ciao
WARNING:tensorflow:From /Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/math_grad.py:1424: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
WARNING:tensorflow:From /Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/ops/math_grad.py:1424: where (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
Train on 29740 samples, validate on 7436 samples
2020-02-19 14:29:40.844512: W tensorflow/c/c_api.cc:326] Operation '{name:'keras_layer/cond/StatefulPartitionedCall' id:816 op device:{} def:{{{node keras_layer/cond/StatefulPartitionedCall}} = StatefulPartitionedCall[Tin=[DT_INT32, DT_INT32, DT_INT32, DT_RESOURCE, DT_RESOURCE, ..., DT_RESOURCE, DT_RESOURCE, DT_RESOURCE, DT_RESOURCE, DT_RESOURCE], Tout=[DT_FLOAT, DT_FLOAT, DT_INT32, DT_INT32, DT_INT32, ..., DT_RESOURCE, DT_RESOURCE, DT_RESOURCE, DT_RESOURCE, DT_RESOURCE], _gradient_op_type="PartitionedCall-14396", config="", config_proto="\n\007\n\003CPU\020\001\n\007\n\003GPU\020\0002\002J\0008\001", executor_type="", f=__forward_restored_function_body_22592[]](keras_layer/cond/StatefulPartitionedCall/Switch:1, keras_layer/cond/StatefulPartitionedCall/Switch_1:1, keras_layer/cond/StatefulPartitionedCall/Switch_2:1, keras_layer/cond/StatefulPartitionedCall/Switch_3:1, keras_layer/cond/StatefulPartitionedCall/Switch_4:1, keras_layer/cond/StatefulPartitionedCall/Switch_5:1, keras_layer/cond/StatefulPartitionedCall/Switch_6:1, keras_layer/cond/StatefulPartitionedCall/Switch_7:1, keras_layer/cond/StatefulPartitionedCall/Switch_8:1, keras_layer/cond/StatefulPartitionedCall/Switch_9:1, keras_layer/cond/StatefulPartitionedCall/Switch_10:1, keras_layer/cond/StatefulPartitionedCall/Switch_11:1, keras_layer/cond/StatefulPartitionedCall/Switch_12:1, keras_layer/cond/StatefulPartitionedCall/Switch_13:1, keras_layer/cond/StatefulPartitionedCall/Switch_14:1, keras_layer/cond/StatefulPartitionedCall/Switch_15:1, keras_layer/cond/StatefulPartitionedCall/Switch_16:1, keras_layer/cond/StatefulPartitionedCall/Switch_17:1, keras_layer/cond/StatefulPartitionedCall/Switch_18:1, keras_layer/cond/StatefulPartitionedCall/Switch_19:1, keras_layer/cond/StatefulPartitionedCall/Switch_20:1, keras_layer/cond/StatefulPartitionedCall/Switch_21:1, keras_layer/cond/StatefulPartitionedCall/Switch_22:1, keras_layer/cond/StatefulPartitionedCall/Switch_23:1, keras_layer/cond/StatefulPartitionedCall/Switch_24:1, keras_layer/cond/StatefulPartitionedCall/Switch_25:1, keras_layer/cond/StatefulPartitionedCall/Switch_26:1, keras_layer/cond/StatefulPartitionedCall/Switch_27:1, keras_layer/cond/StatefulPartitionedCall/Switch_28:1, keras_layer/cond/StatefulPartitionedCall/Switch_29:1, keras_layer/cond/StatefulPartitionedCall/Switch_30:1, keras_layer/cond/StatefulPartitionedCall/Switch_31:1, keras_layer/cond/StatefulPartitionedCall/Switch_32:1, keras_layer/cond/StatefulPartitionedCall/Switch_33:1, keras_layer/cond/StatefulPartitionedCall/Switch_34:1, keras_layer/cond/StatefulPartitionedCall/Switch_35:1, keras_layer/cond/StatefulPartitionedCall/Switch_36:1, keras_layer/cond/StatefulPartitionedCall/Switch_37:1, keras_layer/cond/StatefulPartitionedCall/Switch_38:1, keras_layer/cond/StatefulPartitionedCall/Switch_39:1, keras_layer/cond/StatefulPartitionedCall/Switch_40:1, keras_layer/cond/StatefulPartitionedCall/Switch_41:1, keras_layer/cond/StatefulPartitionedCall/Switch_42:1, keras_layer/cond/StatefulPartitionedCall/Switch_43:1, keras_layer/cond/StatefulPartitionedCall/Switch_44:1, keras_layer/cond/StatefulPartitionedCall/Switch_45:1, keras_layer/cond/StatefulPartitionedCall/Switch_46:1, keras_layer/cond/StatefulPartitionedCall/Switch_47:1, keras_layer/cond/StatefulPartitionedCall/Switch_48:1, keras_layer/cond/StatefulPartitionedCall/Switch_49:1, keras_layer/cond/StatefulPartitionedCall/Switch_50:1, keras_layer/cond/StatefulPartitionedCall/Switch_51:1, keras_layer/cond/StatefulPartitionedCall/Switch_52:1, keras_layer/cond/StatefulPartitionedCall/Switch_53:1, keras_layer/cond/StatefulPartitionedCall/Switch_54:1, keras_layer/cond/StatefulPartitionedCall/Switch_55:1, keras_layer/cond/StatefulPartitionedCall/Switch_56:1, keras_layer/cond/StatefulPartitionedCall/Switch_57:1, keras_layer/cond/StatefulPartitionedCall/Switch_58:1, keras_layer/cond/StatefulPartitionedCall/Switch_59:1, keras_layer/cond/StatefulPartitionedCall/Switch_60:1, keras_layer/cond/StatefulPartitionedCall/Switch_61:1, keras_layer/cond/StatefulPartitionedCall/Switch_62:1, keras_layer/cond/StatefulPartitionedCall/Switch_63:1, keras_layer/cond/StatefulPartitionedCall/Switch_64:1, keras_layer/cond/StatefulPartitionedCall/Switch_65:1, keras_layer/cond/StatefulPartitionedCall/Switch_66:1, keras_layer/cond/StatefulPartitionedCall/Switch_67:1, keras_layer/cond/StatefulPartitionedCall/Switch_68:1, keras_layer/cond/StatefulPartitionedCall/Switch_69:1, keras_layer/cond/StatefulPartitionedCall/Switch_70:1, keras_layer/cond/StatefulPartitionedCall/Switch_71:1, keras_layer/cond/StatefulPartitionedCall/Switch_72:1, keras_layer/cond/StatefulPartitionedCall/Switch_73:1, keras_layer/cond/StatefulPartitionedCall/Switch_74:1, keras_layer/cond/StatefulPartitionedCall/Switch_75:1, keras_layer/cond/StatefulPartitionedCall/Switch_76:1, keras_layer/cond/StatefulPartitionedCall/Switch_77:1, keras_layer/cond/StatefulPartitionedCall/Switch_78:1, keras_layer/cond/StatefulPartitionedCall/Switch_79:1, keras_layer/cond/StatefulPartitionedCall/Switch_80:1, keras_layer/cond/StatefulPartitionedCall/Switch_81:1, keras_layer/cond/StatefulPartitionedCall/Switch_82:1, keras_layer/cond/StatefulPartitionedCall/Switch_83:1, keras_layer/cond/StatefulPartitionedCall/Switch_84:1, keras_layer/cond/StatefulPartitionedCall/Switch_85:1, keras_layer/cond/StatefulPartitionedCall/Switch_86:1, keras_layer/cond/StatefulPartitionedCall/Switch_87:1, keras_layer/cond/StatefulPartitionedCall/Switch_88:1, keras_layer/cond/StatefulPartitionedCall/Switch_89:1, keras_layer/cond/StatefulPartitionedCall/Switch_90:1, keras_layer/cond/StatefulPartitionedCall/Switch_91:1, keras_layer/cond/StatefulPartitionedCall/Switch_92:1, keras_layer/cond/StatefulPartitionedCall/Switch_93:1, keras_layer/cond/StatefulPartitionedCall/Switch_94:1, keras_layer/cond/StatefulPartitionedCall/Switch_95:1, keras_layer/cond/StatefulPartitionedCall/Switch_96:1, keras_layer/cond/StatefulPartitionedCall/Switch_97:1, keras_layer/cond/StatefulPartitionedCall/Switch_98:1, keras_layer/cond/StatefulPartitionedCall/Switch_99:1, keras_layer/cond/StatefulPartitionedCall/Switch_100:1, keras_layer/cond/StatefulPartitionedCall/Switch_101:1, keras_layer/cond/StatefulPartitionedCall/Switch_102:1, keras_layer/cond/StatefulPartitionedCall/Switch_103:1, keras_layer/cond/StatefulPartitionedCall/Switch_104:1, keras_layer/cond/StatefulPartitionedCall/Switch_105:1, keras_layer/cond/StatefulPartitionedCall/Switch_106:1, keras_layer/cond/StatefulPartitionedCall/Switch_107:1, keras_layer/cond/StatefulPartitionedCall/Switch_108:1, keras_layer/cond/StatefulPartitionedCall/Switch_109:1, keras_layer/cond/StatefulPartitionedCall/Switch_110:1, keras_layer/cond/StatefulPartitionedCall/Switch_111:1, keras_layer/cond/StatefulPartitionedCall/Switch_112:1, keras_layer/cond/StatefulPartitionedCall/Switch_113:1, keras_layer/cond/StatefulPartitionedCall/Switch_114:1, keras_layer/cond/StatefulPartitionedCall/Switch_115:1, keras_layer/cond/StatefulPartitionedCall/Switch_116:1, keras_layer/cond/StatefulPartitionedCall/Switch_117:1, keras_layer/cond/StatefulPartitionedCall/Switch_118:1, keras_layer/cond/StatefulPartitionedCall/Switch_119:1, keras_layer/cond/StatefulPartitionedCall/Switch_120:1, keras_layer/cond/StatefulPartitionedCall/Switch_121:1, keras_layer/cond/StatefulPartitionedCall/Switch_122:1, keras_layer/cond/StatefulPartitionedCall/Switch_123:1, keras_layer/cond/StatefulPartitionedCall/Switch_124:1, keras_layer/cond/StatefulPartitionedCall/Switch_125:1, keras_layer/cond/StatefulPartitionedCall/Switch_126:1, keras_layer/cond/StatefulPartitionedCall/Switch_127:1, keras_layer/cond/StatefulPartitionedCall/Switch_128:1, keras_layer/cond/StatefulPartitionedCall/Switch_129:1, keras_layer/cond/StatefulPartitionedCall/Switch_130:1, keras_layer/cond/StatefulPartitionedCall/Switch_131:1, keras_layer/cond/StatefulPartitionedCall/Switch_132:1, keras_layer/cond/StatefulPartitionedCall/Switch_133:1, keras_layer/cond/StatefulPartitionedCall/Switch_134:1, keras_layer/cond/StatefulPartitionedCall/Switch_135:1, keras_layer/cond/StatefulPartitionedCall/Switch_136:1, keras_layer/cond/StatefulPartitionedCall/Switch_137:1, keras_layer/cond/StatefulPartitionedCall/Switch_138:1, keras_layer/cond/StatefulPartitionedCall/Switch_139:1, keras_layer/cond/StatefulPartitionedCall/Switch_140:1, keras_layer/cond/StatefulPartitionedCall/Switch_141:1, keras_layer/cond/StatefulPartitionedCall/Switch_142:1, keras_layer/cond/StatefulPartitionedCall/Switch_143:1, keras_layer/cond/StatefulPartitionedCall/Switch_144:1, keras_layer/cond/StatefulPartitionedCall/Switch_145:1, keras_layer/cond/StatefulPartitionedCall/Switch_146:1, keras_layer/cond/StatefulPartitionedCall/Switch_147:1, keras_layer/cond/StatefulPartitionedCall/Switch_148:1, keras_layer/cond/StatefulPartitionedCall/Switch_149:1, keras_layer/cond/StatefulPartitionedCall/Switch_150:1, keras_layer/cond/StatefulPartitionedCall/Switch_151:1, keras_layer/cond/StatefulPartitionedCall/Switch_152:1, keras_layer/cond/StatefulPartitionedCall/Switch_153:1, keras_layer/cond/StatefulPartitionedCall/Switch_154:1, keras_layer/cond/StatefulPartitionedCall/Switch_155:1, keras_layer/cond/StatefulPartitionedCall/Switch_156:1, keras_layer/cond/StatefulPartitionedCall/Switch_157:1, keras_layer/cond/StatefulPartitionedCall/Switch_158:1, keras_layer/cond/StatefulPartitionedCall/Switch_159:1, keras_layer/cond/StatefulPartitionedCall/Switch_160:1, keras_layer/cond/StatefulPartitionedCall/Switch_161:1, keras_layer/cond/StatefulPartitionedCall/Switch_162:1, keras_layer/cond/StatefulPartitionedCall/Switch_163:1, keras_layer/cond/StatefulPartitionedCall/Switch_164:1, keras_layer/cond/StatefulPartitionedCall/Switch_165:1, keras_layer/cond/StatefulPartitionedCall/Switch_166:1, keras_layer/cond/StatefulPartitionedCall/Switch_167:1, keras_layer/cond/StatefulPartitionedCall/Switch_168:1, keras_layer/cond/StatefulPartitionedCall/Switch_169:1, keras_layer/cond/StatefulPartitionedCall/Switch_170:1, keras_layer/cond/StatefulPartitionedCall/Switch_171:1, keras_layer/cond/StatefulPartitionedCall/Switch_172:1, keras_layer/cond/StatefulPartitionedCall/Switch_173:1, keras_layer/cond/StatefulPartitionedCall/Switch_174:1, keras_layer/cond/StatefulPartitionedCall/Switch_175:1, keras_layer/cond/StatefulPartitionedCall/Switch_176:1, keras_layer/cond/StatefulPartitionedCall/Switch_177:1, keras_layer/cond/StatefulPartitionedCall/Switch_178:1, keras_layer/cond/StatefulPartitionedCall/Switch_179:1, keras_layer/cond/StatefulPartitionedCall/Switch_180:1, keras_layer/cond/StatefulPartitionedCall/Switch_181:1, keras_layer/cond/StatefulPartitionedCall/Switch_182:1, keras_layer/cond/StatefulPartitionedCall/Switch_183:1, keras_layer/cond/StatefulPartitionedCall/Switch_184:1, keras_layer/cond/StatefulPartitionedCall/Switch_185:1, keras_layer/cond/StatefulPartitionedCall/Switch_186:1, keras_layer/cond/StatefulPartitionedCall/Switch_187:1, keras_layer/cond/StatefulPartitionedCall/Switch_188:1, keras_layer/cond/StatefulPartitionedCall/Switch_189:1, keras_layer/cond/StatefulPartitionedCall/Switch_190:1, keras_layer/cond/StatefulPartitionedCall/Switch_191:1, keras_layer/cond/StatefulPartitionedCall/Switch_192:1, keras_layer/cond/StatefulPartitionedCall/Switch_193:1, keras_layer/cond/StatefulPartitionedCall/Switch_194:1, keras_layer/cond/StatefulPartitionedCall/Switch_195:1, keras_layer/cond/StatefulPartitionedCall/Switch_196:1, keras_layer/cond/StatefulPartitionedCall/Switch_197:1, keras_layer/cond/StatefulPartitionedCall/Switch_198:1, keras_layer/cond/StatefulPartitionedCall/Switch_199:1, keras_layer/cond/StatefulPartitionedCall/Switch_200:1, keras_layer/cond/StatefulPartitionedCall/Switch_201:1)}}' 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.
Traceback (most recent call last):
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1365, in _do_call
    return fn(*args)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1348, in _run_fn
    self._extend_graph()
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1388, in _extend_graph
    tf_session.ExtendSession(self._session)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Node 'training/Adam/gradients/gradients/keras_layer/cond/StatefulPartitionedCall_1_grad/PartitionedCall': Connecting to invalid output 2 of source node keras_layer/cond/StatefulPartitionedCall_1 which has 2 outputs.

During handling of the above exception, another exception occurred:

Traceback (most recent call last):
  File "/Users/gimmi/Desktop/Università/MAGISTRALE/NLP/Progetto/code/model.py", line 181, in <module>
    modello.train(train,label,vocab_label_bn,vocab_label_wndmn,vocab_label_lex, train_dev, label_dev)
  File "/Users/gimmi/Desktop/Università/MAGISTRALE/NLP/Progetto/code/model.py", line 89, in train
    callbacks = [checkpoint, early_stopper],
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 727, in fit
    use_multiprocessing=use_multiprocessing)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py", line 675, in fit
    steps_name='steps_per_epoch')
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training_arrays.py", line 271, in model_iteration
    model.reset_metrics()
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/training.py", line 914, in reset_metrics
    m.reset_states()
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/metrics.py", line 210, in reset_states
    K.batch_set_value([(v, 0) for v in self.variables])
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py", line 3259, in batch_set_value
    get_session().run(assign_ops, feed_dict=feed_dict)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py", line 486, in get_session
    _initialize_variables(session)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/keras/backend.py", line 903, in _initialize_variables
    [variables_module.is_variable_initialized(v) for v in candidate_vars])
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 956, in run
    run_metadata_ptr)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1180, in _run
    feed_dict_tensor, options, run_metadata)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1359, in _do_run
    run_metadata)
  File "/Users/gimmi/anaconda3/lib/python3.7/site-packages/tensorflow_core/python/client/session.py", line 1384, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Node 'training/Adam/gradients/gradients/keras_layer/cond/StatefulPartitionedCall_1_grad/PartitionedCall': Connecting to invalid output 2 of source node keras_layer/cond/StatefulPartitionedCall_1 which has 2 outputs.

Process finished with exit code 1