tensorflow - LSTM - RuntimeError：构建模型的尝试失败次数过多
问题描述
我正在尝试使用 keras 调谐器来调整 LSTM 神经网络，以使用 kaggle 数据集来检测文章是否是假新闻。但是，我不断收到此错误：RuntimeError：构建模型的尝试失败次数过多我也尝试使用 RandomSearch 而不是 BayesianOptimization，但仍然遇到相同类型的错误。
这是代码：
'''
def build_model(hp):
voc_size=5000
embedding_vector_features=40
model = Sequential([
Embedding(
voc_size,
embedding_vector_features,
input_length = sent_length
),
AlphaDropout(
rate = hp.Choice(
'dropout_1_rate',
values=[0.3, 0.5],
default=0.3
)
),
LSTM(
units = hp.Int(
'LSTM_1_units',
min_value=100,
max_value=300,
step=32,
default=128
),
activation = hp.Choice(
'LSTM_1_activation',
values=['relu', 'selu']
),
kernel_initializer='lecun_normal'
),
AlphaDropout(
rate = hp.Choice(
'dropout_2_rate',
values=[0.3, 0.5],
default=0.3
)
),
LSTM(
units = hp.Int(
'LSTM_2_units',
min_value=100,
max_value=300,
step=32,
default=128
),
activation = hp.Choice(
'LSTM_2_activation',
values=['relu', 'selu']
),
kernel_initializer='lecun_normal'
),
AlphaDropout(
rate = hp.Choice(
'dropout_3_rate',
values=[0.3, 0.5],
default=0.3
)
),
Dense(
units = 1,
activation = 'sigmoid',
kernel_initializer='lecun_normal'
)
])
model.compile(
optimizer = keras.optimizers.Nadam(
hp.Choice(
'learning_rate',
values=[1e-2, 1e-3]
)
),
loss = 'binary_crooentropy',
metric = ['accuracy']
)
return model
tuner_search = BayesianOptimization(build_model,
objective='val_accuracy',
max_trials=3,
seed=42,
directory='output',
project_name='Fake News Classifier'
)
'''
当我尝试运行此代码时，出现以下错误：
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Invalid model 0/5
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
Invalid model 1/5
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
Invalid model 2/5
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
Invalid model 3/5
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
Invalid model 4/5
WARNING:tensorflow:Layer lstm will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
WARNING:tensorflow:Layer lstm_1 will not use cuDNN kernel since it doesn't meet the cuDNN kernel criteria. It will use generic GPU kernel as fallback when running on GPU
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
Invalid model 5/5
Traceback (most recent call last):
File "/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py", line 104, in build
model = self.hypermodel.build(hp)
File "<ipython-input-18-fe84fe0afbca>", line 62, in build_model
kernel_initializer='lecun_normal'
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 144, in __init__
self.add(layer)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/training/tracking/base.py", line 517, in _method_wrapper
result = method(self, *args, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/sequential.py", line 223, in add
output_tensor = layer(self.outputs[0])
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/layers/recurrent.py", line 660, in __call__
return super(RNN, self).__call__(inputs, **kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 952, in __call__
input_list)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 1091, in _functional_construction_call
inputs, input_masks, args, kwargs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 822, in _keras_tensor_symbolic_call
return self._infer_output_signature(inputs, args, kwargs, input_masks)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 862, in _infer_output_signature
self._maybe_build(inputs)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/base_layer.py", line 2685, in _maybe_build
self.input_spec, inputs, self.name)
File "/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py", line 223, in assert_input_compatibility
str(tuple(shape)))
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py in build(self, hp)
103 with maybe_distribute(self.distribution_strategy):
--> 104 model = self.hypermodel.build(hp)
105 except:
19 frames
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (None, 128)
During handling of the above exception, another exception occurred:
RuntimeError Traceback (most recent call last)
/usr/local/lib/python3.7/dist-packages/kerastuner/engine/hypermodel.py in build(self, hp)
111 if i == self._max_fail_streak:
112 raise RuntimeError(
--> 113 'Too many failed attempts to build model.')
114 continue
115
RuntimeError: Too many failed attempts to build model.
我该如何解决这个问题？
解决方案
实际错误是ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2。收到的完整形状：（无，128）
LSTM 层需要输入形状输入：具有形状 [batch, timesteps, feature] 的 3D 张量
我可以重现你的问题
import tensorflow as tf
inputs = tf.random.normal([32, 8])
lstm = tf.keras.layers.LSTM(4)
output = lstm(inputs)
print(output.shape)
输出
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-2-160c5e8d5d9a> in <module>()
2 inputs = tf.random.normal([32, 8])
3 lstm = tf.keras.layers.LSTM(4)
----> 4 output = lstm(inputs)
5 print(output.shape)
2 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/keras/engine/input_spec.py in assert_input_compatibility(input_spec, inputs, layer_name)
217 'expected ndim=' + str(spec.ndim) + ', found ndim=' +
218 str(ndim) + '. Full shape received: ' +
--> 219 str(tuple(shape)))
220 if spec.max_ndim is not None:
221 ndim = x.shape.rank
ValueError: Input 0 of layer lstm_1 is incompatible with the layer: expected ndim=3, found ndim=2. Full shape received: (32, 8)
Working code snippet
import tensorflow as tf
inputs = tf.random.normal([32, 10, 8])
lstm = tf.keras.layers.LSTM(4)
output = lstm(inputs)
print(output.shape)
输出
(32, 4)
推荐阅读
- c - 错误：使用“designated_init”属性声明的“struct”中字段的位置初始化 [-Werror=designated-init]
- java - 根据 ADF 中的自定义 Pojo 列表在 af:table 上应用过滤器
- c# - 如何使用推送通知将来自 webapi 操作方法的返回消息显示到我的 Web 浏览器
- css - 使用断点创建新的引导类
- laravel-5.7 - DB::select() - 如何获取数组数组而不是集合数组
- ios - UISearchBarController 卡在 NavigationBar Swift 下
- string - 如何在没有大写和小写python的情况下检查路径是否存在
- python - 一个热编码单分类数值列
- python - 无需平铺的水平连接的有效方式
- shell - Ssh to multiple hosts and run command based on hostnames