Tensorflow 无效形状 (InvalidArgumentError)
Tensorflow invalid shape (InvalidArgumentError)
model.fit 产生异常:
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot update variable with shape [] using a Tensor with shape [32], shapes must be equal.
[[{{node metrics/accuracy/AssignAddVariableOp}}]]
[[loss/dense_loss/categorical_crossentropy/weighted_loss/broadcast_weights/assert_broadcastable/AssertGuard/pivot_f/_50/_63]] [Op:__inference_keras_scratch_graph_1408]
模型定义:
model = tf.keras.Sequential()
model.add(tf.keras.layers.InputLayer(
input_shape=(360, 7)
))
model.add(tf.keras.layers.Conv1D(32, 1, activation='relu', input_shape=(360, 7)))
model.add(tf.keras.layers.Conv1D(32, 1, activation='relu'))
model.add(tf.keras.layers.MaxPooling1D(3))
model.add(tf.keras.layers.Conv1D(512, 1, activation='relu'))
model.add(tf.keras.layers.Conv1D(1048, 1, activation='relu'))
model.add(tf.keras.layers.GlobalAveragePooling1D())
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(32, activation='softmax'))
输入要素形状
(105, 360, 7)
输入标签形状
(105, 32, 1)
编译语句
model.compile(optimizer='adam',
loss=tf.keras.losses.CategoricalCrossentropy(),
metrics=['accuracy'])
Model.fit 声明
model.fit(features,
labels,
epochs=50000,
validation_split=0.2,
verbose=1)
如有任何帮助,我们将不胜感激
您可以使用 model.summary()
查看您的模型架构。
print(model.summary())
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d (Conv1D) (None, 360, 32) 256
_________________________________________________________________
conv1d_1 (Conv1D) (None, 360, 32) 1056
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 120, 32) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None, 120, 512) 16896
_________________________________________________________________
conv1d_3 (Conv1D) (None, 120, 1048) 537624
_________________________________________________________________
global_average_pooling1d (Gl (None, 1048) 0
_________________________________________________________________
dropout (Dropout) (None, 1048) 0
_________________________________________________________________
dense (Dense) (None, 32) 33568
=================================================================
Total params: 589,400
Trainable params: 589,400
Non-trainable params: 0
_________________________________________________________________
None
你的输出层的形状要求是(None,32)
,但是你的labels
的形状是(105,32,1)
。所以你需要把形状改成(105,32)
。当我们想从数组的形状中删除 single-dimensional 个条目时,使用 np.squeeze()
函数。
在密集层之前使用 Flatten()。
model.fit 产生异常:
tensorflow.python.framework.errors_impl.InvalidArgumentError: Cannot update variable with shape [] using a Tensor with shape [32], shapes must be equal.
[[{{node metrics/accuracy/AssignAddVariableOp}}]]
[[loss/dense_loss/categorical_crossentropy/weighted_loss/broadcast_weights/assert_broadcastable/AssertGuard/pivot_f/_50/_63]] [Op:__inference_keras_scratch_graph_1408]
模型定义:
model = tf.keras.Sequential()
model.add(tf.keras.layers.InputLayer(
input_shape=(360, 7)
))
model.add(tf.keras.layers.Conv1D(32, 1, activation='relu', input_shape=(360, 7)))
model.add(tf.keras.layers.Conv1D(32, 1, activation='relu'))
model.add(tf.keras.layers.MaxPooling1D(3))
model.add(tf.keras.layers.Conv1D(512, 1, activation='relu'))
model.add(tf.keras.layers.Conv1D(1048, 1, activation='relu'))
model.add(tf.keras.layers.GlobalAveragePooling1D())
model.add(tf.keras.layers.Dropout(0.5))
model.add(tf.keras.layers.Dense(32, activation='softmax'))
输入要素形状
(105, 360, 7)
输入标签形状
(105, 32, 1)
编译语句
model.compile(optimizer='adam',
loss=tf.keras.losses.CategoricalCrossentropy(),
metrics=['accuracy'])
Model.fit 声明
model.fit(features,
labels,
epochs=50000,
validation_split=0.2,
verbose=1)
如有任何帮助,我们将不胜感激
您可以使用 model.summary()
查看您的模型架构。
print(model.summary())
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv1d (Conv1D) (None, 360, 32) 256
_________________________________________________________________
conv1d_1 (Conv1D) (None, 360, 32) 1056
_________________________________________________________________
max_pooling1d (MaxPooling1D) (None, 120, 32) 0
_________________________________________________________________
conv1d_2 (Conv1D) (None, 120, 512) 16896
_________________________________________________________________
conv1d_3 (Conv1D) (None, 120, 1048) 537624
_________________________________________________________________
global_average_pooling1d (Gl (None, 1048) 0
_________________________________________________________________
dropout (Dropout) (None, 1048) 0
_________________________________________________________________
dense (Dense) (None, 32) 33568
=================================================================
Total params: 589,400
Trainable params: 589,400
Non-trainable params: 0
_________________________________________________________________
None
你的输出层的形状要求是(None,32)
,但是你的labels
的形状是(105,32,1)
。所以你需要把形状改成(105,32)
。当我们想从数组的形状中删除 single-dimensional 个条目时,使用 np.squeeze()
函数。
在密集层之前使用 Flatten()。