我对机器学习非常陌生,在尝试创建简单的LSTM模型时遇到了一个错误,而且我绝对不知道如何调试它。我正在使用Keras版本2.2.2。 我的代码大致如下所示:
model = Sequential()
model.add(Embedding(400001, emb_dim, trainable=False, input_length = 56, weights = [emb_matrix]))
model.add(LSTM(128, return_sequences=False))
model.add(Dense(5, activation='softmax'))
model.summary()
model.fit(train_in, train_out, epochs = 50, batch_size = 32, shuffle=True)
我的输入最初是我打算进行情感分析的句子列表,然后我使用50暗淡的Glove向量将句子转换为形状(样本大小为56、50)的向量,因为我的单词数最大每句话是56个(偏高吗?)。
我的模型摘要:
Layer (type) Output Shape Param #
=================================================================
embedding_5 (Embedding) (None, 56, 50) 20000050
_________________________________________________________________
lstm_6 (LSTM) (None, 128) 91648
_________________________________________________________________
dense_4 (Dense) (None, 5) 645
=================================================================
Total params: 20,092,343
Trainable params: 92,293
Non-trainable params: 20,000,050
我的输入:
print(train_in.shape, train_out.shape)
>(156060, 56) (156060, 5)
emb_matrix.shape
>(400001, 50)
print(train_in.dtype, train_out.dtype, emb_matrix.dtype)
>float32 float32 float32
最后是我的错误消息:
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gradients_impl.py in _MaybeCompile(scope, op, func, grad_fn)
369 try:
--> 370 xla_compile = op.get_attr("_XlaCompile")
371 xla_separate_compiled_gradients = op.get_attr(
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in get_attr(self, name)
2172 raise ValueError(
-> 2173 "No attr named '" + name + "' in " + str(self._node_def))
2174 x = self._node_def.attr[name]
ValueError: No attr named '_XlaCompile' in name: "lstm_6/while/TensorArrayWrite/TensorArrayWriteV3"
op: "TensorArrayWriteV3"
input: "lstm_6/while/TensorArrayWrite/TensorArrayWriteV3/Enter"
input: "lstm_6/while/Identity_1"
input: "lstm_6/while/mul_5"
input: "lstm_6/while/Identity_2"
attr {
key: "T"
value {
type: DT_FLOAT
}
}
attr {
key: "_class"
value {
list {
s: "loc:@lstm_6/while/mul_5"
}
}
}
During handling of the above exception, another exception occurred:
ValueError Traceback (most recent call last)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
509 as_ref=input_arg.is_ref,
--> 510 preferred_dtype=default_dtype)
511 except TypeError as err:
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in internal_convert_to_tensor(value, dtype, name, as_ref, preferred_dtype, ctx)
1021 if ret is None:
-> 1022 ret = conversion_func(value, dtype=dtype, name=name, as_ref=as_ref)
1023
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in _TensorTensorConversionFunction(t, dtype, name, as_ref)
865 "Tensor conversion requested dtype %s for Tensor with dtype %s: %r" %
--> 866 (dtype.name, t.dtype.name, str(t)))
867 return t
ValueError: Tensor conversion requested dtype int32 for Tensor with dtype int64: 'Tensor("lstm_6/while/maximum_iterations:0", shape=(), dtype=int64)'
During handling of the above exception, another exception occurred:
TypeError Traceback (most recent call last)
<ipython-input-54-936a1189c2d5> in <module>()
----> 1 model.fit(train_in, train_out, epochs = 50, batch_size = 32, shuffle=True)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\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, **kwargs)
1006 else:
1007 ins = x + y + sample_weights
-> 1008 self._make_train_function()
1009 f = self.train_function
1010
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\keras\engine\training.py in _make_train_function(self)
496 training_updates = self.optimizer.get_updates(
497 params=self._collected_trainable_weights,
--> 498 loss=self.total_loss)
499 updates = (self.updates +
500 training_updates +
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\keras\legacy\interfaces.py in wrapper(*args, **kwargs)
89 warnings.warn('Update your `' + object_name +
90 '` call to the Keras 2 API: ' + signature, stacklevel=2)
---> 91 return func(*args, **kwargs)
92 wrapper._original_function = func
93 return wrapper
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\keras\optimizers.py in get_updates(self, loss, params)
633 @interfaces.legacy_get_updates_support
634 def get_updates(self, loss, params):
--> 635 grads = self.get_gradients(loss, params)
636 self.updates = [K.update_add(self.iterations, 1)]
637
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\keras\optimizers.py in get_gradients(self, loss, params)
87
88 def get_gradients(self, loss, params):
---> 89 grads = K.gradients(loss, params)
90 if None in grads:
91 raise ValueError('An operation has `None` for gradient. '
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\keras\backend\tensorflow_backend.py in gradients(loss, variables)
2706 A gradients tensor.
2707 """
-> 2708 return tf.gradients(loss, variables, colocate_gradients_with_ops=True)
2709
2710
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gradients_impl.py in gradients(ys, xs, grad_ys, name, colocate_gradients_with_ops, gate_gradients, aggregation_method, stop_gradients)
607 # functions.
608 in_grads = _MaybeCompile(
--> 609 grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
610 else:
611 # For function call ops, we add a 'SymbolicGradient'
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gradients_impl.py in _MaybeCompile(scope, op, func, grad_fn)
373 xla_scope = op.get_attr("_XlaScope").decode()
374 except ValueError:
--> 375 return grad_fn() # Exit early
376
377 if not xla_compile:
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gradients_impl.py in <lambda>()
607 # functions.
608 in_grads = _MaybeCompile(
--> 609 grad_scope, op, func_call, lambda: grad_fn(op, *out_grads))
610 else:
611 # For function call ops, we add a 'SymbolicGradient'
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\tensor_array_grad.py in _TensorArrayWriteGrad(op, flow)
129 colocate_with_first_write_call=False)
130 .grad(source=grad_source, flow=flow))
--> 131 grad = g.read(index)
132 return [None, None, grad, flow]
133
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\tensor_array_ops.py in read(self, index, name)
857 The tensor at index `index`.
858 """
--> 859 return self._implementation.read(index, name=name)
860
861 @tf_should_use.should_use_result
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\tensor_array_ops.py in read(self, index, name)
257 flow_in=self._flow,
258 dtype=self._dtype,
--> 259 name=name)
260 if self._element_shape:
261 value.set_shape(self._element_shape[0].dims)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gen_data_flow_ops.py in _tensor_array_read_v3(handle, index, flow_in, dtype, name)
4993 _, _, _op = _op_def_lib._apply_op_helper(
4994 "TensorArrayReadV3", handle=handle, index=index, flow_in=flow_in,
-> 4995 dtype=dtype, name=name)
4996 _result = _op.outputs[:]
4997 _inputs_flat = _op.inputs
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
785 op = g.create_op(op_type_name, inputs, output_types, name=scope,
786 input_types=input_types, attrs=attr_protos,
--> 787 op_def=op_def)
788 return output_structure, op_def.is_stateful, op
789
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in create_op(self, op_type, inputs, dtypes, input_types, name, attrs, op_def, compute_shapes, compute_device)
3158 input_types=input_types,
3159 original_op=self._default_original_op,
-> 3160 op_def=op_def)
3161 self._create_op_helper(ret, compute_shapes=compute_shapes,
3162 compute_device=compute_device)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\ops.py in __init__(self, node_def, g, inputs, output_types, control_inputs, input_types, original_op, op_def)
1672 control_flow_util.CheckInputFromValidContext(self, input_tensor.op)
1673 if self._control_flow_context is not None:
-> 1674 self._control_flow_context.AddOp(self)
1675 self._recompute_node_def()
1676
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in AddOp(self, op)
2249 op_input_ctxt._AddOpInternal(op)
2250 return
-> 2251 self._AddOpInternal(op)
2252
2253 def _AddOpInternal(self, op):
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in _AddOpInternal(self, op)
2272 for index in range(len(op.inputs)):
2273 x = op.inputs[index]
-> 2274 real_x = self.AddValue(x)
2275 if real_x != x:
2276 op._update_input(index, real_x)
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in AddValue(self, val)
2205 forward_ctxt = forward_ctxt.GetWhileContext()
2206 if forward_ctxt == grad_ctxt.grad_state.forward_context:
-> 2207 real_val = grad_ctxt.grad_state.GetRealValue(val)
2208 self._external_values[val.name] = real_val
2209 return real_val
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in GetRealValue(self, value)
1048 # Record the history of this value in forward_ctxt.
1049 self._grad_context.Exit()
-> 1050 history_value = cur_grad_state.AddForwardAccumulator(cur_value)
1051 self._grad_context.Enter()
1052 break
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\control_flow_ops.py in AddForwardAccumulator(self, value, dead_branch)
906 max_size=maximum_iterations,
907 elem_type=value.dtype.base_dtype,
--> 908 name="f_acc")
909 # pylint: enable=protected-access
910 if curr_ctxt: curr_ctxt.Exit()
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\ops\gen_data_flow_ops.py in _stack_v2(max_size, elem_type, stack_name, name)
4014 _, _, _op = _op_def_lib._apply_op_helper(
4015 "StackV2", max_size=max_size, elem_type=elem_type,
-> 4016 stack_name=stack_name, name=name)
4017 _result = _op.outputs[:]
4018 _inputs_flat = _op.inputs
c:\users\admin\appdata\local\programs\python\python36\lib\site-packages\tensorflow\python\framework\op_def_library.py in _apply_op_helper(self, op_type_name, name, **keywords)
531 if input_arg.type != types_pb2.DT_INVALID:
532 raise TypeError("%s expected type of %s." %
--> 533 (prefix, dtypes.as_dtype(input_arg.type).name))
534 else:
535 # Update the maps with the default, if needed.
TypeError: Input 'max_size' of 'StackV2' Op has type int64 that does not match expected type of int32.
答案 0 :(得分:1)
我最初使用的是TF的1.5.0版本,已升级到v1.8.0,并且一切正常。问题已解决。