python - 错误 : Value passed to parameter 'input' has DataType int64 not in list of allowed values: float16, bfloat16、float32、float64？

Question

我有这段代码，但应用预测时出现错误？

import pandas as pd
import numpy as np
import sklearn

import keras
from tensorflow.keras.models import Sequential
from tensorflow.keras.utils import to_categorical
from tensorflow.keras.layers import Dense, Flatten
from tensorflow.keras.layers import Conv2D,Conv1D, MaxPooling2D,MaxPooling1D
from tensorflow.keras.layers import Activation
from tensorflow.keras.layers import Dropout,BatchNormalization

dataset=pd.read_csv("C:/Users/User/Desktop/data.csv",encoding='cp1252')
dataset.shape
#output:(53480, 37)
array = dataset.values
X = array[:,0:36]
Y = array[:,36]
kf = KFold(n_splits=10)
kf.get_n_splits(X)
ACC_array = np.array([])
sensitivity_array = np.array([])
specificity_array = np.array([])
for trainindex, testindex in kf.split(X):
Xtrain, Xtest = X[trainindex], X[testindex]
Ytrain, Ytest = Y[trainindex], Y[testindex]
Xtrain = np.expand_dims(np.random.normal(size=(53480, 36)),axis=-1)

Ytrain = np.random.choice([0,1], size=(53480,10))
n_timesteps, n_features, n_outputs =Xtrain.shape[0], Xtrain.shape[1], Ytrain.shape[1]

model = Sequential()
model.add(Conv1D(filters=64, kernel_size=1, 
activation='relu',input_shape=(n_features,1)))

model.add(Conv1D(filters=64, kernel_size=1, activation='relu'))
model.add(Dropout(0.5))
model.add(MaxPooling1D(pool_size=2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(n_outputs, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
# fit network
model.fit(Xtrain, Ytrain, epochs=10, batch_size=128, verbose=1)
model.summary()


#output:
Model: "sequential"
.
.

Predictions = model.predict(Xtest,batch_size =1024)
rounded = [round(x[0]) for x in Predictions]
Y_predection = pd.DataFrame(rounded)
Y_predection = Y_predection.iloc[:, 0]

错误消息:

TypeError                                 Traceback (most recent call last)
<ipython-input-16-67624699b454> in <module>
----> 1 Predictions = model.predict(Xtest,batch_size =1024)
  2 rounded = [round(x[0]) for x in Predictions]
  3 Y_predection = pd.DataFrame(rounded)
  4 Y_predection = Y_predection.iloc[:, 0]
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training.py in predict(self, x, batch_size, verbose, steps, callbacks, max_queue_size, workers, use_multiprocessing)
907         max_queue_size=max_queue_size,
908         workers=workers,
--> 909         use_multiprocessing=use_multiprocessing)
910 
911   def reset_metrics(self):
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in predict(self, model, x, batch_size, verbose, steps, callbacks, **kwargs)
460     return self._model_iteration(
461         model, ModeKeys.PREDICT, x=x, batch_size=batch_size, 
verbose=verbose,
--> 462         steps=steps, callbacks=callbacks, **kwargs)
463 
464 
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in _model_iteration(self, model, mode, x, y, batch_size, verbose, sample_weight, steps, callbacks, **kwargs)
442               mode=mode,
443               training_context=training_context,
--> 444               total_epochs=1)
445           cbks.make_logs(model, epoch_logs, result, mode)
446 
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py in run_one_epoch(model, iterator, execution_function, dataset_size, batch_size, strategy, steps_per_epoch, num_samples, mode, training_context, total_epochs)
121         step=step, mode=mode, size=current_batch_size) as batch_logs:
122       try:
--> 123         batch_outs = execution_function(iterator)
124       except (StopIteration, errors.OutOfRangeError):
125         # TODO(kaftan): File bug about tf function and 
errors.OutOfRangeError?
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in execution_function(input_fn)
 84     # `numpy` translates Tensors to values in Eager mode.
 85     return nest.map_structure(_non_none_constant_value,
---> 86                               distributed_function(input_fn))
 87 
 88   return execution_function
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\eager\def_function.py in __call__(self, *args, **kwds)
455 
456     tracing_count = self._get_tracing_count()
--> 457     result = self._call(*args, **kwds)
458     if tracing_count == self._get_tracing_count():
459       self._call_counter.called_without_tracing()
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\eager\def_function.py in _call(self, *args, **kwds)
501       # This is the first call of __call__, so we have to initialize.
502       initializer_map = object_identity.ObjectIdentityDictionary()
--> 503       self._initialize(args, kwds, add_initializers_to=initializer_map)
504     finally:
505       # At this point we know that the initialization is complete (or 
less

~\.conda\envs\tensorflow\lib\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):

~\.conda\envs\tensorflow\lib\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 
~\.conda\envs\tensorflow\lib\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
~\.conda\envs\tensorflow\lib\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

~\.conda\envs\tensorflow\lib\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,

~\.conda\envs\tensorflow\lib\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 

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in distributed_function(input_iterator)
 71     strategy = distribution_strategy_context.get_strategy()
 72     outputs = strategy.experimental_run_v2(
---> 73         per_replica_function, args=(model, x, y, sample_weights))
 74     # Out of PerReplica outputs reduce or pick values to return.
 75     all_outputs = dist_utils.unwrap_output_dict(

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in experimental_run_v2(self, fn, args, kwargs)
758       fn = autograph.tf_convert(fn, ag_ctx.control_status_ctx(),
759                                 convert_by_default=False)
--> 760       return self._extended.call_for_each_replica(fn, args=args, 
kwargs=kwargs)
761 
762   def reduce(self, reduce_op, value, axis):
~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\distribute\distribute_lib.py in 
call_for_each_replica(self, fn, args, kwargs)
   1785       kwargs = {}
   1786     with self._container_strategy().scope():
 -> 1787       return self._call_for_each_replica(fn, args, kwargs)
   1788 
   1789   def _call_for_each_replica(self, fn, args, kwargs):

    ~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\distribute\distribute_lib.py in 
_call_for_each_replica(self, fn, args, kwargs)
2130         self._container_strategy(),
2131         replica_id_in_sync_group=constant_op.constant(0, 
dtypes.int32)):
-> 2132       return fn(*args, **kwargs)
   2133 
   2134   def _reduce_to(self, reduce_op, value, destinations):

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\autograph\impl\api.py in wrapper(*args, **kwargs)
290   def wrapper(*args, **kwargs):
291     with ag_ctx.ControlStatusCtx(status=ag_ctx.Status.DISABLED):
--> 292       return func(*args, **kwargs)
293 
294   if inspect.isfunction(func) or inspect.ismethod(func):

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in _predict_on_batch(***failed resolving arguments***)
160     def _predict_on_batch(model, x, y=None, sample_weights=None):
161       del y, sample_weights
--> 162       return predict_on_batch(model, x)
163 
164     func = _predict_on_batch

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\training_v2_utils.py in predict_on_batch(model, x)
368 
369   with backend.eager_learning_phase_scope(0):
--> 370     return model(inputs)  # pylint: disable=not-callable

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
845                     outputs = base_layer_utils.mark_as_return(outputs, acd)
846                 else:
--> 847                   outputs = call_fn(cast_inputs, *args, **kwargs)
848 
849             except errors.OperatorNotAllowedInGraphError as e:

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\sequential.py in call(self, inputs, training, mask)
254       if not self.built:
255         self._init_graph_network(self.inputs, self.outputs, name=self.name)
--> 256       return super(Sequential, self).call(inputs, training=training, mask=mask)
257 
258     outputs = inputs  # handle the corner case where self.layers is empty

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\network.py in call(self, inputs, training, mask)
706     return self._run_internal_graph(
707         inputs, training=training, mask=mask,
--> 708         convert_kwargs_to_constants=base_layer_utils.call_context().saving)
709 
710   def compute_output_shape(self, input_shape):

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\network.py in _run_internal_graph(self, inputs, training, mask, convert_kwargs_to_constants)
858 
859           # Compute outputs.
--> 860           output_tensors = layer(computed_tensors, **kwargs)
861 
862           # Update tensor_dict.

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py in __call__(self, inputs, *args, **kwargs)
845                     outputs = base_layer_utils.mark_as_return(outputs, acd)
846                 else:
--> 847                   outputs = call_fn(cast_inputs, *args, **kwargs)
848 
849             except errors.OperatorNotAllowedInGraphError as e:

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\layers\convolutional.py in call(self, inputs)
385     if self.padding == 'causal':
386       inputs = array_ops.pad(inputs, self._compute_causal_padding())
--> 387     return super(Conv1D, self).call(inputs)
388 
389 

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\keras\layers\convolutional.py in call(self, inputs)
195 
196   def call(self, inputs):
--> 197     outputs = self._convolution_op(inputs, self.kernel)
198 
199     if self.use_bias:
~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\ops\nn_ops.py in __call__(self, inp, 
filter)
1132           call_from_convolution=False)
1133     else:
-> 1134       return self.conv_op(inp, filter)
1135     # copybara:strip_end
1136     # copybara:insert return self.conv_op(inp, filter)
~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\ops\nn_ops.py in __call__(self, inp, filter)
637 
638   def __call__(self, inp, filter):  # pylint: disable=redefined- 
builtin
--> 639     return self.call(inp, filter)
640 
641  

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\ops\nn_ops.py in __call__(self, inp, filter)
236         padding=self.padding,
237         data_format=self.data_format,
--> 238         name=self.name)
239 
240 

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\ops\nn_ops.py in _conv1d(self, input, filter, strides, padding, data_format, name)
225         padding=padding,
226         data_format=data_format,
--> 227         name=name)
228 
229   # pylint: enable=redefined-builtin

~\.conda\envs\tensorflow\lib\site-packages\tensorflow_core\python\util\deprecation.py in new_func(*args, **kwargs)
572                   func.__module__, arg_name, arg_value, 'in a future version'
573                   if date is None else ('after %s' % date), instructions)
--> 574       return func(*args, **kwargs)
575 
576     doc = _add_deprecated_arg_value_notice_to_docstring(
~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\util\deprecation.py in new_func(*args, 
**kwargs)
572                   func.__module__, arg_name, arg_value, 'in a future 
version'
573                   if date is None else ('after %s' % date), 
instructions)
--> 574       return func(*args, **kwargs)
575 
576     doc = _add_deprecated_arg_value_notice_to_docstring(
~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\ops\nn_ops.py in conv1d(value, filters, 
stride, padding, use_cudnn_on_gpu, data_format, name, input, dilations)
1679         data_format=data_format,
1680         dilations=dilations,
-> 1681         name=name)
1682     return array_ops.squeeze(result, [spatial_start_dim])
1683 

~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\ops\gen_nn_ops.py in conv2d(input, filter, 
strides, padding, use_cudnn_on_gpu, explicit_paddings, data_format, 
dilations, name)
1068                   padding=padding, use_cudnn_on_gpu=use_cudnn_on_gpu,
1069                   explicit_paddings=explicit_paddings,
-> 1070                   data_format=data_format, dilations=dilations, 
name=name)
1071   _result = _op.outputs[:]
1072   _inputs_flat = _op.inputs

~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\framework\op_def_library.py in 
_apply_op_helper(self, op_type_name, name, **keywords)
629               _SatisfiesTypeConstraint(base_type,
630                                        _Attr(op_def, 
input_arg.type_attr),
--> 631                                        param_name=input_name)
632             attrs[input_arg.type_attr] = attr_value
633             inferred_from[input_arg.type_attr] = input_name

~\.conda\envs\tensorflow\lib\site- 
packages\tensorflow_core\python\framework\op_def_library.py in 
_SatisfiesTypeConstraint(dtype, attr_def, param_name)
 58           "allowed values: %s" %
 59           (param_name, dtypes.as_dtype(dtype).name,
---> 60            ", ".join(dtypes.as_dtype(x).name for x in allowed_list)))
 61 
 62 

TypeError: Value passed to parameter 'input' has DataType int64 not in list of allowed values: float16, bfloat16, float32, float64   

我想将一维CNN应用于表格数据(数值)，如何通过交叉验证来评估模型来计算(准确度、灵敏度、特异性) ，如何修复上面的错误？ 或如何通过使用 70% 进行训练和 30% 进行测试来计算混淆指标？

Answer 1

错误发生在以下行:

Predictions = model.predict(Xtest,batch_size =1024)

因为在你定义之后:

Xtrain, Xtest = X[trainindex], X[testindex]

你没有对 Xtest 进行维度扩展就像Xtrain的随机重新定义(我猜这只是为了一些测试目的):

Xtrain = np.expand_dims(np.random.normal(size=(213412, 36)),axis=-1)

所以Xtrain具有正确的 3D 形状 (?, 36, 1)，与您使用 input_shape=(n_features,1) 定义的输入大小完全相同在您的代码中:

model.add(Conv1D(filters=64, kernel_size=1, 
activation='relu',input_shape=(n_features,1)))

同时Xtest仍然是二维数据，即形状为(?, 36)或完全(5348, 36)。这就是您的模型提示输入形状的原因。

因此做 np.expand_dims()上Xtest也有:

Xtest = np.expand_dims(Xtest, axis=-1)

更新:

正如我在您后来的评论中看到的，您不明白为什么“准确率逐渐下降，并且损失函数不断增加，差异显着”。这就是为什么你重新定义了你的 X_train如上所述:np.random.normal(size=(53480, 36))行中:

Xtrain = np.expand_dims(np.random.normal(size=(53480, 36)),axis=-1)

所以你的模型试图适应随机数据。