ValueError: Unknown loss function:focal_loss_fixed when loading model with my custom loss function
ValueError: Unknown loss function:focal_loss_fixed when loading model with my custom loss function
我设计了自己的损失函数。但是，当尝试恢复到
训练期间遇到的最佳模型时
model = load_model("lc_model.h5")
我收到以下错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-105-9d09ef163b0a> in <module>
23
24 # revert to the best model encountered during training
---> 25 model = load_model("lc_model.h5")
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\saving.py in load_model(filepath, custom_objects, compile)
417 f = h5dict(filepath, 'r')
418 try:
--> 419 model = _deserialize_model(f, custom_objects, compile)
420 finally:
421 if opened_new_file:
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\saving.py in _deserialize_model(f, custom_objects, compile)
310 metrics=metrics,
311 loss_weights=loss_weights,
--> 312 sample_weight_mode=sample_weight_mode)
313
314 # Set optimizer weights.
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
137 loss_functions = [losses.get(l) for l in loss]
138 else:
--> 139 loss_function = losses.get(loss)
140 loss_functions = [loss_function for _ in range(len(self.outputs))]
141 self.loss_functions = loss_functions
C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py in get(identifier)
131 if isinstance(identifier, six.string_types):
132 identifier = str(identifier)
--> 133 return deserialize(identifier)
134 if isinstance(identifier, dict):
135 return deserialize(identifier)
C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py in deserialize(name, custom_objects)
112 module_objects=globals(),
113 custom_objects=custom_objects,
--> 114 printable_module_name='loss function')
115
116
C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
163 if fn is None:
164 raise ValueError('Unknown ' + printable_module_name +
--> 165 ':' + function_name)
166 return fn
167 else:
ValueError: Unknown loss function:focal_loss_fixed
这是神经网络：
from keras.callbacks import ModelCheckpoint
from keras.models import load_model
model = create_model(x_train.shape[1], y_train.shape[1])
epochs = 35
batch_sz = 64
print("Beginning model training with batch size {} and {} epochs".format(batch_sz, epochs))
checkpoint = ModelCheckpoint("lc_model.h5", monitor='val_acc', verbose=0, save_best_only=True, mode='auto', period=1)
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.constraints import maxnorm
def create_model(input_dim, output_dim):
print(output_dim)
# create model
model = Sequential()
# input layer
model.add(Dense(100, input_dim=input_dim, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
# hidden layer
model.add(Dense(60, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
# output layer
model.add(Dense(output_dim, activation='softmax'))
# Compile model
# model.compile(loss='categorical_crossentropy', loss_weights=None, optimizer='adam', metrics=['accuracy'])
model.compile(loss=focal_loss(alpha=1), loss_weights=None, optimizer='adam', metrics=['accuracy'])
return model
# train the model
history = model.fit(x_train.as_matrix(),
y_train.as_matrix(),
validation_split=0.2,
epochs=epochs,
batch_size=batch_sz, # Can I tweak the batch here to get evenly distributed data ?
verbose=2,
class_weight = weights, # class_weight tells the model to "pay more attention" to samples from an under-represented fraud class.
callbacks=[checkpoint])
# revert to the best model encountered during training
model = load_model("lc_model.h5")
这是我的损失函数：
import tensorflow as tf
def focal_loss(gamma=2., alpha=4.):
gamma = float(gamma)
alpha = float(alpha)
def focal_loss_fixed(y_true, y_pred):
"""Focal loss for multi-classification
FL(p_t)=-alpha(1-p_t)^{gamma}ln(p_t)
Notice: y_pred is probability after softmax
gradient is d(Fl)/d(p_t) not d(Fl)/d(x) as described in paper
d(Fl)/d(p_t) * [p_t(1-p_t)] = d(Fl)/d(x)
Focal Loss for Dense Object Detection
https://arxiv.org/abs/1708.02002
Arguments:
y_true {tensor} -- ground truth labels, shape of [batch_size, num_cls]
y_pred {tensor} -- model's output, shape of [batch_size, num_cls]
Keyword Arguments:
gamma {float} -- (default: {2.0})
alpha {float} -- (default: {4.0})
Returns:
[tensor] -- loss.
"""
epsilon = 1.e-9
y_true = tf.convert_to_tensor(y_true, tf.float32)
y_pred = tf.convert_to_tensor(y_pred, tf.float32)
model_out = tf.add(y_pred, epsilon)
ce = tf.multiply(y_true, -tf.log(model_out))
weight = tf.multiply(y_true, tf.pow(tf.subtract(1., model_out), gamma))
fl = tf.multiply(alpha, tf.multiply(weight, ce))
reduced_fl = tf.reduce_max(fl, axis=1)
return tf.reduce_mean(reduced_fl)
return focal_loss_fixed
# model.compile(loss=focal_loss(alpha=1), optimizer='nadam', metrics=['accuracy'])
# model.fit(X_train, y_train, epochs=3, batch_size=1000)
您必须加载 focal_loss_fixed 的 custom_objects，如下所示：
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss()})
但是，如果您只想对您的模型进行推理而不进一步优化或训练您的模型，您可以像这样忽略损失函数：
model = load_model("lc_model.h5", compile=False)
@Prasad 的回答很好，但我想补充一点解释和一点更正：
在 custom_objects 词典中提及您的自定义损失函数时，您不必调用损失函数，因为它可能会导致一些参数缺失错误。
# Instead of this
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss()})
# ty this without calling your loss function
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss})
此外，我想在这里补充的是，你必须使用你的自定义损失函数的名称作为键，你的函数对象作为它在 custom_objects 中的值。我知道这是非常基本的，但值得一提，但我希望这对某人有所帮助。
我设计了自己的损失函数。但是，当尝试恢复到
训练期间遇到的最佳模型时model = load_model("lc_model.h5")
我收到以下错误：
---------------------------------------------------------------------------
ValueError Traceback (most recent call last)
<ipython-input-105-9d09ef163b0a> in <module>
23
24 # revert to the best model encountered during training
---> 25 model = load_model("lc_model.h5")
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\saving.py in load_model(filepath, custom_objects, compile)
417 f = h5dict(filepath, 'r')
418 try:
--> 419 model = _deserialize_model(f, custom_objects, compile)
420 finally:
421 if opened_new_file:
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\saving.py in _deserialize_model(f, custom_objects, compile)
310 metrics=metrics,
311 loss_weights=loss_weights,
--> 312 sample_weight_mode=sample_weight_mode)
313
314 # Set optimizer weights.
C:\ProgramData\Anaconda3\lib\site-packages\keras\engine\training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
137 loss_functions = [losses.get(l) for l in loss]
138 else:
--> 139 loss_function = losses.get(loss)
140 loss_functions = [loss_function for _ in range(len(self.outputs))]
141 self.loss_functions = loss_functions
C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py in get(identifier)
131 if isinstance(identifier, six.string_types):
132 identifier = str(identifier)
--> 133 return deserialize(identifier)
134 if isinstance(identifier, dict):
135 return deserialize(identifier)
C:\ProgramData\Anaconda3\lib\site-packages\keras\losses.py in deserialize(name, custom_objects)
112 module_objects=globals(),
113 custom_objects=custom_objects,
--> 114 printable_module_name='loss function')
115
116
C:\ProgramData\Anaconda3\lib\site-packages\keras\utils\generic_utils.py in deserialize_keras_object(identifier, module_objects, custom_objects, printable_module_name)
163 if fn is None:
164 raise ValueError('Unknown ' + printable_module_name +
--> 165 ':' + function_name)
166 return fn
167 else:
ValueError: Unknown loss function:focal_loss_fixed
这是神经网络：
from keras.callbacks import ModelCheckpoint
from keras.models import load_model
model = create_model(x_train.shape[1], y_train.shape[1])
epochs = 35
batch_sz = 64
print("Beginning model training with batch size {} and {} epochs".format(batch_sz, epochs))
checkpoint = ModelCheckpoint("lc_model.h5", monitor='val_acc', verbose=0, save_best_only=True, mode='auto', period=1)
from keras.models import Sequential
from keras.layers import Dense, Dropout
from keras.constraints import maxnorm
def create_model(input_dim, output_dim):
print(output_dim)
# create model
model = Sequential()
# input layer
model.add(Dense(100, input_dim=input_dim, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
# hidden layer
model.add(Dense(60, activation='relu', kernel_constraint=maxnorm(3)))
model.add(Dropout(0.2))
# output layer
model.add(Dense(output_dim, activation='softmax'))
# Compile model
# model.compile(loss='categorical_crossentropy', loss_weights=None, optimizer='adam', metrics=['accuracy'])
model.compile(loss=focal_loss(alpha=1), loss_weights=None, optimizer='adam', metrics=['accuracy'])
return model
# train the model
history = model.fit(x_train.as_matrix(),
y_train.as_matrix(),
validation_split=0.2,
epochs=epochs,
batch_size=batch_sz, # Can I tweak the batch here to get evenly distributed data ?
verbose=2,
class_weight = weights, # class_weight tells the model to "pay more attention" to samples from an under-represented fraud class.
callbacks=[checkpoint])
# revert to the best model encountered during training
model = load_model("lc_model.h5")
这是我的损失函数：
import tensorflow as tf
def focal_loss(gamma=2., alpha=4.):
gamma = float(gamma)
alpha = float(alpha)
def focal_loss_fixed(y_true, y_pred):
"""Focal loss for multi-classification
FL(p_t)=-alpha(1-p_t)^{gamma}ln(p_t)
Notice: y_pred is probability after softmax
gradient is d(Fl)/d(p_t) not d(Fl)/d(x) as described in paper
d(Fl)/d(p_t) * [p_t(1-p_t)] = d(Fl)/d(x)
Focal Loss for Dense Object Detection
https://arxiv.org/abs/1708.02002
Arguments:
y_true {tensor} -- ground truth labels, shape of [batch_size, num_cls]
y_pred {tensor} -- model's output, shape of [batch_size, num_cls]
Keyword Arguments:
gamma {float} -- (default: {2.0})
alpha {float} -- (default: {4.0})
Returns:
[tensor] -- loss.
"""
epsilon = 1.e-9
y_true = tf.convert_to_tensor(y_true, tf.float32)
y_pred = tf.convert_to_tensor(y_pred, tf.float32)
model_out = tf.add(y_pred, epsilon)
ce = tf.multiply(y_true, -tf.log(model_out))
weight = tf.multiply(y_true, tf.pow(tf.subtract(1., model_out), gamma))
fl = tf.multiply(alpha, tf.multiply(weight, ce))
reduced_fl = tf.reduce_max(fl, axis=1)
return tf.reduce_mean(reduced_fl)
return focal_loss_fixed
# model.compile(loss=focal_loss(alpha=1), optimizer='nadam', metrics=['accuracy'])
# model.fit(X_train, y_train, epochs=3, batch_size=1000)
您必须加载 focal_loss_fixed 的 custom_objects，如下所示：
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss()})
但是，如果您只想对您的模型进行推理而不进一步优化或训练您的模型，您可以像这样忽略损失函数：
model = load_model("lc_model.h5", compile=False)
@Prasad 的回答很好，但我想补充一点解释和一点更正：
在 custom_objects 词典中提及您的自定义损失函数时，您不必调用损失函数，因为它可能会导致一些参数缺失错误。
# Instead of this
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss()})
# ty this without calling your loss function
model = load_model("lc_model.h5", custom_objects={'focal_loss_fixed': focal_loss})
此外，我想在这里补充的是，你必须使用你的自定义损失函数的名称作为键，你的函数对象作为它在 custom_objects 中的值。我知道这是非常基本的，但值得一提，但我希望这对某人有所帮助。