将 Keras-Fuctional-API 转换为 Keras 子类模型
Convert Keras-Fuctional-API into a Keras Subclassed Model
我对 Keras 和 Tensorflow 比较陌生，我想学习基本的实现。为此，我想构建一个可以 learn/detect/predict 手写数字的模型，因此我使用了 Keras 的 MNIST 数据集。我已经使用 Keras Functional API 创建了这个模型，一切正常。现在我想做同样的事情，但这次我想构建一个 Keras 子类模型。问题是，当我使用 Keras 子类模型执行代码时出现错误。
这是具有功能 API 的模型代码（可以正常工作，没有任何问题）：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from keras.datasets import mnist
import numpy as np
#Load MNIST-Dataset
(x_train_full, y_train_full), (x_test, y_test) = mnist.load_data()
#Create train- and validationdata
X_valid = x_train_full[:5000]/255.0
X_train = x_train_full[5000:] / 255.0
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
#Create the model with the keras functional-API
inputs = keras.layers.Input(shape=(28, 28))
flatten = keras.layers.Flatten(input_shape=(28, 28))(inputs)
hidden1 = keras.layers.Dense(256, activation="relu")(flatten)
hidden2 = keras.layers.Dense(128, activation='relu')(hidden1)
outputs = keras.layers.Dense(10, activation='softmax')(hidden2)
model = keras.Model(inputs=[inputs], outputs=[outputs])
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=5, validation_data=(X_valid, y_valid))
#Evaluate the model with testdata
test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
print('\nTest accuracy: ', test_acc)
print('\nTest loss: ', test_loss)
#Create Predictions:
myPrediction = model.predict(x_test)
#Prediction example of one testpicture
print(myPrediction[0])
print('Predicted Item: ', np.argmax(myPrediction[0]))
print('Actual Item: ', y_test[0])
这里是 Keras 子类模型的（不工作）代码，它应该做与上面的代码完全相同的事情：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from keras.datasets import mnist
import numpy as np
#Load MNIST-Dataset
(x_train_full, y_train_full), (x_test, y_test) = mnist.load_data()
#Create train- and validationdata
X_valid = x_train_full[:5000]/255.0
X_train = x_train_full[5000:] / 255.0
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
#Create a keras-subclassing-model:
class MyModel(tf.keras.Model):
def __init__(self):
super(MyModel, self).__init__()
#Define layers
self.input_ = keras.layers.Input(shape=(28, 28))
self.flatten = keras.layers.Flatten(input_shape=(28, 28))
self.dense_1 = keras.layers.Dense(256, activation="relu")
self.dense_2 = keras.layers.Dense(128, activation="relu")
self.output_ = keras.layers.Dense(10, activation="softmax")
def call(self, inputs):
x = self.input_(inputs)
x = self.flatten(x)
x = self.dense_1(x)
x = self.dense_2(x)
x = self.output_(x)
return x
model = MyModel()
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
每次我 运行 这段代码时都会遇到同样的错误。调用fit(...)-方法时出现的错误：
Traceback (most recent call last):
File "c:/Users/MichaelM/Documents/PythonSkripte/MachineLearning/SubclassedModel.py", line 39, in <module>
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 819, in fit
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 235, in fit
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 593, in _process_training_inputs
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 646, in _process_inputs
x, y, sample_weight=sample_weights)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2346, in _standardize_user_data
all_inputs, y_input, dict_inputs = self._build_model_with_inputs(x, y)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2572, in _build_model_with_inputs
self._set_inputs(cast_inputs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2659, in _set_inputs
outputs = self(inputs, **kwargs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py", line 773, in __call__
outputs = call_fn(cast_inputs, *args, **kwargs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py", line 237, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in converted code:
c:/Users/MichaelM/Documents/PythonSkripte/MachineLearning/SubclassedModel.py:28 call *
x = self.input_(inputs)
C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py:447 converted_call
f in m.__dict__.values() for m in (collections, pdb, copy, inspect, re)):
C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py:447 <genexpr>
f in m.__dict__.values() for m in (collections, pdb, copy, inspect, re)):
C:\Python37\lib\site-packages\tensorflow_core\python\ops\math_ops.py:1351 tensor_equals
return gen_math_ops.equal(self, other, incompatible_shape_error=False)
C:\Python37\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py:3240 equal
name=name)
C:\Python37\lib\site-packages\tensorflow_core\python\framework\op_def_library.py:477 _apply_op_helper
repr(values), type(values).__name__, err))
TypeError: Expected float32 passed to parameter 'y' of op 'Equal', got 'collections' of type 'str' instead. Error: Expected float32, got 'collections' of type 'str' instead.
能否请您帮我解决这个问题，也许可以解释为什么这不起作用，因为我不知道这个错误的实际含义。然后我可以像在函数 API 代码中那样调用 evaluate(...) 和 predict(...) 方法吗？我使用以下配置：
- Visual Studio 代码 Python-扩展名为 IDE
- Python-版本：3.7.6
- TensorFlow-版本：2.1.0
- Keras-版本：2.2.4-tf
实际上，您不需要在调用方法中实现Input，因为您直接将数据传递给子类。我更新了代码，它按预期运行良好。请检查下面。
#Create a keras-subclassing-model:
class MyModel(tf.keras.Model):
def __init__(self):
super(MyModel, self).__init__()
#Define layers
#self.input_ = keras.layers.Input(shape=(28, 28))
self.flatten = keras.layers.Flatten(input_shape=(28, 28))
self.dense_1 = keras.layers.Dense(256, activation="relu")
self.dense_2 = keras.layers.Dense(128, activation="relu")
self.output_ = keras.layers.Dense(10, activation="softmax")
def call(self, inputs):
#x = self.input_(inputs)
x = self.flatten(inputs)
x = self.dense_1(x)
x = self.dense_2(x)
x = self.output_(x)
return x
model = MyModel()
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
输出如下
Epoch 1/10
1719/1719 [==============================] - 6s 3ms/step - loss: 0.6251 - accuracy: 0.8327 - val_loss: 0.3068 - val_accuracy: 0.9180
....
....
Epoch 10/10
1719/1719 [==============================] - 6s 3ms/step - loss: 0.1097 - accuracy: 0.9687 - val_loss: 0.1215 - val_accuracy: 0.9648
完整代码为 here.
我对 Keras 和 Tensorflow 比较陌生，我想学习基本的实现。为此，我想构建一个可以 learn/detect/predict 手写数字的模型，因此我使用了 Keras 的 MNIST 数据集。我已经使用 Keras Functional API 创建了这个模型，一切正常。现在我想做同样的事情，但这次我想构建一个 Keras 子类模型。问题是，当我使用 Keras 子类模型执行代码时出现错误。 这是具有功能 API 的模型代码（可以正常工作，没有任何问题）：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from keras.datasets import mnist
import numpy as np
#Load MNIST-Dataset
(x_train_full, y_train_full), (x_test, y_test) = mnist.load_data()
#Create train- and validationdata
X_valid = x_train_full[:5000]/255.0
X_train = x_train_full[5000:] / 255.0
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
#Create the model with the keras functional-API
inputs = keras.layers.Input(shape=(28, 28))
flatten = keras.layers.Flatten(input_shape=(28, 28))(inputs)
hidden1 = keras.layers.Dense(256, activation="relu")(flatten)
hidden2 = keras.layers.Dense(128, activation='relu')(hidden1)
outputs = keras.layers.Dense(10, activation='softmax')(hidden2)
model = keras.Model(inputs=[inputs], outputs=[outputs])
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=5, validation_data=(X_valid, y_valid))
#Evaluate the model with testdata
test_loss, test_acc = model.evaluate(x_test, y_test, verbose=2)
print('\nTest accuracy: ', test_acc)
print('\nTest loss: ', test_loss)
#Create Predictions:
myPrediction = model.predict(x_test)
#Prediction example of one testpicture
print(myPrediction[0])
print('Predicted Item: ', np.argmax(myPrediction[0]))
print('Actual Item: ', y_test[0])
这里是 Keras 子类模型的（不工作）代码，它应该做与上面的代码完全相同的事情：
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras import layers
from keras.datasets import mnist
import numpy as np
#Load MNIST-Dataset
(x_train_full, y_train_full), (x_test, y_test) = mnist.load_data()
#Create train- and validationdata
X_valid = x_train_full[:5000]/255.0
X_train = x_train_full[5000:] / 255.0
y_valid, y_train = y_train_full[:5000], y_train_full[5000:]
#Create a keras-subclassing-model:
class MyModel(tf.keras.Model):
def __init__(self):
super(MyModel, self).__init__()
#Define layers
self.input_ = keras.layers.Input(shape=(28, 28))
self.flatten = keras.layers.Flatten(input_shape=(28, 28))
self.dense_1 = keras.layers.Dense(256, activation="relu")
self.dense_2 = keras.layers.Dense(128, activation="relu")
self.output_ = keras.layers.Dense(10, activation="softmax")
def call(self, inputs):
x = self.input_(inputs)
x = self.flatten(x)
x = self.dense_1(x)
x = self.dense_2(x)
x = self.output_(x)
return x
model = MyModel()
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
每次我 运行 这段代码时都会遇到同样的错误。调用fit(...)-方法时出现的错误：
Traceback (most recent call last):
File "c:/Users/MichaelM/Documents/PythonSkripte/MachineLearning/SubclassedModel.py", line 39, in <module>
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 819, in fit
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 235, in fit
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 593, in _process_training_inputs
use_multiprocessing=use_multiprocessing)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training_v2.py", line 646, in _process_inputs
x, y, sample_weight=sample_weights)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2346, in _standardize_user_data
all_inputs, y_input, dict_inputs = self._build_model_with_inputs(x, y)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2572, in _build_model_with_inputs
self._set_inputs(cast_inputs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\training.py", line 2659, in _set_inputs
outputs = self(inputs, **kwargs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\keras\engine\base_layer.py", line 773, in __call__
outputs = call_fn(cast_inputs, *args, **kwargs)
File "C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py", line 237, in wrapper
raise e.ag_error_metadata.to_exception(e)
TypeError: in converted code:
c:/Users/MichaelM/Documents/PythonSkripte/MachineLearning/SubclassedModel.py:28 call *
x = self.input_(inputs)
C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py:447 converted_call
f in m.__dict__.values() for m in (collections, pdb, copy, inspect, re)):
C:\Python37\lib\site-packages\tensorflow_core\python\autograph\impl\api.py:447 <genexpr>
f in m.__dict__.values() for m in (collections, pdb, copy, inspect, re)):
C:\Python37\lib\site-packages\tensorflow_core\python\ops\math_ops.py:1351 tensor_equals
return gen_math_ops.equal(self, other, incompatible_shape_error=False)
C:\Python37\lib\site-packages\tensorflow_core\python\ops\gen_math_ops.py:3240 equal
name=name)
C:\Python37\lib\site-packages\tensorflow_core\python\framework\op_def_library.py:477 _apply_op_helper
repr(values), type(values).__name__, err))
TypeError: Expected float32 passed to parameter 'y' of op 'Equal', got 'collections' of type 'str' instead. Error: Expected float32, got 'collections' of type 'str' instead.
能否请您帮我解决这个问题，也许可以解释为什么这不起作用，因为我不知道这个错误的实际含义。然后我可以像在函数 API 代码中那样调用 evaluate(...) 和 predict(...) 方法吗？我使用以下配置：
- Visual Studio 代码 Python-扩展名为 IDE
- Python-版本：3.7.6
- TensorFlow-版本：2.1.0
- Keras-版本：2.2.4-tf
实际上，您不需要在调用方法中实现Input，因为您直接将数据传递给子类。我更新了代码，它按预期运行良好。请检查下面。
#Create a keras-subclassing-model:
class MyModel(tf.keras.Model):
def __init__(self):
super(MyModel, self).__init__()
#Define layers
#self.input_ = keras.layers.Input(shape=(28, 28))
self.flatten = keras.layers.Flatten(input_shape=(28, 28))
self.dense_1 = keras.layers.Dense(256, activation="relu")
self.dense_2 = keras.layers.Dense(128, activation="relu")
self.output_ = keras.layers.Dense(10, activation="softmax")
def call(self, inputs):
#x = self.input_(inputs)
x = self.flatten(inputs)
x = self.dense_1(x)
x = self.dense_2(x)
x = self.output_(x)
return x
model = MyModel()
model.compile(loss="sparse_categorical_crossentropy", optimizer="sgd", metrics=["accuracy"])
h = model.fit(X_train, y_train, epochs=10, validation_data=(X_valid, y_valid))
输出如下
Epoch 1/10
1719/1719 [==============================] - 6s 3ms/step - loss: 0.6251 - accuracy: 0.8327 - val_loss: 0.3068 - val_accuracy: 0.9180
....
....
Epoch 10/10
1719/1719 [==============================] - 6s 3ms/step - loss: 0.1097 - accuracy: 0.9687 - val_loss: 0.1215 - val_accuracy: 0.9648
完整代码为 here.