ValueError：“顺序”的输入0;与该层不兼容：预期形状=（无，81），发现形状=（无，77）

Question

我正在尝试培训神经网络，但我会收到以下错误：

 ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 81), found shape=(None, 77)

我试图找到解决方案，但无法做到。有人可以帮我吗？

这是与建议的代码相同的代码

from sklearn.preprocessing import StandardScaler
from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.wrappers.scikit_learn import KerasRegressor
from tensorflow.keras.callbacks import EarlyStopping
# Scaling the data
ss = StandardScaler()
X_train_sc = ss.fit_transform(X_train)
X_test_sc = ss.transform(X_test)

# Creating our model's structure
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(81,)))
model.add(Dropout(0.18))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.15))
model.add(Dense(1, activation='sigmoid'))
es = EarlyStopping(monitor='val_loss', patience=5) 

# Compiling the model
model.compile(loss='bce',
              optimizer='adam',
              metrics=['binary_accuracy'])

# Fitting the model
history = model.fit(X_train_sc,
                    y_train, 
                    batch_size = 256,
                    validation_data =(X_test_sc, y_test),
                    epochs = 500,
                    verbose = 0,
                    callbacks=[es])

，我已将代码编辑为：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.wrappers.scikit_learn import KerasRegressor
from tensorflow.keras.callbacks import EarlyStopping
import tensorflow as tf

samples = 500
X_train_sc = tf.random.normal((samples, 81))
y_train = tf.random.uniform((samples, ), maxval=2, dtype=tf.int32)

# Creating our model's structure
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(81,)))
model.add(Dropout(0.18))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.15))
model.add(Dense(1, activation='sigmoid'))

es = EarlyStopping(monitor='val_loss', patience=5) 

# Compiling the model
model.compile(loss='bce',
              optimizer='adam',
              metrics=['binary_accuracy'])

# Fitting the model
history = model.fit(X_train_sc,
                    y_train, 
                    batch_size = 32,
                    epochs = 2,
                    verbose = 0)

但是，当我尝试找到准确性时，我会得到与下面相同的错误：

# Scoring
train_score = model.evaluate(X_train_sc,
                       y_train,
                       verbose=1)
test_score = model.evaluate(X_test_sc,
                       y_test,
                       verbose=1)
labels = model.metrics_names

print('')
print(f'Training Accuracy: {train_score[1]}')
print(f'Testing Accuracy: {test_score[1]}')


16/16 [==============================] - 0s 2ms/step - loss: 0.6613 - binary_accuracy: 0.6040
---------------------------------------------------------------------------
ValueError                                Traceback (most recent call last)
~\AppData\Local\Temp/ipykernel_7572/1082894889.py in <module>
      3                        y_train,
      4                        verbose=1)
----> 5 test_score = model.evaluate(X_test_sc,
      6                        y_test,
      7                        verbose=1)

~\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py in error_handler(*args, **kwargs)
     65     except Exception as e:  # pylint: disable=broad-except
     66       filtered_tb = _process_traceback_frames(e.__traceback__)
---> 67       raise e.with_traceback(filtered_tb) from None
     68     finally:
     69       del filtered_tb

~\Anaconda3\lib\site-packages\tensorflow\python\framework\func_graph.py in autograph_handler(*args, **kwargs)
   1145           except Exception as e:  # pylint:disable=broad-except
   1146             if hasattr(e, "ag_error_metadata"):
-> 1147               raise e.ag_error_metadata.to_exception(e)
   1148             else:
   1149               raise

ValueError: in user code:

    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\engine\training.py", line 1525, in test_function  *
        return step_function(self, iterator)
    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\engine\training.py", line 1514, in step_function  **
        outputs = model.distribute_strategy.run(run_step, args=(data,))
    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\engine\training.py", line 1507, in run_step  **
        outputs = model.test_step(data)
    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\engine\training.py", line 1471, in test_step
        y_pred = self(x, training=False)
    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\utils\traceback_utils.py", line 67, in error_handler
        raise e.with_traceback(filtered_tb) from None
    File "C:\Users\sadik\Anaconda3\lib\site-packages\keras\engine\input_spec.py", line 264, in assert_input_compatibility
        raise ValueError(f'Input {input_index} of layer "{layer_name}" is '

    ValueError: Input 0 of layer "sequential_4" is incompatible with the layer: expected shape=(None, 81), found shape=(None, 77)

Answer 1

问题在于您的输入数据的形状与第一层中定义的形状不同。确保数据的功能维度对应于模型第一层中的输入形状。这是一个示例：

from tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Dense, Dropout
from tensorflow.keras.wrappers.scikit_learn import KerasRegressor
from tensorflow.keras.callbacks import EarlyStopping
import tensorflow as tf

samples = 500

# Create random dummy data
X_train_sc = tf.random.normal((samples, 81))
y_train = tf.random.uniform((samples, ), maxval=2, dtype=tf.int32)

X_test_sc = tf.random.normal((samples, 81))
y_test = tf.random.uniform((samples, ), maxval=2, dtype=tf.int32)

# Creating our model's structure
model = Sequential()
model.add(Dense(64, activation='relu', input_shape=(81,)))
model.add(Dropout(0.18))
model.add(Dense(32, activation='relu'))
model.add(Dropout(0.15))
model.add(Dense(1, activation='sigmoid'))

# Compiling the model
model.compile(loss='bce',
              optimizer='adam',
              metrics=['binary_accuracy'])

# Fitting the model
history = model.fit(X_train_sc,
                    y_train, 
                    batch_size = 32,
                    epochs = 2,
                    verbose = 0)

因此，如果您的功能维度为77，则将input_shape =（81，）更改为input_shape =（77，）。