Stackoverflow/Python
[Python] tensorflow/core/common_runtime/executor.cc:1197
The Neo
2023. 5. 24. 11:33
에러메세지
2023-05-24 11:16:48.358780: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_2_grad/concat/split_2/split_dim' with dtype int32 [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]] 2023-05-24 11:16:48.361971: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_grad/concat/split/split_dim' with dtype int32 [[{{node gradients/split_grad/concat/split/split_dim}}]] 2023-05-24 11:16:48.363507: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_1_grad/concat/split_1/split_dim' with dtype int32 [[{{node gradients/split_1_grad/concat/split_1/split_dim}}]] Epoch 1/1000 2023-05-24 11:16:48.742808: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_2_grad/concat/split_2/split_dim' with dtype int32 [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]] 2023-05-24 11:16:48.744458: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_grad/concat/split/split_dim' with dtype int32 [[{{node gradients/split_grad/concat/split/split_dim}}]] 2023-05-24 11:16:48.745851: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_1_grad/concat/split_1/split_dim' with dtype int32 [[{{node gradients/split_1_grad/concat/split_1/split_dim}}]] 2023-05-24 11:16:49.662961: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_2_grad/concat/split_2/split_dim' with dtype int32 [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]] 2023-05-24 11:16:49.664478: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_grad/concat/split/split_dim' with dtype int32 [[{{node gradients/split_grad/concat/split/split_dim}}]] 2023-05-24 11:16:49.665923: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_1_grad/concat/split_1/split_dim' with dtype int32 [[{{node gradients/split_1_grad/concat/split_1/split_dim}}]] 37/37 [==============================] - ETA: 0s - loss: 6.3564 - accuracy: 0.00172023-05-24 11:16:52.422661: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error message): INVALID_ARGUMENT: You must feed a value for placeholder tensor 'gradients/split_2_grad/concat/split_2/split_dim' with dtype int32 [[{{node gradients/split_2_grad/concat/split_2/split_dim}}]] 2023-05-24 11:16:52.424228: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_grad/concat/split/split_dim' with dtype int32 [[{{node gradients/split_grad/concat/split/split_dim}}]] 2023-05-24 11:16:52.425688: I tensorflow/core/common_runtime/executor.cc:1197] [/device:CPU:0] (DEBUG INFO) Executor start aborting (this does not indicate an error and you can ignore this message): INVALID_ARGUMENT: You must feed a value for plats/split_1_grad/concat/split_1/split_dim' with dtype int32
실제 에러 화면
원인
원인은 텐서플로우(Tensorflow) 버전이 2.12 버전일 때 발생하는 것으로 보인다.
해결방법
결국 텐서플로우를 다운그레이드 하는 것으로 해결을 하는 것 같고, 아니면 그냥 참고 경고 메세지를 보는 것 같다.
텐서플로우 다운그레이드
pip install tensorflow==2.11
참고자료
[2] https://discuss.tensorflow.org/t/you-must-feed-a-value-for-placeholder-tensor-gradients-split-dim-with-dtype-int32/15712/13
반응형