Get “ValueError: No gradients provided for any variable” when running Image_COCO.Main

[CorbinZhou]

Traceback (most recent call last): File "/Users/zhouye/Documents/dtwave/LeakGAN/run.py", line 14, in main() File "/Users/zhouye/Documents/dtwave/LeakGAN/Image_COCO/Main.py", line 161, in main batch_size=BATCH_SIZE,hidden_dim=HIDDEN_DIM,start_token=START_TOKEN,goal_out_size=GOAL_OUT_SIZE,goal_size=GOAL_SIZE,step_size=4,D_model=discriminator) File "/Users/zhouye/Documents/dtwave/LeakGAN/Image_COCO/LeakGANModel.py", line 284, in init self.pretrain_manager_updates = pretrain_manager_opt.apply_gradients(pretrain_manager_grads_vars) File "/Users/zhouye/miniconda/envs/py36/lib/python3.6/site-packages/tensorflow/python/training/optimizer.py", line 593, in apply_gradients ([str(v) for _, v, _ in converted_grads_and_vars],)) ValueError: No gradients provided for any variable: ["<tf.Variable 'Manager/Manager/Variable:0' shape=(1880, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_1:0' shape=(128, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_2:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_3:0' shape=(1880, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_4:0' shape=(128, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_5:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_6:0' shape=(1880, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_7:0' shape=(128, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_8:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_9:0' shape=(1880, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_10:0' shape=(128, 128) dtype=float32_ref>", "<tf.Variable 'Manager/Manager/Variable_11:0' shape=(128,) dtype=float32_ref>", "<tf.Variable 'Manager/Manager_1/Variable:0' shape=(128, 1880) dtype=float32_ref>", "<tf.Variable 'Manager/Manager_1/Variable_1:0' shape=(1880,) dtype=float32_ref>", "<tf.Variable 'Manager/goal_init:0' shape=(64, 1880) dtype=float32_ref>"].

python3.6+tensorflow1.13

many thanks.