lr=configs.learning_rate,
lr_decay_step=configs.lr_decay_step,
lr_decay_rate=configs.lr_decay_rate)
print("Network built!")
# log_writer = tf.summary.FileWriter(logdir=log_dir, graph=sess.graph)
model_saver = tf.train.Saver()
net_init = tf.global_variables_initializer()
sess.run([net_init])
# reload the model
for cur_model_iterations in evaluation_models:
if os.path.exists(
configs.restore_model_path_fn(cur_model_iterations) +
".index"):
print(
"#######################Restored all weights ###########################"
)
model_saver.restore(
sess, configs.restore_model_path_fn(cur_model_iterations))
else:
print(configs.restore_model_path_fn(cur_model_iterations))
print("The prev model is not existing!")
quit()
##################### First get the depth scale from the subset of the training set ######################
cur_model_depth_scale = my_utils.mAverageCounter(shape=[1])
scale_data_index = my_utils.mRangeVariable(
# log_writer = tf.summary.FileWriter(logdir=log_dir, graph=sess.graph)
model_saver = tf.train.Saver()
net_init = tf.global_variables_initializer()
sess.run([net_init])
# reload the model
for cur_model_iterations in evaluation_models:
pose_error_statistic = pose_error.mResultSaver()
depth_eval = evaluators.mEvaluatorDepth(nJoints=configs.nJoints)
coords_eval = evaluators.mEvaluatorPose3D(nJoints=configs.nJoints)
data_index = my_utils.mRangeVariable(min_val=data_from, max_val=data_to-1, initial_val=data_from)
if os.path.exists(configs.restore_model_path_fn(cur_model_iterations)+".index"):
print("#######################Restored all weights ###########################")
model_saver.restore(sess, configs.restore_model_path_fn(cur_model_iterations))
else:
print(configs.restore_model_path_fn(cur_model_iterations))
print("The prev model is not existing!")
quit()
while not data_index.isEnd():
global_steps = sess.run(ordinal_model.global_steps)
batch_images_np = np.zeros([configs.batch_size, configs.img_size, configs.img_size, 3], dtype=np.float32)
batch_depth_np = np.zeros([configs.batch_size, configs.nJoints], dtype=np.float32)
img_path_for_show = []
label_path_for_show = []