3_name = tf.string_join([self.img_dir, '/', filename_queue[2]])
img4_name = tf.string_join([self.img_dir, '/', filename_queue[3]])
img5_name = tf.string_join([self.img_dir, '/', filename_queue[4]])
img1 = tf.image.decode_png(tf.read_file(img1_name), channels=3)
img1 = tf.cast(img1, tf.float32)
img2 = tf.image.decode_png(tf.read_file(img2_name), channels=3)
img2 = tf.cast(img2, tf.float32)
img3 = tf.image.decode_png(tf.read_file(img3_name), channels=3)
img3 = tf.cast(img3, tf.float32)
img4 = tf.image.decode_png(tf.read_file(img4_name), channels=3)
img4 = tf.cast(img4, tf.float32)
img5 = tf.image.decode_png(tf.read_file(img5_name), channels=3)
img5 = tf.cast(img5, tf.float32)
return img1, img2, img3, img4, img5
def make_status_message(model):
"""Makes a string `Tensor` of training status."""
return tf.string_join([
'Starting train step: current_image_id: ',
tf.as_string(model.current_image_id), ', progress: ',
tf.as_string(model.progress), ', num_blocks: {}'.format(
model.num_blocks), ', batch_size: {}'.format(model.batch_size)
],
name='status_message')
def read_and_decode_distillation(self, filename_queue):
img1_name = tf.string_join([self.img_dir, '/', filename_queue[0]])
img2_name = tf.string_join([self.img_dir, '/', filename_queue[1]])
img3_name = tf.string_join([self.img_dir, '/', filename_queue[2]])
img4_name = tf.string_join([self.img_dir, '/', filename_queue[3]])
img5_name = tf.string_join([self.img_dir, '/', filename_queue[4]])
img1 = tf.image.decode_png(tf.read_file(img1_name), channels=3)
img1 = tf.cast(img1, tf.float32)
img2 = tf.image.decode_png(tf.read_file(img2_name), channels=3)
img2 = tf.cast(img2, tf.float32)
img3 = tf.image.decode_png(tf.read_file(img3_name), channels=3)
img3 = tf.cast(img3, tf.float32)
img4 = tf.image.decode_png(tf.read_file(img4_name), channels=3)
img4 = tf.cast(img4, tf.float32)
img5 = tf.image.decode_png(tf.read_file(img5_name), channels=3)
img5 = tf.cast(img5, tf.float32)
flow_occ_fw_12_name = tf.string_join([
self.fake_flow_occ_dir, '/flow_occ_12_fw_', filename_queue[5],
'.png'
])
flow_occ_bw_21_name = tf.string_join([
self.fake_flow_occ_dir, '/flow_occ_21_bw_', filename_queue[5],
'.png'
])
flow_occ_fw_12 = tf.image.decode_png(tf.read_file(flow_occ_fw_12_name),
dtype=tf.uint16,
channels=3)
flow_occ_fw_12 = tf.cast(flow_occ_fw_12, tf.float32)
flow_occ_bw_21 = tf.image.decode_png(tf.read_file(flow_occ_bw_21_name),
dtype=tf.uint16,
channels=3)
flow_occ_bw_21 = tf.cast(flow_occ_bw_21, tf.float32)
flow_fw_12, occ_fw_12 = self.extract_flow_and_mask(flow_occ_fw_12)
flow_bw_21, occ_bw_21 = self.extract_flow_and_mask(flow_occ_bw_21)
flow_occ_fw_23_name = tf.string_join([
self.fake_flow_occ_dir, '/flow_occ_23_fw_', filename_queue[5],
'.png'
])
flow_occ_bw_32_name = tf.string_join([
self.fake_flow_occ_dir, '/flow_occ_32_bw_', filename_queue[5],
'.png'
])
flow_occ_fw_23 = tf.image.decode_png(tf.read_file(flow_occ_fw_23_name),
dtype=tf.uint16,
channels=3)
flow_occ_fw_23 = tf.cast(flow_occ_fw_23, tf.float32)
flow_occ_bw_32 = tf.image.decode_png(tf.read_file(flow_occ_bw_32_name),
dtype=tf.uint16,
channels=3)
flow_occ_bw_32 = tf.cast(flow_occ_bw_32, tf.float32)
flow_fw_23, occ_fw_23 = self.extract_flow_and_mask(flow_occ_fw_23)
flow_bw_32, occ_bw_32 = self.extract_flow_and_mask(flow_occ_bw_32)
superpix_name = tf.string_join(
[self.superpixel_dir, '/', filename_queue[2]])
superpixels = tf.image.decode_png(tf.read_file(superpix_name),
channels=1)
superpixels = tf.cast(superpixels, tf.int32)
return img1, img2, img3, img4, img5, flow_fw_12, flow_bw_21, occ_fw_12, occ_bw_21, flow_fw_23, flow_bw_32, occ_fw_23, occ_bw_32, superpixels
