KlausRyu
commented
1 year ago hey i got same error how do you fix it
Open DivertisseurGames opened 1 year ago
KlausRyu
commented
1 year ago hey i got same error how do you fix it
The training is going fine but when it tries to evaluate the player against a random one it just stops working. I'm not getting any error, it just doesn't print anything. Is it just because my pc is taking very long? idk. Here's the full output : UserWarning: WARN: Official support for the
seedfunction is dropped. Standard practice is to reset gym environments usingenv.reset(seed=<desired seed>)logger.warn( C:\Users\Mael\AppData\Local\Programs\Python\Python310\lib\site-packages\gym\utils\env_checker.py:169: UserWarning: WARN:return_infois deprecated as an optional argument toreset.resetshould now always returnobs, infowhereobsis an observation, andinfois a dictionarycontaining additional information. logger.warn( C:\Users\Mael\AppData\Local\Programs\Python\Python310\lib\site-packages\gym\utils\passive_envchecker.py:233: DeprecationWarning:np.bool8is a deprecated alias for `np.bool. (Deprecated NumPy 1.24) if not isinstance(terminated, (bool, np.bool8)): 2023-01-06 13:17:47.279881: I tensorflow/core/platform/cpu_feature_guard.cc:193] This TensorFlow binary is optimized with oneAPI Deep Neural Network Library (oneDNN) to use the following CPU instructions in performance-critical operations: AVX AVX2 To enable them in other operations, rebuild TensorFlow with the appropriate compiler flags. 2023-01-06 13:17:47.312055: I tensorflow/compiler/mlir/mlir_graph_optimization_pass.cc:357] MLIR V1 optimization pass is not enabled 2023-01-06 13:17:47.423380: W tensorflow/c/c_api.cc:291] Operation '{name:'dense_2_1/kernel/Assign' id:179 op device:{requested: '', assigned: ''} def:{{{node dense_2_1/kernel/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](dense_2_1/kernel, dense_2_1/kernel/Initializer/stateless_random_uniform)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. WARNING:tensorflow:From C:\Users\Mael\AppData\Local\Programs\Python\Python310\lib\site-packages\tensorflow\python\autograph\pyct\static_analysis\liveness.py:83: Analyzer.lamba_check (from tensorflow.python.autograph.pyct.static_analysis.liveness) is deprecated and will be removed after 2023-09-23. Instructions for updating: Lambda fuctions will be no more assumed to be used in the statement where they are used, or at least in the same block. https://github.com/tensorflow/tensorflow/issues/56089 Training for 10000 steps ... Interval 1 (0 steps performed) C:\Users\Mael\AppData\Local\Programs\Python\Python310\lib\site-packages\keras\engine\training_v1.py:2357: UserWarning:Model.state_updateswill be removed in a future version. This property should not be used in TensorFlow 2.0, asupdates` are applied automatically. updates=self.state_updates, 2023-01-06 13:17:49.424296: W tensorflow/c/c_api.cc:291] Operation '{name:'dense_2/BiasAdd' id:95 op device:{requested: '', assigned: ''} def:{{{node dense_2/BiasAdd}} = BiasAdd[T=DT_FLOAT, _has_manual_control_dependencies=true, data_format="NHWC"](dense_2/MatMul, dense_2/BiasAdd/ReadVariableOp)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. 2023-01-06 13:17:49.455286: W tensorflow/c/c_api.cc:291] Operation '{name:'count_2/Assign' id:305 op device:{requested: '', assigned: ''} def:{{{node count_2/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](count_2, count_2/Initializer/zeros)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. 1001/10000 [==>...........................] - ETA: 2:30 - reward: 0.35712023-01-06 13:18:06.349830: W tensorflow/c/c_api.cc:291] Operation '{name:'dense_2_1/BiasAdd' id:189 op device:{requested: '', assigned: ''} def:{{{node dense_2_1/BiasAdd}} = BiasAdd[T=DT_FLOAT, _has_manual_control_dependencies=true, data_format="NHWC"](dense_2_1/MatMul, dense_2_1/BiasAdd/ReadVariableOp)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. 2023-01-06 13:18:06.634700: W tensorflow/c/c_api.cc:291] Operation '{name:'loss_3/AddN' id:411 op device:{requested: '', assigned: ''} def:{{{node loss_3/AddN}} = AddN[N=2, T=DT_FLOAT, _has_manual_control_dependencies=true](loss_3/mul, loss_3/mul_1)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. 2023-01-06 13:18:06.685677: W tensorflow/c/c_api.cc:291] Operation '{name:'training/Adam/dense_2/kernel/v/Assign' id:671 op device:{requested: '', assigned: ''} def:{{{node training/Adam/dense_2/kernel/v/Assign}} = AssignVariableOp[_has_manual_control_dependencies=true, dtype=DT_FLOAT, validate_shape=false](training/Adam/dense_2/kernel/v, training/Adam/dense_2/kernel/v/Initializer/zeros)}}' was changed by setting attribute after it was run by a session. This mutation will have no effect, and will trigger an error in the future. Either don't modify nodes after running them or create a new session. 10000/10000 [==============================] - 297s 30ms/step - reward: 0.7144 done, took 298.200 secondsand then nothing after the "done"