I Was following a post on 'Training a transformer model for a chatbot with TensorFlow 2.0'. I have encountered an error on my local machine although the code seems to work fine in colab. Below is the code snippet.
def encoder_layer(units, d_model, num_heads, dropout, name="encoder_layer"):
inputs = tf.keras.Input(shape=(None, d_model), name="inputs")
padding_mask = tf.keras.Input(shape=(1, 1, None), name="padding_mask")
attention = MultiHeadAttention(
d_model, num_heads, name="attention")({
'query': inputs,
'key': inputs,
'value': inputs,
'mask': padding_mask
})
attention = tf.keras.layers.Dropout(rate=dropout)(attention)
attention = tf.keras.layers.LayerNormalization(
epsilon=1e-6)(inputs + attention)
outputs = tf.keras.layers.Dense(units=units, activation='relu')(attention)
outputs = tf.keras.layers.Dense(units=d_model)(outputs)
outputs = tf.keras.layers.Dropout(rate=dropout)(outputs)
outputs = tf.keras.layers.LayerNormalization(
epsilon=1e-6)(attention + outputs)
return tf.keras.Model(
inputs=[inputs, padding_mask], outputs=outputs, name=name)
I called above function with the following function call;
sample_encoder_layer = encoder_layer(
units=512,
d_model=128,
num_heads=4,
dropout=0.3,
name="sample_encoder_layer")
Below is the traceback of the error:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in _AssertCompatible(values, dtype)
323 try:
--> 324 fn(values)
325 except ValueError as e:
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in _check_not_tensor(values)
275 def _check_not_tensor(values):
--> 276 _ = [_check_failed(v) for v in nest.flatten(values)
277 if isinstance(v, ops.Tensor)]
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in <listcomp>(.0)
276 _ = [_check_failed(v) for v in nest.flatten(values)
--> 277 if isinstance(v, ops.Tensor)]
278 # pylint: enable=invalid-name
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in _check_failed(v)
247 # it is safe to use here.
--> 248 raise ValueError(v)
249
ValueError: Tensor("attention_1/Identity:0", shape=(None, None, 128), dtype=float32)
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-20-3fa05a9bbfda> in <module>
----> 1 sample_encoder_layer = encoder_layer(units=512, d_model=128, num_heads=4, dropout=0.3, name='sample_encoder_layer')
2
3 tf.keras.utils.plot_model(
4 sample_encoder_layer, to_file='encoder_layer.png', show_shapes=True)
<ipython-input-18-357ca53de1c0> in encoder_layer(units, d_model, num_heads, dropout, name)
10 'mask': padding_mask
11 })
---> 12 attention = tf.keras.layers.Dropout(rate=dropout)(attention)
13 attention = tf.keras.layers.LayerNormalization(
14 epsilon=1e-6)(inputs + attention)
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
920 not base_layer_utils.is_in_eager_or_tf_function()):
921 with auto_control_deps.AutomaticControlDependencies() as acd:
--> 922 outputs = call_fn(cast_inputs, *args, **kwargs)
923 # Wrap Tensors in `outputs` in `tf.identity` to avoid
924 # circular dependencies.
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/keras/layers/core.py in call(self, inputs, training)
209 output = tf_utils.smart_cond(training,
210 dropped_inputs,
--> 211 lambda: array_ops.identity(inputs))
212 return output
213
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/keras/utils/tf_utils.py in smart_cond(pred, true_fn, false_fn, name)
63 pred, true_fn=true_fn, false_fn=false_fn, name=name)
64 return smart_module.smart_cond(
---> 65 pred, true_fn=true_fn, false_fn=false_fn, name=name)
66
67
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/smart_cond.py in smart_cond(pred, true_fn, false_fn, name)
57 else:
58 return control_flow_ops.cond(pred, true_fn=true_fn, false_fn=false_fn,
---> 59 name=name)
60
61
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
505 'in a future version' if date is None else ('after %s' % date),
506 instructions)
--> 507 return func(*args, **kwargs)
508
509 doc = _add_deprecated_arg_notice_to_docstring(
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/ops/control_flow_ops.py in cond(pred, true_fn, false_fn, strict, name, fn1, fn2)
1175 if (util.EnableControlFlowV2(ops.get_default_graph()) and
1176 not context.executing_eagerly()):
-> 1177 return cond_v2.cond_v2(pred, true_fn, false_fn, name)
1178
1179 # We needed to make true_fn/false_fn keyword arguments for
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/ops/cond_v2.py in cond_v2(pred, true_fn, false_fn, name)
82 true_name, collections=ops.get_default_graph()._collections), # pylint: disable=protected-access
83 add_control_dependencies=add_control_dependencies,
---> 84 op_return_value=pred)
85 false_graph = func_graph_module.func_graph_from_py_func(
86 false_name,
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
979 _, original_func = tf_decorator.unwrap(python_func)
980
--> 981 func_outputs = python_func(*func_args, **func_kwargs)
982
983 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/keras/layers/core.py in dropped_inputs()
205 noise_shape=self._get_noise_shape(inputs),
206 seed=self.seed,
--> 207 rate=self.rate)
208
209 output = tf_utils.smart_cond(training,
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/util/deprecation.py in new_func(*args, **kwargs)
505 'in a future version' if date is None else ('after %s' % date),
506 instructions)
--> 507 return func(*args, **kwargs)
508
509 doc = _add_deprecated_arg_notice_to_docstring(
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in dropout(x, keep_prob, noise_shape, seed, name, rate)
4341 raise ValueError("You must provide a rate to dropout.")
4342
-> 4343 return dropout_v2(x, rate, noise_shape=noise_shape, seed=seed, name=name)
4344
4345
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/ops/nn_ops.py in dropout_v2(x, rate, noise_shape, seed, name)
4422 raise ValueError("rate must be a scalar tensor or a float in the "
4423 "range [0, 1), got %g" % rate)
-> 4424 x = ops.convert_to_tensor(x, name="x")
4425 x_dtype = x.dtype
4426 if not x_dtype.is_floating:
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1339
1340 if ret is None:
-> 1341 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1342
1343 if ret is NotImplemented:
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
319 as_ref=False):
320 _ = as_ref
--> 321 return constant(v, dtype=dtype, name=name)
322
323
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
260 """
261 return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 262 allow_broadcast=True)
263
264
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
298 tensor_util.make_tensor_proto(
299 value, dtype=dtype, shape=shape, verify_shape=verify_shape,
--> 300 allow_broadcast=allow_broadcast))
301 dtype_value = attr_value_pb2.AttrValue(type=tensor_value.tensor.dtype)
302 const_tensor = g._create_op_internal( # pylint: disable=protected-access
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in make_tensor_proto(values, dtype, shape, verify_shape, allow_broadcast)
449 nparray = np.empty(shape, dtype=np_dt)
450 else:
--> 451 _AssertCompatible(values, dtype)
452 nparray = np.array(values, dtype=np_dt)
453 # check to them.
~/anaconda3/envs/tf-chatbot/lib/python3.6/site-packages/tensorflow/python/framework/tensor_util.py in _AssertCompatible(values, dtype)
326 [mismatch] = e.args
327 if dtype is None:
--> 328 raise TypeError("Expected any non-tensor type, got a tensor instead.")
329 else:
330 raise TypeError("Expected %s, got %s of type '%s' instead." %
TypeError: Expected any non-tensor type, got a tensor instead.
I had this error when I converted a function argument of int datatype to tf.constant . I resolved the issue in my case by undoing it. I faced this issue when I was converting TF1 codes to TF2.3.0 . Looking at your error trace I can see it's pointed to handling some constants in tf-chatbot. Kindly check how that constant is handled.
This is a fixed issue in TensorFlow 2.3.0 onwards. Can you upgrade your TensorFlow version?
pip install tensorflow==2.3.0
pip install --upgrade tensorflow
Related
I was trying to reproach the examples Transfer learning and fine-tuning adapting for my problem My colab with GPU. When I use a softmax in the last Dense Layers, this error not ocorrer. But with 'from_logits=True', this error ocorrer, my imagens are jpg and they are divided in folders:
InvalidArgumentError Traceback (most recent call last)
<ipython-input-85-7ea61d5df8ec> in <module>()
----> 1 loss0, accuracy0, auc0, precision0, recall0 = model.evaluate(val_ds)
5 frames
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py in evaluate(self, x, y, batch_size, verbose, sample_weight, steps, callbacks, max_queue_size, workers, use_multiprocessing, return_dict)
1387 with trace.Trace('test', step_num=step, _r=1):
1388 callbacks.on_test_batch_begin(step)
-> 1389 tmp_logs = self.test_function(iterator)
1390 if data_handler.should_sync:
1391 context.async_wait()
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in __call__(self, *args, **kwds)
826 tracing_count = self.experimental_get_tracing_count()
827 with trace.Trace(self._name) as tm:
--> 828 result = self._call(*args, **kwds)
829 compiler = "xla" if self._experimental_compile else "nonXla"
830 new_tracing_count = self.experimental_get_tracing_count()
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/def_function.py in _call(self, *args, **kwds)
893 # If we did not create any variables the trace we have is good enough.
894 return self._concrete_stateful_fn._call_flat(
--> 895 filtered_flat_args, self._concrete_stateful_fn.captured_inputs) # pylint: disable=protected-access
896
897 def fn_with_cond(inner_args, inner_kwds, inner_filtered_flat_args):
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in _call_flat(self, args, captured_inputs, cancellation_manager)
1917 # No tape is watching; skip to running the function.
1918 return self._build_call_outputs(self._inference_function.call(
-> 1919 ctx, args, cancellation_manager=cancellation_manager))
1920 forward_backward = self._select_forward_and_backward_functions(
1921 args,
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/function.py in call(self, ctx, args, cancellation_manager)
558 inputs=args,
559 attrs=attrs,
--> 560 ctx=ctx)
561 else:
562 outputs = execute.execute_with_cancellation(
/usr/local/lib/python3.6/dist-packages/tensorflow/python/eager/execute.py in quick_execute(op_name, num_outputs, inputs, attrs, ctx, name)
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:
62 if name is not None:
InvalidArgumentError: 2 root error(s) found.
(0) Invalid argument: assertion failed: [predictions must be >= 0] [Condition x >= y did not hold element-wise:] [x (Dense121/dense_1/BiasAdd:0) = ] [[0.853173912 1.97515857 0.608713508...]...] [y (Cast_4/x:0) = ] [0]
[[{{node assert_greater_equal/Assert/AssertGuard/else/_1/assert_greater_equal/Assert/AssertGuard/Assert}}]]
(1) Invalid argument: assertion failed: [predictions must be >= 0] [Condition x >= y did not hold element-wise:] [x (Dense121/dense_1/BiasAdd:0) = ] [[0.853173912 1.97515857 0.608713508...]...] [y (Cast_4/x:0) = ] [0]
[[{{node assert_greater_equal/Assert/AssertGuard/else/_1/assert_greater_equal/Assert/AssertGuard/Assert}}]]
[[assert_greater_equal_2/Assert/AssertGuard/branch_executed/_65/_167]]
0 successful operations.
0 derived errors ignored. [Op:__inference_test_function_61870]
Function call stack:
test_function -> test_function
I tried several things to solve and nothing
I am trying to make a Keras layer that returns None in its tuple.
class transformer_IO(tf.keras.layers.Layer):
def call(self, input):
return (input, None, None, None)
However, when I try to compile with this error, I get
AttributeError: 'NoneType' object has no attribute 'shape'
Here is an example
!pip install transformers
from transformers import TFBertModel
import tensorflow as tf
from copy import deepcopy
class transformer_IO(tf.keras.layers.Layer):
def call(self, input):
return (input, None, None, None)
def get_functional_model_protoFix():
bioRoberta_f = TFBertModel.from_pretrained('bert-base-uncased', from_pt=True)
Q_Tlayer0_f = deepcopy(bioRoberta_f.layers[0].encoder.layer[8])
Q_Tlayer0_f._name = Q_Tlayer0_f._name + 'Query_f'
Q_Tlayer1_f = deepcopy(bioRoberta_f.layers[0].encoder.layer[9])
Q_Tlayer1_f._name = Q_Tlayer1_f._name + 'Query_f'
transIO = transformer_IO()
inputIds = tf.keras.Input(shape=(None,), dtype=tf.int32, name='input_Q')
Q_outputs = bioRoberta_f(inputIds)[0]
Q_outputs = transIO(Q_outputs)
Q_outputs = Q_Tlayer0_f(Q_outputs)[0]
Q_outputs = transIO(Q_outputs)
Q_outputs = Q_Tlayer1_f(Q_outputs)[0]
modelNew = tf.keras.Model(inputs=inputIds, outputs=Q_outputs)
return modelNew
model_functional = get_functional_model_protoFix()
model_functional.compile(loss=loss_fn,
optimizer=tfa.optimizers.AdamW(weight_decay=1e-4, learning_rate=1e-5,
epsilon=1e-06))
Full error message
---------------------------------------------------------------------------
AttributeError Traceback (most recent call last)
<ipython-input-35-a029c18cecf9> in <module>()
----> 1 model_functional_new = get_functional_model_protoFix()
2 model_functional_new.compile(loss=loss_fn,
3 optimizer=tfa.optimizers.AdamW(weight_decay=1e-4, learning_rate=1e-5,
4 epsilon=1e-06))
7 frames
<ipython-input-34-693ee085f848> in get_functional_model_protoFix()
13
14 Q_outputs = bioRoberta_f(inputIds)[0]
---> 15 Q_outputs = transIO(Q_outputs)
16 Q_outputs = Q_Tlayer0_f(Q_outputs)[0]
17 Q_outputs = transIO(Q_outputs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
952 kwargs.pop('mask')
953 inputs, outputs = self._set_connectivity_metadata_(
--> 954 inputs, outputs, args, kwargs)
955 self._handle_activity_regularization(inputs, outputs)
956 self._set_mask_metadata(inputs, outputs, input_masks)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _set_connectivity_metadata_(self, inputs, outputs, args, kwargs)
2312 # This updates the layer history of the output tensor(s).
2313 self._add_inbound_node(
-> 2314 input_tensors=inputs, output_tensors=outputs, arguments=arguments)
2315 return inputs, outputs
2316
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/base_layer.py in _add_inbound_node(self, input_tensors, output_tensors, arguments)
2342 input_tensors=input_tensors,
2343 output_tensors=output_tensors,
-> 2344 arguments=arguments)
2345
2346 # Update tensor history metadata.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/node.py in __init__(self, outbound_layer, inbound_layers, node_indices, tensor_indices, input_tensors, output_tensors, arguments)
108 self.input_shapes = nest.map_structure(backend.int_shape, input_tensors)
109 # Nested structure of shape tuples, shapes of output_tensors.
--> 110 self.output_shapes = nest.map_structure(backend.int_shape, output_tensors)
111
112 # Optional keyword arguments to layer's `call`.
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py in map_structure(func, *structure, **kwargs)
615
616 return pack_sequence_as(
--> 617 structure[0], [func(*x) for x in entries],
618 expand_composites=expand_composites)
619
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/nest.py in <listcomp>(.0)
615
616 return pack_sequence_as(
--> 617 structure[0], [func(*x) for x in entries],
618 expand_composites=expand_composites)
619
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py in int_shape(x)
1201 """
1202 try:
-> 1203 shape = x.shape
1204 if not isinstance(shape, tuple):
1205 shape = tuple(shape.as_list())
AttributeError: 'NoneType' object has no attribute 'shape'
When saving a Keras model defined like this:
# define model
model = Sequential()
model.add(LSTM(200, activation='relu', input_shape=(n_steps_in, n_features)))
model.add(RepeatVector(n_steps_out))
model.add(LSTM(200, activation='relu', return_sequences=True))
model.add(TimeDistributed(Dense(n_features)))
model.compile(optimizer='adam', loss='mse')
model.save(path)
I got this following message:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
~/anaconda3/envs/topic_forecaster/lib/python3.7/inspect.py in getfullargspec(func)
1125 skip_bound_arg=False,
-> 1126 sigcls=Signature)
1127 except Exception as ex:
~/anaconda3/envs/topic_forecaster/lib/python3.7/inspect.py in _signature_from_callable(obj, follow_wrapper_chains, skip_bound_arg, sigcls)
2287 return _signature_from_builtin(sigcls, obj,
-> 2288 skip_bound_arg=skip_bound_arg)
2289
~/anaconda3/envs/topic_forecaster/lib/python3.7/inspect.py in _signature_from_builtin(cls, func, skip_bound_arg)
2111 if not s:
-> 2112 raise ValueError("no signature found for builtin {!r}".format(func))
2113
ValueError: no signature found for builtin <tensorflow.python.keras.saving.saved_model.save_impl.LayerCall object at 0x7f8c1f357190>
The above exception was the direct cause of the following exception:
TypeError Traceback (most recent call last)
<ipython-input-9-3fe80778ab16> in <module>
3 path = Path.cwd().parent / 'models' / 'tpi'
4 Path(path).mkdir(parents=True, exist_ok=True)
----> 5 model.save(str(path))
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/network.py in save(self, filepath, overwrite, include_optimizer, save_format, signatures, options)
973 """
974 saving.save_model(self, filepath, overwrite, include_optimizer, save_format,
--> 975 signatures, options)
976
977 def save_weights(self, filepath, overwrite=True, save_format=None):
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/save.py in save_model(model, filepath, overwrite, include_optimizer, save_format, signatures, options)
113 else:
114 saved_model_save.save(model, filepath, overwrite, include_optimizer,
--> 115 signatures, options)
116
117
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save.py in save(model, filepath, overwrite, include_optimizer, signatures, options)
72 # default learning phase placeholder.
73 with K.learning_phase_scope(0):
---> 74 save_lib.save(model, filepath, signatures, options)
75
76 if not include_optimizer:
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/saved_model/save.py in save(obj, export_dir, signatures, options)
868 if signatures is None:
869 signatures = signature_serialization.find_function_to_export(
--> 870 checkpoint_graph_view)
871
872 signatures = signature_serialization.canonicalize_signatures(signatures)
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/saved_model/signature_serialization.py in find_function_to_export(saveable_view)
62 # If the user did not specify signatures, check the root object for a function
63 # that can be made into a signature.
---> 64 functions = saveable_view.list_functions(saveable_view.root)
65 signature = functions.get(DEFAULT_SIGNATURE_ATTR, None)
66 if signature is not None:
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/saved_model/save.py in list_functions(self, obj)
139 if obj_functions is None:
140 obj_functions = obj._list_functions_for_serialization( # pylint: disable=protected-access
--> 141 self._serialization_cache)
142 self._functions[obj] = obj_functions
143 return obj_functions
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/engine/base_layer.py in _list_functions_for_serialization(self, serialization_cache)
2420 def _list_functions_for_serialization(self, serialization_cache):
2421 return (self._trackable_saved_model_saver
-> 2422 .list_functions_for_serialization(serialization_cache))
2423
2424
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/base_serialization.py in list_functions_for_serialization(self, serialization_cache)
89 `ConcreteFunction`.
90 """
---> 91 fns = self.functions_to_serialize(serialization_cache)
92
93 # The parent AutoTrackable class saves all user-defined tf.functions, and
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/layer_serialization.py in functions_to_serialize(self, serialization_cache)
77 def functions_to_serialize(self, serialization_cache):
78 return (self._get_serialized_attributes(
---> 79 serialization_cache).functions_to_serialize)
80
81 def _get_serialized_attributes(self, serialization_cache):
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/layer_serialization.py in _get_serialized_attributes(self, serialization_cache)
92
93 object_dict, function_dict = self._get_serialized_attributes_internal(
---> 94 serialization_cache)
95
96 serialized_attr.set_and_validate_objects(object_dict)
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/model_serialization.py in _get_serialized_attributes_internal(self, serialization_cache)
51 objects, functions = (
52 super(ModelSavedModelSaver, self)._get_serialized_attributes_internal(
---> 53 serialization_cache))
54 functions['_default_save_signature'] = default_signature
55 return objects, functions
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/layer_serialization.py in _get_serialized_attributes_internal(self, serialization_cache)
101 """Returns dictionary of serialized attributes."""
102 objects = save_impl.wrap_layer_objects(self.obj, serialization_cache)
--> 103 functions = save_impl.wrap_layer_functions(self.obj, serialization_cache)
104 # Attribute validator requires that the default save signature is added to
105 # function dict, even if the value is None.
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in wrap_layer_functions(layer, serialization_cache)
154 # Reset the losses of the layer and its children. The call function in each
155 # child layer is replaced with tf.functions.
--> 156 original_fns = _replace_child_layer_functions(layer, serialization_cache)
157 original_losses = _reset_layer_losses(layer)
158
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in _replace_child_layer_functions(layer, serialization_cache)
246 layer_fns = (
247 child_layer._trackable_saved_model_saver._get_serialized_attributes(
--> 248 serialization_cache).functions)
249 else:
250 layer_fns = (
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/layer_serialization.py in _get_serialized_attributes(self, serialization_cache)
92
93 object_dict, function_dict = self._get_serialized_attributes_internal(
---> 94 serialization_cache)
95
96 serialized_attr.set_and_validate_objects(object_dict)
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/layer_serialization.py in _get_serialized_attributes_internal(self, serialization_cache)
101 """Returns dictionary of serialized attributes."""
102 objects = save_impl.wrap_layer_objects(self.obj, serialization_cache)
--> 103 functions = save_impl.wrap_layer_functions(self.obj, serialization_cache)
104 # Attribute validator requires that the default save signature is added to
105 # function dict, even if the value is None.
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in wrap_layer_functions(layer, serialization_cache)
164 call_fn_with_losses = call_collection.add_function(
165 _wrap_call_and_conditional_losses(layer),
--> 166 '{}_layer_call_and_return_conditional_losses'.format(layer.name))
167 call_fn = call_collection.add_function(
168 _extract_outputs_from_fn(layer, call_fn_with_losses),
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in add_function(self, call_fn, name)
492 # Manually add traces for layers that have keyword arguments and have
493 # a fully defined input signature.
--> 494 self.add_trace(*self._input_signature)
495 return fn
496
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in add_trace(self, *args, **kwargs)
411 fn.get_concrete_function(*args, **kwargs)
412
--> 413 trace_with_training(True)
414 trace_with_training(False)
415 else:
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in trace_with_training(value, fn)
409 utils.set_training_arg(value, self._training_arg_index, args, kwargs)
410 with K.learning_phase_scope(value):
--> 411 fn.get_concrete_function(*args, **kwargs)
412
413 trace_with_training(True)
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in get_concrete_function(self, *args, **kwargs)
536 if not self.call_collection.tracing:
537 self.call_collection.add_trace(*args, **kwargs)
--> 538 return super(LayerCall, self).get_concrete_function(*args, **kwargs)
539
540
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in get_concrete_function(self, *args, **kwargs)
774 if self._stateful_fn is None:
775 initializer_map = object_identity.ObjectIdentityDictionary()
--> 776 self._initialize(args, kwargs, add_initializers_to=initializer_map)
777 self._initialize_uninitialized_variables(initializer_map)
778
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in _initialize(self, args, kwds, add_initializers_to)
406 self._concrete_stateful_fn = (
407 self._stateful_fn._get_concrete_function_internal_garbage_collected( # pylint: disable=protected-access
--> 408 *args, **kwds))
409
410 def invalid_creator_scope(*unused_args, **unused_kwds):
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _get_concrete_function_internal_garbage_collected(self, *args, **kwargs)
1846 if self.input_signature:
1847 args, kwargs = None, None
-> 1848 graph_function, _, _ = self._maybe_define_function(args, kwargs)
1849 return graph_function
1850
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _maybe_define_function(self, args, kwargs)
2148 graph_function = self._function_cache.primary.get(cache_key, None)
2149 if graph_function is None:
-> 2150 graph_function = self._create_graph_function(args, kwargs)
2151 self._function_cache.primary[cache_key] = graph_function
2152 return graph_function, args, kwargs
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/function.py in _create_graph_function(self, args, kwargs, override_flat_arg_shapes)
2039 arg_names=arg_names,
2040 override_flat_arg_shapes=override_flat_arg_shapes,
-> 2041 capture_by_value=self._capture_by_value),
2042 self._function_attributes,
2043 # Tell the ConcreteFunction to clean up its graph once it goes out of
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/framework/func_graph.py in func_graph_from_py_func(name, python_func, args, kwargs, signature, func_graph, autograph, autograph_options, add_control_dependencies, arg_names, op_return_value, collections, capture_by_value, override_flat_arg_shapes)
913 converted_func)
914
--> 915 func_outputs = python_func(*func_args, **func_kwargs)
916
917 # invariant: `func_outputs` contains only Tensors, CompositeTensors,
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/eager/def_function.py in wrapped_fn(*args, **kwds)
356 # __wrapped__ allows AutoGraph to swap in a converted function. We give
357 # the function a weak reference to itself to avoid a reference cycle.
--> 358 return weak_wrapped_fn().__wrapped__(*args, **kwds)
359 weak_wrapped_fn = weakref.ref(wrapped_fn)
360
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in wrapper(*args, **kwargs)
513 layer, inputs=inputs, build_graph=False, training=training,
514 saving=True):
--> 515 ret = method(*args, **kwargs)
516 _restore_layer_losses(original_losses)
517 return ret
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in wrap_with_training_arg(*args, **kwargs)
109 training,
110 lambda: replace_training_and_call(True),
--> 111 lambda: replace_training_and_call(False))
112
113 # Create arg spec for decorated function. If 'training' is not defined in the
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/utils/tf_utils.py in smart_cond(pred, true_fn, false_fn, name)
57 pred, true_fn=true_fn, false_fn=false_fn, name=name)
58 return smart_module.smart_cond(
---> 59 pred, true_fn=true_fn, false_fn=false_fn, name=name)
60
61
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/framework/smart_cond.py in smart_cond(pred, true_fn, false_fn, name)
52 if pred_value is not None:
53 if pred_value:
---> 54 return true_fn()
55 else:
56 return false_fn()
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in <lambda>()
108 return tf_utils.smart_cond(
109 training,
--> 110 lambda: replace_training_and_call(True),
111 lambda: replace_training_and_call(False))
112
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/utils.py in replace_training_and_call(training)
104 def replace_training_and_call(training):
105 set_training_arg(training, training_arg_index, args, kwargs)
--> 106 return wrapped_call(*args, **kwargs)
107
108 return tf_utils.smart_cond(
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/saving/saved_model/save_impl.py in call_and_return_conditional_losses(inputs, *args, **kwargs)
555 layer_call = _get_layer_call_method(layer)
556 def call_and_return_conditional_losses(inputs, *args, **kwargs):
--> 557 return layer_call(inputs, *args, **kwargs), layer.get_losses_for(inputs)
558 return _create_call_fn_decorator(layer, call_and_return_conditional_losses)
559
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/layers/wrappers.py in call(self, inputs, training, mask)
218 def call(self, inputs, training=None, mask=None):
219 kwargs = {}
--> 220 if generic_utils.has_arg(self.layer.call, 'training'):
221 kwargs['training'] = training
222
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/keras/utils/generic_utils.py in has_arg(fn, name, accept_all)
302 bool, whether `fn` accepts a `name` keyword argument.
303 """
--> 304 arg_spec = tf_inspect.getfullargspec(fn)
305 if accept_all and arg_spec.varkw is not None:
306 return True
~/anaconda3/envs/topic_forecaster/lib/python3.7/site-packages/tensorflow_core/python/util/tf_inspect.py in getfullargspec(obj)
255 if d.decorator_argspec is not None:
256 return _convert_maybe_argspec_to_fullargspec(d.decorator_argspec)
--> 257 return _getfullargspec(target)
258
259
~/anaconda3/envs/topic_forecaster/lib/python3.7/inspect.py in getfullargspec(func)
1130 # else. So to be fully backwards compatible, we catch all
1131 # possible exceptions here, and reraise a TypeError.
-> 1132 raise TypeError('unsupported callable') from ex
1133
1134 args = []
TypeError: unsupported callable
However, when saving a regular model without a TimeDistributed layer as below, it worked fine:
mnist = tf.keras.datasets.mnist
(x_train, y_train), (x_test, y_test) = mnist.load_data()
x_train, x_test = x_train / 255.0, x_test / 255.0
model = tf.keras.models.Sequential([
tf.keras.layers.Flatten(input_shape=(28, 28)),
tf.keras.layers.Dense(128, activation='relu'),
tf.keras.layers.Dropout(0.2),
tf.keras.layers.Dense(10)
])
loss_fn = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
model.compile(optimizer='adam',
loss=loss_fn,
metrics=['accuracy'])
model.fit(x_train, y_train, epochs=5)
model.evaluate(x_test, y_test, verbose=2)
model.save('temp', save_format='tf')
By upgrading Tensorflow to 2.1 with CUDA10 using Anaconda as below, the problem is solved.
conda create -n tf-gpu-cuda10 tensorflow-gpu=2.1 cudatoolkit=10
conda activate tf-gpu-cuda10
How do I feed a tf.keras model, that includes a 1D input TF Hub module, with a tf.data.Dataset?
(Ultimately, the aim is to use a single tf.data.Dataset with a multi-input, multi-output keras funtional api model.)
Tried this:
import tensorflow as tf
import tensorflow_hub as hub
embed = "https://tfhub.dev/google/tf2-preview/gnews-swivel-20dim/1"
hub_layer = hub.KerasLayer(embed, output_shape=[20], input_shape=[],
dtype=tf.string, trainable=True, name='hub_layer')
# From tf hub webpage: "The module takes a batch of sentences in a 1-D tensor of strings as input."
input_tensor = tf.keras.Input(shape=(), dtype=tf.string)
hub_tensor = hub_layer(input_tensor)
x = tf.keras.layers.Dense(16, activation='relu')(hub_tensor)#(x)
main_output = tf.keras.layers.Dense(units=4, activation='softmax', name='main_output')(x)
model = tf.keras.models.Model(inputs=[input_tensor], outputs=[main_output])
# This works as expected.
X_tensor = tf.constant(['Hello World', 'The Quick Brown Fox'])
model(X_tensor)
# This fails
X_ds = tf.data.Dataset.from_tensors(X_tensor)
X_ds.element_spec
model(X_ds)
Expectation was that the 1D tensor in the dataset would be automatically extracted and consumed by the model.
Error message:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
in
21 X_ds = tf.data.Dataset.from_tensors(X_tensor)
22 X_ds.element_spec
---> 23 model(X_ds)
24
25
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/base_layer.py in __call__(self, *args, **kwargs)
966 with base_layer_utils.autocast_context_manager(
967 self._compute_dtype):
--> 968 outputs = self.call(cast_inputs, *args, **kwargs)
969 self._handle_activity_regularization(inputs, outputs)
970 self._set_mask_metadata(inputs, outputs, input_masks)
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in call(self, inputs, training, mask)
717 return self._run_internal_graph(
718 inputs, training=training, mask=mask,
--> 719 convert_kwargs_to_constants=base_layer_utils.call_context().saving)
720
721 def compute_output_shape(self, input_shape):
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
835 tensor_dict = {}
836 for x, y in zip(self.inputs, inputs):
--> 837 y = self._conform_to_reference_input(y, ref_input=x)
838 x_id = str(id(x))
839 tensor_dict[x_id] = [y] * self._tensor_usage_count[x_id]
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/keras/engine/network.py in _conform_to_reference_input(self, tensor, ref_input)
959 # Dtype handling.
960 if isinstance(ref_input, (ops.Tensor, composite_tensor.CompositeTensor)):
--> 961 tensor = math_ops.cast(tensor, dtype=ref_input.dtype)
962
963 return tensor
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/util/dispatch.py in wrapper(*args, **kwargs)
178 """Call target, and fall back on dispatchers if there is a TypeError."""
179 try:
--> 180 return target(*args, **kwargs)
181 except (TypeError, ValueError):
182 # Note: convert_to_eager_tensor currently raises a ValueError, not a
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/ops/math_ops.py in cast(x, dtype, name)
785 # allows some conversions that cast() can't do, e.g. casting numbers to
786 # strings.
--> 787 x = ops.convert_to_tensor(x, name="x")
788 if x.dtype.base_dtype != base_type:
789 x = gen_math_ops.cast(x, base_type, name=name)
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/ops.py in convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, dtype_hint, ctx, accepted_result_types)
1339
1340 if ret is None:
-> 1341 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1342
1343 if ret is NotImplemented:
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_tensor_conversion_function(v, dtype, name, as_ref)
319 as_ref=False):
320 _ = as_ref
--> 321 return constant(v, dtype=dtype, name=name)
322
323
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in constant(value, dtype, shape, name)
260 """
261 return _constant_impl(value, dtype, shape, name, verify_shape=False,
--> 262 allow_broadcast=True)
263
264
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in _constant_impl(value, dtype, shape, name, verify_shape, allow_broadcast)
268 ctx = context.context()
269 if ctx.executing_eagerly():
--> 270 t = convert_to_eager_tensor(value, ctx, dtype)
271 if shape is None:
272 return t
~/projects/email_analysis/email_venv/lib/python3.6/site-packages/tensorflow/python/framework/constant_op.py in convert_to_eager_tensor(value, ctx, dtype)
94 dtype = dtypes.as_dtype(dtype).as_datatype_enum
95 ctx.ensure_initialized()
---> 96 return ops.EagerTensor(value, ctx.device_name, dtype)
97
98
ValueError: Attempt to convert a value () with an unsupported type () to a Tensor.
The point of a dataset is to provide a sequence of tensors, like here:
all_data = tf.constant([['Hello', 'World'], ['Brown Fox', 'lazy dog']])
ds = tf.data.Dataset.from_tensor_slices(all_data)
for tensor in ds:
print(tensor)
which outputs
tf.Tensor([b'Hello' b'World'], shape=(2,), dtype=string)
tf.Tensor([b'Brown Fox' b'lazy dog'], shape=(2,), dtype=string)
Instead of just printing tensor, you can compute with it:
for tensor in ds:
print(hub_layer(tensor))
which outputs 2 tensors of shape (2,20) each.
For more, see https://www.tensorflow.org/guide/data.
I am following this guide by Google (https://github.com/GoogleCloudPlatform/training-data-analyst/blob/master/courses/machine_learning/tensorflow/d_experiment.ipynb) to build a simple linear regression model.
In the notebook it has used the Experiment class and learn_runner (a class that I cannot find any documentation) to train up the model. I am now trying to use the model for prediction. I tried the following but i got an error. Would you please let me know the correct way to do it? Thanks.
Code added to the bottom:
# load the saved model
estimator = tflearn.LinearRegressor(feature_columns=feature_cols, model_dir='taxi_trained')
estimator.predict(input_fn=get_test)
Error got:
INFO:tensorflow:Using default config.
INFO:tensorflow:Using config: {'_is_chief': True, '_model_dir': None, '_save_checkpoints_secs': 600, '_cluster_spec': <tensorflow.python.training.server_lib.ClusterSpec object at 0x00000218611630F0>, '_master': '', '_task_id': 0, '_keep_checkpoint_every_n_hours': 10000, '_evaluation_master': '', '_environment': 'local', '_num_worker_replicas': 0, '_tf_random_seed': None, '_tf_config': gpu_options {
per_process_gpu_memory_fraction: 1
}
, '_save_checkpoints_steps': None, '_keep_checkpoint_max': 5, '_task_type': None, '_num_ps_replicas': 0, '_save_summary_steps': 100}
WARNING:tensorflow:From c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py:335: calling LinearRegressor.predict (from tensorflow.contrib.learn.python.learn.estimators.linear) with outputs=None is deprecated and will be removed after 2017-03-01.
Instructions for updating:
Please switch to predict_scores, or set `outputs` argument.
---------------------------------------------------------------------------
KeyError Traceback (most recent call last)
<ipython-input-5-7f1903437174> in <module>()
1 with tf.Session() as sess:
2 estimator = tflearn.LinearRegressor(feature_columns=feature_cols, model_dir='taxi_trained')
----> 3 estimator.predict(input_fn=get_test)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
333 _call_location(), decorator_utils.get_qualified_name(func),
334 func.__module__, arg_name, arg_value, date, instructions)
--> 335 return func(*args, **kwargs)
336 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
337 func.__doc__, date, instructions)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
333 _call_location(), decorator_utils.get_qualified_name(func),
334 func.__module__, arg_name, arg_value, date, instructions)
--> 335 return func(*args, **kwargs)
336 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
337 func.__doc__, date, instructions)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\linear.py in predict(self, x, input_fn, batch_size, outputs, as_iterable)
755 input_fn=input_fn,
756 batch_size=batch_size,
--> 757 as_iterable=as_iterable)
758 return super(LinearRegressor, self).predict(
759 x=x,
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
333 _call_location(), decorator_utils.get_qualified_name(func),
334 func.__module__, arg_name, arg_value, date, instructions)
--> 335 return func(*args, **kwargs)
336 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
337 func.__doc__, date, instructions)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\linear.py in predict_scores(self, x, input_fn, batch_size, as_iterable)
790 batch_size=batch_size,
791 outputs=[key],
--> 792 as_iterable=as_iterable)
793 if as_iterable:
794 return _as_iterable(preds, output=key)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\python\util\deprecation.py in new_func(*args, **kwargs)
279 _call_location(), decorator_utils.get_qualified_name(func),
280 func.__module__, arg_name, date, instructions)
--> 281 return func(*args, **kwargs)
282 new_func.__doc__ = _add_deprecated_arg_notice_to_docstring(
283 func.__doc__, date, instructions)
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in predict(self, x, input_fn, batch_size, outputs, as_iterable)
563 feed_fn=feed_fn,
564 outputs=outputs,
--> 565 as_iterable=as_iterable)
566
567 def get_variable_value(self, name):
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _infer_model(self, input_fn, feed_fn, outputs, as_iterable, iterate_batches)
855 contrib_framework.create_global_step(g)
856 features = self._get_features_from_input_fn(input_fn)
--> 857 infer_ops = self._get_predict_ops(features)
858 predictions = self._filter_predictions(infer_ops.predictions, outputs)
859 mon_sess = monitored_session.MonitoredSession(
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _get_predict_ops(self, features)
1186 labels = tensor_signature.create_placeholders_from_signatures(
1187 self._labels_info)
-> 1188 return self._call_model_fn(features, labels, model_fn_lib.ModeKeys.INFER)
1189
1190 def export_savedmodel(
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\estimator.py in _call_model_fn(self, features, labels, mode)
1101 if 'model_dir' in model_fn_args:
1102 kwargs['model_dir'] = self.model_dir
-> 1103 model_fn_results = self._model_fn(features, labels, **kwargs)
1104
1105 if isinstance(model_fn_results, model_fn_lib.ModelFnOps):
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\learn\python\learn\estimators\linear.py in _linear_model_fn(features, labels, mode, params, config)
159 num_outputs=head.logits_dimension,
160 weight_collections=[parent_scope],
--> 161 scope=scope)
162
163 def _train_op_fn(loss):
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\layers\python\layers\feature_column_ops.py in weighted_sum_from_feature_columns(columns_to_tensors, feature_columns, num_outputs, weight_collections, trainable, scope)
529 # pylint: disable=protected-access
530 for column in sorted(set(feature_columns), key=lambda x: x.key):
--> 531 transformed_tensor = transformer.transform(column)
532 try:
533 embedding_lookup_arguments = column._wide_embedding_lookup_arguments(
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\layers\python\layers\feature_column_ops.py in transform(self, feature_column)
880 return self._columns_to_tensors[feature_column]
881
--> 882 feature_column.insert_transformed_feature(self._columns_to_tensors)
883
884 if feature_column not in self._columns_to_tensors:
c:\users\tommy\appdata\local\programs\python\python35\lib\site-packages\tensorflow\contrib\layers\python\layers\feature_column.py in insert_transformed_feature(self, columns_to_tensors)
1406 """
1407 # Transform the input tensor according to the normalizer function.
-> 1408 input_tensor = self._normalized_input_tensor(columns_to_tensors[self.name])
1409 columns_to_tensors[self] = math_ops.to_float(input_tensor)
1410
KeyError: 'dropofflat'
I am using TensorFlow 1.1 with Python 3.5 on Windows 10. GPU enabled.