def build_pose_test_graph(self, input_uint8):
input_mc = self.select_tensor_or_placeholder_input(input_uint8)
loader = DataLoader()
tgt_image, src_image_stack = \
loader.batch_unpack_image_sequence(
input_mc, self.img_height, self.img_width, self.num_source)
with tf.name_scope("pose_prediction"):
pred_poses, _ = pose_net(tgt_image,
src_image_stack,
is_training=False)
self.pred_poses = pred_poses
def build_pose_test_graph(self):
input_uint8 = tf.placeholder(tf.uint8, [self.batch_size,
self.img_height, self.img_width * self.seq_length, 3],
name='raw_input')
input_mc = self.preprocess_image(input_uint8)
loader = DataLoader()
tgt_image, src_image_stack = \
loader.batch_unpack_image_sequence(
input_mc, self.img_height, self.img_width, self.num_source)
with tf.name_scope("pose_prediction"):
pred_poses, _, _ = pose_exp_net(
tgt_image, src_image_stack, do_exp=False, is_training=False)
self.inputs = input_uint8
self.pred_poses = pred_poses
def build_pose_test_graph(self):
input_uint8 = tf.placeholder(tf.uint8, [
self.batch_size, self.img_height, self.img_width * self.seq_length,
3
],
name='raw_input') #shape(1,128,416*3,3)
input_mc = self.preprocess_image(input_uint8) #shape(1,128,416*3,3)
# print('input_mc.shape:',input_mc.shape)
# input_mc = tf.Print(input_mc,[input_mc.shape],message='input_mc')
loader = DataLoader()
tgt_image, src_image_stack = \
loader.batch_unpack_image_sequence(
input_mc, self.img_height, self.img_width, self.num_source)
with tf.name_scope("pose_prediction"):
pred_poses, _, _ = pose_exp_net(tgt_image,
src_image_stack,
do_exp=False,
is_training=False)
# print('pred_poses:',pred_poses)
# tf.Print(pred_poses,[pred_poses.shape],message='pred_poses') #shape(1,2,6)
self.inputs = input_uint8
self.pred_poses = pred_poses
