我正试图在MNIST数据集上创建一个带有Tensorflow和Keras的Vgg-16模型。我已经成功地建立了模型，但在训练MNIST数据集时出现了错误。我已经检查了这个错误的不同解决方案，但它似乎不起作用，因为我是这个领域的新手
错误生成
ValueError: in user code:
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:805 train_function *
return step_function(self, iterator)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:795 step_function **
outputs = model.distribute_strategy.run(run_step, args=(data,))
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:1259 run
return self._extended.call_for_each_replica(fn, args=args, kwargs=kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:2730 call_for_each_replica
return self._call_for_each_replica(fn, args, kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/distribute/distribute_lib.py:3417 _call_for_each_replica
return fn(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:788 run_step **
outputs = model.train_step(data)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/training.py:756 train_step
y, y_pred, sample_weight, regularization_losses=self.losses)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/engine/compile_utils.py:203 __call__
loss_value = loss_obj(y_t, y_p, sample_weight=sw)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:152 __call__
losses = call_fn(y_true, y_pred)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:256 call **
return ag_fn(y_true, y_pred, **self._fn_kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/losses.py:1537 categorical_crossentropy
return K.categorical_crossentropy(y_true, y_pred, from_logits=from_logits)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/util/dispatch.py:201 wrapper
return target(*args, **kwargs)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/backend.py:4833 categorical_crossentropy
target.shape.assert_is_compatible_with(output.shape)
/usr/local/lib/python3.6/dist-packages/tensorflow/python/framework/tensor_shape.py:1134 assert_is_compatible_with
raise ValueError("Shapes %s and %s are incompatible" % (self, other))
ValueError: Shapes (None, 10, 10) and (None, 2) are incompatible
模型构建
model = Sequential()
model.add(Conv2D(input_shape=(input_shape),filters=64,kernel_size=(3,3),padding="same", activation="relu"))
model.add(Conv2D(filters=64,kernel_size=(3,3),padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=128, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=128, kernel_size=(3,3), padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=256, kernel_size=(3,3), padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2)))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(Conv2D(filters=512, kernel_size=(3,3), padding="same", activation="relu"))
model.add(MaxPool2D(pool_size=(2,2),strides=(2,2), padding='same'))
model.add(Flatten())
model.add(Dense(units=4096,activation="relu")); model.add(Dropout(0.5))
model.add(Dense(units=4096,activation="relu")); model.add(Dropout(0.5))
model.add(Dense(units=2, activation="softmax"))
# Compile the Model
model.compile(optimizer='adam', loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])
MNISt数据集
mnist = tf.keras.datasets.mnist
(X_train, Y_train), (X_test, Y_test) = mnist.load_data()
#processing
rows, cols = 28, 28
X_train = X_train.reshape(X_train.shape[0], rows, cols, 1)
X_test = X_test.reshape(X_test.shape[0], rows, cols, 1)
input_shape = (rows, cols, 1)
Y_train = tf.keras.utils.to_categorical(Y_train, 10)
Y_test = tf.keras.utils.to_categorical(Y_test, 10)
# Normalize
X_train = X_train.astype('float32')
X_test = X_test.astype('float32')
X_train = X_train / 255.0
X_test = X_test / 255.0
训练
history = model.fit(X_train, Y_train,
batch_size= 128,
epochs= 5,
verbose= 1)
最后一层应该输出10个值，因为MNIST包含10个类。
model.add(Dense(units=10, activation="softmax"))
我复制了你的代码并运行了它。一旦你将顶层更改为有10个神经元，它就会运行而不会出现任何错误。但是你的模特训练不好。我在下面提供了一个简单的模型，它确实训练得很好。我还将您的测试集作为验证集。代码低于
model = tf.keras.Sequential([
Conv2D(16, 3, padding='same', activation='relu', input_shape=input_shape ),
MaxPooling2D(strides=1),
Conv2D(32, 3, padding='same', activation='relu'),
MaxPooling2D(strides=1),
Conv2D(64, 3, padding='same', activation='relu'),
MaxPooling2D(strides=1),
Conv2D(128, 3, padding='same', activation='relu'),
MaxPooling2D(strides=1),
Conv2D(256, 3, padding='same', activation='relu'),
MaxPooling2D(strides=1),
Flatten(),
Dense(128, activation='relu'),
Dropout(.3),
Dense(64, activation='relu'),
Dropout(.3),
Dense(10, activation='softmax')
])
model.compile(optimizer='adam', loss=keras.losses.categorical_crossentropy, metrics=['accuracy'])
print (model.summary())
val_data=(X_test, Y_test)
history = model.fit(X_train, Y_train, validation_data=val_data,
batch_size= 128,
epochs= 5,
verbose= 1)
# after 5 epochs result is accuracy: 0.9883 - val_accuracy: 0.9915