How to fix tensorflow "InvalidArgumentError: Shapes of all inputs must match"
How to fix tensorflow "InvalidArgumentError: Shapes of all inputs must match"
我正在尝试通过顺序 Keras 神经网络 运行 小波重建数据集。为了从训练中获得更好的结果，我试图构建一个自定义损失函数，它只关注波形的某些指标。我打算创建一个神经网络来插入剪切波形，所以我只希望神经网络通过将波形的剪切段与实际输出进行比较来计算损失。
我已经尝试为我的自定义损失函数创建一个包装器，以便我可以传入一个额外的输入参数。然后，我使用此输入参数来查找裁剪数据点的索引，并尝试从 y_pred 和 y_true.
收集这些索引
这是实例化和训练模型的地方：
x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.7)
_dim = len(x_train[0])
# define the keras model
model = Sequential()
# tanh activation allows for vals between -1 and 1 unlike relu
model.add(Dense(_dim*2, input_dim=_dim, activation=_activation))
model.add(Dense(_dim*2, activation=_activation))
model.add(Dense(_dim, activation=_activation))
# model.compile(loss=_loss, optimizer=_optimizer)
model.compile(loss=_loss, optimizer=_optimizer, metrics=[custom_loss_wrapper_2(x_train)])
print(model.summary())
# The patience parameter is the amount of epochs to check for improvement
early_stop = EarlyStopping(monitor='val_loss', patience=5)
# fit the model
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=150, batch_size=15, callbacks=[early_stop])
这就是我的自定义损失函数所在的位置：
def custom_loss_wrapper_2(inputs):
# source:
# 2nd source: http://whosebug.com/questions.55597335/how-to-use-tf-gather-in-batch
def reindex(tensor_tuple):
# unpack tensor tuple
y_true = tensor_tuple[0]
y_pred = tensor_tuple[1]
t_inputs = K.cast(tensor_tuple[2], dtype='int64')
t_max_indices = K.tf.where(K.tf.equal(t_inputs, K.max(t_inputs)))
# gather the values from y_true and y_pred
y_true_gathered = K.gather(y_true, t_max_indices)
y_pred_gathered = K.gather(y_pred, t_max_indices)
print(K.mean(K.square(y_true_gathered - y_pred_gathered)))
return K.mean(K.square(y_true_gathered - y_pred_gathered))
def custom_loss(y_true, y_pred):
# Step 1: "tensorize" the previous list
t_inputs = K.variable(inputs)
# Step 2: Stack tensors
tensor_tuple = K.stack([y_true, y_pred, t_inputs], axis=1)
vals = K.map_fn(reindex, tensor_tuple, dtype='float32')
print('vals: ', vals)
return K.mean(vals)
return custom_loss
我在尝试自定义损失函数时收到以下错误消息：
Using TensorFlow backend.
WARNING: Logging before flag parsing goes to stderr.
W0722 15:28:20.239395 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
W0722 15:28:20.252325 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
W0722 15:28:20.253353 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.
W0722 15:28:20.280281 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.
W0722 15:28:20.293246 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:1521: The name tf.log is deprecated. Please use tf.math.log instead.
W0722 15:28:20.366046 17232 deprecation.py:323] From C:\Users\Madison\PycharmProjects\MSTS\Seismic_Analysis\ML\custom_loss.py:83: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
Tensor("metrics/custom_loss/map/while/Mean:0", shape=(), dtype=float32)
vals: Tensor("metrics/custom_loss/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(1228,), dtype=float32)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 1002) 503004
_________________________________________________________________
dense_2 (Dense) (None, 1002) 1005006
_________________________________________________________________
dense_3 (Dense) (None, 501) 502503
=================================================================
Total params: 2,010,513
Trainable params: 2,010,513
Non-trainable params: 0
_________________________________________________________________
None
W0722 15:28:20.467779 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.
Train on 1228 samples, validate on 527 samples
Epoch 1/150
2019-07-22 15:28:20.606792: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Traceback (most recent call last):
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 172, in <module>
main()
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 168, in main
run_general()
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 156, in run_general
_loss=_loss, _activation=_activation, _optimizer=_optimizer)
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 59, in build_clipping_model
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=150, batch_size=15, callbacks=[early_stop])
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\engine\training.py", line 1039, in fit
validation_steps=validation_steps)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\engine\training_arrays.py", line 199, in fit_loop
outs = f(ins_batch)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__
return self._call(inputs)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\tensorflow\python\client\session.py", line 1458, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.**InvalidArgumentError: Shapes of all inputs must match**: values[0].shape = [15,501] != values[2].shape = [1228,501]
[[{{node metrics/custom_loss/stack}}]]
能否分享一个可运行但失败的问题示例？即使只有几个数据点。现在看起来您的数据形状不一致。例如。一个小波比另一个长。批次需要是同质的。一种检查方法是：
print(set(inp.shape for inp in inputs))
如果该集合包含多个元素，您可能需要扩充数据。
来自问题片段的示例代码
import numpy as np
from keras import backend as K
from keras.callbacks import EarlyStopping
from keras.layers import Dense, Activation
from keras.models import Sequential
from keras import optimizers
from sklearn.model_selection import train_test_split
_activation = Activation('softmax')
_optimizer = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
def custom_loss_wrapper_2(inputs):
print("inputs {}".format(inputs.shape))
# source:
# 2nd source: http://whosebug.com/questions.55597335/how-to-use-tf-gather-in-batch
def reindex(tensor_tuple):
# unpack tensor tuple
y_true = tensor_tuple[0]
y_pred = tensor_tuple[1]
t_inputs = K.cast(tensor_tuple[2], dtype='int64')
t_max_indices = K.tf.where(K.tf.equal(t_inputs, K.max(t_inputs)))
# gather the values from y_true and y_pred
print("y_true {}".format(y_true.shape))
print("y_pred {}".format(y_pred.shape))
y_true_gathered = K.gather(y_true, t_max_indices)
y_pred_gathered = K.gather(y_pred, t_max_indices)
print(K.mean(K.square(y_true_gathered - y_pred_gathered)))
return K.mean(K.square(y_true_gathered - y_pred_gathered))
def custom_loss(y_true, y_pred):
print("y_true2 {}".format(y_true.shape))
print("y_pred2 {}".format(y_pred.shape))
# Step 1: "tensorize" the previous list
t_inputs = K.variable(inputs)
# Step 2: Stack tensors
tensor_tuple = K.stack([y_true, y_pred, t_inputs], axis=1)
vals = K.map_fn(reindex, tensor_tuple, dtype='float32')
print('vals: {}'.format(vals.shape))
print('kvals: {}'.format(K.mean(vals).shape))
return K.mean(vals, keepdims=True)
return custom_loss
dataset_size = 100
dim = 501
X = np.random.rand(dataset_size, dim)
Y = np.random.rand(dataset_size, dim)
x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.7)
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)
_dim = len(x_train[0])
print("_dim {}".format(_dim))
# define the keras model
model = Sequential()
_loss = custom_loss_wrapper_2(x_train)
_mmm = _loss
# tanh activation allows for vals between -1 and 1 unlike relu
model.add(Dense(_dim*2, input_shape=(_dim,), activation=_activation))
model.add(Dense(_dim*2, activation=_activation))
model.add(Dense(_dim, activation=_activation))
# model.compile(loss=_loss, optimizer=_optimizer)
model.compile(loss=_loss, optimizer=_optimizer, metrics=[_mmm])
print(model.summary())
# The patience parameter is the amount of epochs to check for improvement
early_stop = EarlyStopping(monitor='val_loss', patience=5)
# fit the model
history = model.fit(
x_train,
y_train,
validation_data=(x_test, y_test),
epochs=150,
batch_size=10,
callbacks=[early_stop])
经过深思熟虑，我找到了原来问题的答案。我想我会 post 把它放在这里，以防将来它对某人有所帮助。我遇到的问题与我提供损失函数包装器的输入参数有关。当我应该只传递批处理输入时，我传递了整个输入数组。这是在函数调用期间通过发送 model.inputs 来完成的。所以新的编译行应该是这样的：
model.compile(loss=_loss, optimizer=_optimizer, metrics=[custom_loss_wrapper_2(model.input)])
我正在尝试通过顺序 Keras 神经网络 运行 小波重建数据集。为了从训练中获得更好的结果，我试图构建一个自定义损失函数，它只关注波形的某些指标。我打算创建一个神经网络来插入剪切波形，所以我只希望神经网络通过将波形的剪切段与实际输出进行比较来计算损失。
我已经尝试为我的自定义损失函数创建一个包装器，以便我可以传入一个额外的输入参数。然后，我使用此输入参数来查找裁剪数据点的索引，并尝试从 y_pred 和 y_true.
收集这些索引这是实例化和训练模型的地方：
x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.7)
_dim = len(x_train[0])
# define the keras model
model = Sequential()
# tanh activation allows for vals between -1 and 1 unlike relu
model.add(Dense(_dim*2, input_dim=_dim, activation=_activation))
model.add(Dense(_dim*2, activation=_activation))
model.add(Dense(_dim, activation=_activation))
# model.compile(loss=_loss, optimizer=_optimizer)
model.compile(loss=_loss, optimizer=_optimizer, metrics=[custom_loss_wrapper_2(x_train)])
print(model.summary())
# The patience parameter is the amount of epochs to check for improvement
early_stop = EarlyStopping(monitor='val_loss', patience=5)
# fit the model
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=150, batch_size=15, callbacks=[early_stop])
这就是我的自定义损失函数所在的位置：
def custom_loss_wrapper_2(inputs):
# source:
# 2nd source: http://whosebug.com/questions.55597335/how-to-use-tf-gather-in-batch
def reindex(tensor_tuple):
# unpack tensor tuple
y_true = tensor_tuple[0]
y_pred = tensor_tuple[1]
t_inputs = K.cast(tensor_tuple[2], dtype='int64')
t_max_indices = K.tf.where(K.tf.equal(t_inputs, K.max(t_inputs)))
# gather the values from y_true and y_pred
y_true_gathered = K.gather(y_true, t_max_indices)
y_pred_gathered = K.gather(y_pred, t_max_indices)
print(K.mean(K.square(y_true_gathered - y_pred_gathered)))
return K.mean(K.square(y_true_gathered - y_pred_gathered))
def custom_loss(y_true, y_pred):
# Step 1: "tensorize" the previous list
t_inputs = K.variable(inputs)
# Step 2: Stack tensors
tensor_tuple = K.stack([y_true, y_pred, t_inputs], axis=1)
vals = K.map_fn(reindex, tensor_tuple, dtype='float32')
print('vals: ', vals)
return K.mean(vals)
return custom_loss
我在尝试自定义损失函数时收到以下错误消息：
Using TensorFlow backend.
WARNING: Logging before flag parsing goes to stderr.
W0722 15:28:20.239395 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:74: The name tf.get_default_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.
W0722 15:28:20.252325 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:517: The name tf.placeholder is deprecated. Please use tf.compat.v1.placeholder instead.
W0722 15:28:20.253353 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:4138: The name tf.random_uniform is deprecated. Please use tf.random.uniform instead.
W0722 15:28:20.280281 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\optimizers.py:790: The name tf.train.Optimizer is deprecated. Please use tf.compat.v1.train.Optimizer instead.
W0722 15:28:20.293246 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:1521: The name tf.log is deprecated. Please use tf.math.log instead.
W0722 15:28:20.366046 17232 deprecation.py:323] From C:\Users\Madison\PycharmProjects\MSTS\Seismic_Analysis\ML\custom_loss.py:83: add_dispatch_support.<locals>.wrapper (from tensorflow.python.ops.array_ops) is deprecated and will be removed in a future version.
Instructions for updating:
Use tf.where in 2.0, which has the same broadcast rule as np.where
Tensor("metrics/custom_loss/map/while/Mean:0", shape=(), dtype=float32)
vals: Tensor("metrics/custom_loss/map/TensorArrayStack/TensorArrayGatherV3:0", shape=(1228,), dtype=float32)
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
dense_1 (Dense) (None, 1002) 503004
_________________________________________________________________
dense_2 (Dense) (None, 1002) 1005006
_________________________________________________________________
dense_3 (Dense) (None, 501) 502503
=================================================================
Total params: 2,010,513
Trainable params: 2,010,513
Non-trainable params: 0
_________________________________________________________________
None
W0722 15:28:20.467779 17232 deprecation_wrapper.py:119] From C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py:986: The name tf.assign_add is deprecated. Please use tf.compat.v1.assign_add instead.
Train on 1228 samples, validate on 527 samples
Epoch 1/150
2019-07-22 15:28:20.606792: I tensorflow/core/platform/cpu_feature_guard.cc:142] Your CPU supports instructions that this TensorFlow binary was not compiled to use: AVX2
Traceback (most recent call last):
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 172, in <module>
main()
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 168, in main
run_general()
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 156, in run_general
_loss=_loss, _activation=_activation, _optimizer=_optimizer)
File "C:/Users/Madison/PycharmProjects/MSTS/Seismic_Analysis/ML/clipping_ml.py", line 59, in build_clipping_model
history = model.fit(x_train, y_train, validation_data=(x_test, y_test), epochs=150, batch_size=15, callbacks=[early_stop])
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\engine\training.py", line 1039, in fit
validation_steps=validation_steps)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\engine\training_arrays.py", line 199, in fit_loop
outs = f(ins_batch)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2715, in __call__
return self._call(inputs)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\keras\backend\tensorflow_backend.py", line 2675, in _call
fetched = self._callable_fn(*array_vals)
File "C:\Users\Madison\PycharmProjects\MSTS\venv\lib\site-packages\tensorflow\python\client\session.py", line 1458, in __call__
run_metadata_ptr)
tensorflow.python.framework.errors_impl.**InvalidArgumentError: Shapes of all inputs must match**: values[0].shape = [15,501] != values[2].shape = [1228,501]
[[{{node metrics/custom_loss/stack}}]]
能否分享一个可运行但失败的问题示例？即使只有几个数据点。现在看起来您的数据形状不一致。例如。一个小波比另一个长。批次需要是同质的。一种检查方法是：
print(set(inp.shape for inp in inputs))
如果该集合包含多个元素，您可能需要扩充数据。
来自问题片段的示例代码
import numpy as np
from keras import backend as K
from keras.callbacks import EarlyStopping
from keras.layers import Dense, Activation
from keras.models import Sequential
from keras import optimizers
from sklearn.model_selection import train_test_split
_activation = Activation('softmax')
_optimizer = optimizers.SGD(lr=0.01, decay=1e-6, momentum=0.9, nesterov=True)
def custom_loss_wrapper_2(inputs):
print("inputs {}".format(inputs.shape))
# source:
# 2nd source: http://whosebug.com/questions.55597335/how-to-use-tf-gather-in-batch
def reindex(tensor_tuple):
# unpack tensor tuple
y_true = tensor_tuple[0]
y_pred = tensor_tuple[1]
t_inputs = K.cast(tensor_tuple[2], dtype='int64')
t_max_indices = K.tf.where(K.tf.equal(t_inputs, K.max(t_inputs)))
# gather the values from y_true and y_pred
print("y_true {}".format(y_true.shape))
print("y_pred {}".format(y_pred.shape))
y_true_gathered = K.gather(y_true, t_max_indices)
y_pred_gathered = K.gather(y_pred, t_max_indices)
print(K.mean(K.square(y_true_gathered - y_pred_gathered)))
return K.mean(K.square(y_true_gathered - y_pred_gathered))
def custom_loss(y_true, y_pred):
print("y_true2 {}".format(y_true.shape))
print("y_pred2 {}".format(y_pred.shape))
# Step 1: "tensorize" the previous list
t_inputs = K.variable(inputs)
# Step 2: Stack tensors
tensor_tuple = K.stack([y_true, y_pred, t_inputs], axis=1)
vals = K.map_fn(reindex, tensor_tuple, dtype='float32')
print('vals: {}'.format(vals.shape))
print('kvals: {}'.format(K.mean(vals).shape))
return K.mean(vals, keepdims=True)
return custom_loss
dataset_size = 100
dim = 501
X = np.random.rand(dataset_size, dim)
Y = np.random.rand(dataset_size, dim)
x_train, x_test, y_train, y_test = train_test_split(X, Y, train_size=0.7)
print(x_train.shape)
print(y_train.shape)
print(x_test.shape)
print(y_test.shape)
_dim = len(x_train[0])
print("_dim {}".format(_dim))
# define the keras model
model = Sequential()
_loss = custom_loss_wrapper_2(x_train)
_mmm = _loss
# tanh activation allows for vals between -1 and 1 unlike relu
model.add(Dense(_dim*2, input_shape=(_dim,), activation=_activation))
model.add(Dense(_dim*2, activation=_activation))
model.add(Dense(_dim, activation=_activation))
# model.compile(loss=_loss, optimizer=_optimizer)
model.compile(loss=_loss, optimizer=_optimizer, metrics=[_mmm])
print(model.summary())
# The patience parameter is the amount of epochs to check for improvement
early_stop = EarlyStopping(monitor='val_loss', patience=5)
# fit the model
history = model.fit(
x_train,
y_train,
validation_data=(x_test, y_test),
epochs=150,
batch_size=10,
callbacks=[early_stop])
经过深思熟虑，我找到了原来问题的答案。我想我会 post 把它放在这里，以防将来它对某人有所帮助。我遇到的问题与我提供损失函数包装器的输入参数有关。当我应该只传递批处理输入时，我传递了整个输入数组。这是在函数调用期间通过发送 model.inputs 来完成的。所以新的编译行应该是这样的：
model.compile(loss=_loss, optimizer=_optimizer, metrics=[custom_loss_wrapper_2(model.input)])