Error at reading data line 100000: Received a label value of 19143 which is outside the valid range of [0, 256).

[coreych]

Anyhow has a similar issue?

Run the following command

$ python execute.py

And the error:

Reading development and training data (limit: 0). reading data line 100000 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 19143 which is outside the valid range of [0, 256). Label values: 149 567 18943 7 7 1024 7 78 20 160 1216 320 11712 78 273 5 33 566 78 138 20 212 1650 392 104 1359 69 83 14028 3 241 487 33 273 7 33 142 3 7 619 547 7 7 124 33 415 4 2753 3035 33 562 79 79 127 354 47 19143 62 117 20 33 1664 78 6290 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 10939 which is outside the valid range of [0, 256). Label values: 13 5942 168 5 64 4 5 4 25 221 32 9 595 4 7 149 48 141 30 31 29 6 8 4 9 114 8 6 4 7 34 4 5 8 44 9 111 10245 5 59 9 5 136 5 52 6 4 4 2 42 15 6 15 8 150 9 7804 10939 924 96 5 13 16 19 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 5787 which is outside the valid range of [0, 256). Label values: 527 4 37 24 11 2 24 2 37 23 102 2 108 2 42 750 3 4 15 80 11 7 5787 2 2 9 29 7 2 25 6 4 85 267 5 2 252 2249 24 16 2 24 10 14 8 342 4 2 0 9 144 161 5 125 453 190 16 3 1060 21 85 369 2 2326 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 10895 which is outside the valid range of [0, 256). Label values: 4 2 1665 87 600 0 295 0 221 950 812 0 50 0 9 5 9 2 23 949 436 488 9 0 0 2 11 100 0 8 125 4 8 42 14 0 4 168 279 2 0 279 280 36 196 4 15 0 0 33 6 9 12 11 4 42 10895 9 4 13 15 358 0 4 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 10079 which is outside the valid range of [0, 256). Label values: 528 0 4 2577 13 0 189 0 4 4 4 0 3 0 2 9 2 0 4 4 26 18 2 0 0 0 398 4 0 9 34 148 36 7 130 0 2 13 4 0 0 4 4 15 9 745 23 0 0 10079 4101 2 40 5360 2 100 16 2 2 644 106 4 0 2 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 19143 which is outside the valid range of [0, 256). Label values: 9 0 2 87 300 0 4 0 2 2 2 0 9 0 0 2 0 0 2 2 294 838 0 0 0 0 37 2 0 2 4 7 9 137 10 0 0 568 337 0 0 2 2 16 16 807 77 0 0 9 30 0 13 30 0 43 19143 0 0 9 9 2 0 0 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 8089 which is outside the valid range of [0, 256). Label values: 2 0 0 290 4 0 2 0 0 0 0 0 2 0 0 0 0 0 0 0 4 4 0 0 0 0 287 0 0 0 4 444 2 9 6065 0 0 8089 4 0 0 0 0 2 2 4 34 0 0 2 2 0 261 2 0 106 16 0 0 2 2 0 0 0 W tensorflow/core/framework/op_kernel.cc:993] Invalid argument: Received a label value of 13568 which is outside the valid range of [0, 256). Label values: 0 0 0 3 2 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 2 2 0 0 0 0 4 0 0 0 4 9 0 2 4 0 0 4 2 0 0 0 0 0 0 2 4 0 0 0 0 0 13568 0 0 9 2 0 0 0 0 0 0 0 Traceback (most recent call last): File "execute.py", line 319, in train() File "execute.py", line 169, in train target_weights, bucket_id, False) File "/Users/user/tensorflow/chatbot-master/seq2seq_model.py", line 238, in step outputs = session.run(output_feed, input_feed) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 767, in run run_metadata_ptr) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 965, in _run feed_dict_string, options, run_metadata) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1015, in _do_run target_list, options, run_metadata) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/client/session.py", line 1035, in _do_call raise type(e)(node_def, op, message) tensorflow.python.framework.errors_impl.InvalidArgumentError: Received a label value of 19143 which is outside the valid range of [0, 256). Label values: 149 567 18943 7 7 1024 7 78 20 160 1216 320 11712 78 273 5 33 566 78 138 20 212 1650 392 104 1359 69 83 14028 3 241 487 33 273 7 33 142 3 7 619 547 7 7 124 33 415 4 2753 3035 33 562 79 79 127 354 47 19143 62 117 20 33 1664 78 6290 [[Node: model_with_buckets/sequence_loss/sequence_loss_by_example/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](model_with_buckets/embedding_attention_seq2seq/embedding_attention_decoder/attention_decoder/AttnOutputProjection/BiasAdd, model_with_buckets/sequence_loss/sequence_loss_by_example/Reshape)]]

Caused by op u'model_with_buckets/sequence_loss/sequence_loss_by_example/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits', defined at: File "execute.py", line 319, in train() File "execute.py", line 137, in train model = create_model(sess, False) File "execute.py", line 104, in create_model model = seq2seq_model.Seq2SeqModel( gConfig['enc_vocab_size'], gConfig['dec_vocab_size'], _buckets, gConfig['layer_size'], gConfig['num_layers'], gConfig['max_gradient_norm'], gConfig['batch_size'], gConfig['learning_rate'], gConfig['learning_rate_decay_factor'], forward_only=forward_only) File "/Users/user/tensorflow/chatbot-master/seq2seq_model.py", line 166, in init softmax_loss_function=softmax_loss_function) File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 1195, in model_with_buckets softmax_loss_function=softmax_loss_function)) File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 1110, in sequence_loss softmax_loss_function=softmax_loss_function)) File "/usr/local/lib/python2.7/site-packages/tensorflow/contrib/legacy_seq2seq/python/ops/seq2seq.py", line 1065, in sequence_loss_by_example labels=target, logits=logit) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.py", line 1713, in sparse_softmax_cross_entropy_with_logits precise_logits, labels, name=name) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/ops/gen_nn_ops.py", line 2378, in _sparse_softmax_cross_entropy_with_logits features=features, labels=labels, name=name) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/op_def_library.py", line 763, in apply_op op_def=op_def) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 2395, in create_op original_op=self._default_original_op, op_def=op_def) File "/usr/local/lib/python2.7/site-packages/tensorflow/python/framework/ops.py", line 1264, in init self._traceback = _extract_stack()

InvalidArgumentError (see above for traceback): Received a label value of 19143 which is outside the valid range of [0, 256). Label values: 149 567 18943 7 7 1024 7 78 20 160 1216 320 11712 78 273 5 33 566 78 138 20 212 1650 392 104 1359 69 83 14028 3 241 487 33 273 7 33 142 3 7 619 547 7 7 124 33 415 4 2753 3035 33 562 79 79 127 354 47 19143 62 117 20 33 1664 78 6290 [[Node: model_with_buckets/sequence_loss/sequence_loss_by_example/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits = SparseSoftmaxCrossEntropyWithLogits[T=DT_FLOAT, Tlabels=DT_INT32, _device="/job:localhost/replica:0/task:0/cpu:0"](model_with_buckets/embedding_attention_seq2seq/embedding_attention_decoder/attention_decoder/AttnOutputProjection/BiasAdd, model_with_buckets/sequence_loss/sequence_loss_by_example/Reshape)]]

[AbhishekAshokDubey]

I had a similar error, and it was dude to the following line: encoder_inputs_t.append(tf.placeholder(tf.int32, shape=[None], name="encoder{0}".format(i))) replace every such line, like above, to below encoder_inputs_t.append(tf.placeholder(tf.int32, shape=[None,], name="encoder{0}".format(i)))

Check the value of shape attribute. This surprising worked for me 👍

[sundaygeek]

@AbhishekAshokDubey which file is located of you changed the code?

[shantianyang]

hi, did you fixed the problem?

[shantianyang]

@coreych ,did you fix this problem?

[vipinbansal1]

Please switch to latest Tensorflow version.

[rinush]

In the last layer of the model use proper shape. For eg you used model.add(Dense(256, activation='softmax')) as the last layer. Here 256 restricts output's value from [0, 256) change its shape to the maximum output label. For eg your output is from label [0,23000) then use model.add(Dense(23000, activation='softmax'))

[coreych]

Switch to latest TensorFlow version.

[sechabapeter]

please help

InvalidArgumentError: Received a label value of 3298 which is outside the valid range of [0, 2). Label values: 980 3113 2936 1164 2232 3298 1612 2849 1877 3205 3065 1432 2407 2582 1300 2143 1074 1000 2692 1341 1770 1976 2120 [[node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits (defined at :1) ]] [Op:__inference_train_function_2707]

Function call stack: train_function

[vipinbansal1]

if its a regression problem, according to me its possible to get such response from the system. In case of classification, you have to use softmax on the output layer to ivercome such problem,

[sechabapeter]

@vipinbansal1 Thanks for the response I did try to use softmax but the issue was not resolved

numDim = X_train_normalized.shape[1] dnnModel = tf.keras.Sequential([ layers.Dense(16, activation = 'relu', input_shape =(numDim,)), layers.BatchNormalization(), layers.Dropout(0.3), layers.Dense(16, activation = 'relu'), layers.BatchNormalization(), layers.Dropout(0.3), layers.Dense(126, activation = 'relu'), layers.BatchNormalization(), layers.Dropout(0.5), layers.Dense(160, activation = 'relu'), layers.BatchNormalization(), layers.Dropout(0.5), layers.Dense(10, activation = 'relu'), layers.Dropout(0.1), layers.BatchNormalization(), layers.Dense(2)

]) optimizer = tf.keras.optimizers.Adam(0.01) dnnModel.compile(optimizer=optimizer, loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])``

[sechabapeter]

numDim = X_train_normalized.shape[1]
dnnModel = tf.keras.Sequential([
    layers.Dense(16, activation = 'relu', input_shape =(numDim,)),
    layers.BatchNormalization(),
    layers.Dropout(0.3),
    layers.Dense(16, activation = 'relu'),
    layers.BatchNormalization(),
    layers.Dropout(0.3),
    layers.Dense(126, activation = 'relu'),
    layers.BatchNormalization(),
    layers.Dropout(0.5),
    layers.Dense(160, activation = 'relu'),
    layers.BatchNormalization(),
    layers.Dropout(0.5),
    layers.Dense(10, activation = 'softmax' ),
    layers.Dropout(0.1),
    layers.BatchNormalization(),
    layers.Dense(2)

])
optimizer = tf.keras.optimizers.Adam(0.01)
dnnModel.compile(optimizer=optimizer, loss=tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True), metrics=['accuracy'])

dnnModel.fit(X_train_normalized, y_train, epochs=100)

Epoch 1/100
---------------------------------------------------------------------------
InvalidArgumentError                      Traceback (most recent call last)
<ipython-input-93-47e282adff89> in <module>
----> 1 dnnModel.fit(X_train_normalized, y_train, epochs=100)
      2 #last results accuracy shows training accuracy

~\Anaconda3\lib\site-packages\tensorflow\python\keras\engine\training.py in fit(self, x, y, batch_size, epochs, verbose, callbacks, validation_split, validation_data, shuffle, class_weight, sample_weight, initial_epoch, steps_per_epoch, validation_steps, validation_batch_size, validation_freq, max_queue_size, workers, use_multiprocessing)
   1181                 _r=1):
   1182               callbacks.on_train_batch_begin(step)
-> 1183               tmp_logs = self.train_function(iterator)
   1184               if data_handler.should_sync:
   1185                 context.async_wait()

~\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in __call__(self, *args, **kwds)
    887 
    888       with OptionalXlaContext(self._jit_compile):
--> 889         result = self._call(*args, **kwds)
    890 
    891       new_tracing_count = self.experimental_get_tracing_count()

~\Anaconda3\lib\site-packages\tensorflow\python\eager\def_function.py in _call(self, *args, **kwds)
    948         # Lifting succeeded, so variables are initialized and we can run the
    949         # stateless function.
--> 950         return self._stateless_fn(*args, **kwds)
    951     else:
    952       _, _, _, filtered_flat_args = \

~\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in __call__(self, *args, **kwargs)
   3021       (graph_function,
   3022        filtered_flat_args) = self._maybe_define_function(args, kwargs)
-> 3023     return graph_function._call_flat(
   3024         filtered_flat_args, captured_inputs=graph_function.captured_inputs)  # pylint: disable=protected-access
   3025 

~\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
   1958         and executing_eagerly):
   1959       # No tape is watching; skip to running the function.
-> 1960       return self._build_call_outputs(self._inference_function.call(
   1961           ctx, args, cancellation_manager=cancellation_manager))
   1962     forward_backward = self._select_forward_and_backward_functions(

~\Anaconda3\lib\site-packages\tensorflow\python\eager\function.py in call(self, ctx, args, cancellation_manager)
    589       with _InterpolateFunctionError(self):
    590         if cancellation_manager is None:
--> 591           outputs = execute.execute(
    592               str(self.signature.name),
    593               num_outputs=self._num_outputs,

~\Anaconda3\lib\site-packages\tensorflow\python\eager\execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
     57   try:
     58     ctx.ensure_initialized()
---> 59     tensors = pywrap_tfe.TFE_Py_Execute(ctx._handle, device_name, op_name,
     60                                         inputs, attrs, num_outputs)
     61   except core._NotOkStatusException as e:

InvalidArgumentError:  Received a label value of 3298 which is outside the valid range of [0, 2).  Label values: 1074 2232 2849 3298 2936 2407 1341 1770 2120 3205 2143 3065 2582 1877 3113 2692 980 1432 1000 1976 1164 1300 1612
     [[node sparse_categorical_crossentropy/SparseSoftmaxCrossEntropyWithLogits/SparseSoftmaxCrossEntropyWithLogits (defined at <ipython-input-93-47e282adff89>:1) ]] [Op:__inference_train_function_12138]

Function call stack:
train_function

[vipinbansal1]

last layer should have softmax as an activation function. Refer online available source code for more info...

[sechabapeter]

Thank you, got it right.