在 keras 中实现自定义 objective 函数
Implementing custom objective function in keras
我正在尝试实现我自己的成本函数，具体如下：
现在我知道这个问题已经在这个网站上被问过好几次了，我读到的答案通常如下所示：
def custom_objective(y_true, y_pred):
....
return L
人们似乎总是使用 y_true 和 y_pred 然后说你只需要编译模型 model.compile(loss=custom_objective) 然后从那里开始。没有人真正提到代码中的某处 y_true=something 和 y_pred=something。这是我必须在我的模型中指定的东西吗？
我的代码
不确定我是否使用 .predict() 正确地从正在训练的模型中获得 运行ning 预测：
params = {'lr': 0.0001,
'batch_size': 30,
'epochs': 400,
'dropout': 0.2,
'optimizer': 'adam',
'losses': 'avg_partial_likelihood',
'activation':'relu',
'last_activation': 'linear'}
def model(x_train, y_train, x_val, y_val):
l2_reg = 0.4
kernel_init ='he_uniform'
bias_init ='he_uniform'
layers=[20, 20, 1]
model = Sequential()
# layer 1
model.add(Dense(layers[0], input_dim=x_train.shape[1],
W_regularizer=l2(l2_reg),
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.add(BatchNormalization(axis=-1, momentum=momentum, center=True))
model.add(Activation(params['activation']))
model.add(Dropout(params['dropout']))
# layer 2+
for layer in range(0, len(layers)-1):
model.add(Dense(layers[layer+1], W_regularizer=l2(l2_reg),
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.add(BatchNormalization(axis=-1, momentum=momentum, center=True))
model.add(Activation(params['activation']))
model.add(Dropout(params['dropout']))
# Last layer
model.add(Dense(layers[-1], activation=params['last_activation'],
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.compile(loss=params['losses'],
optimizer=keras.optimizers.adam(lr=params['lr']),
metrics=['accuracy'])
history = model.fit(x_train, y_train,
validation_data=[x_val, y_val],
batch_size=params['batch_size'],
epochs=params['epochs'],
verbose=1)
y_pred = model.predict(x_train, batch_size=params['batch_size'])
history_dict = history.history
model_output = {'model':model,
'history_dict':history_dict,
'log_risk':y_pred}
return model_output
然后创建模型：
model(x_train, y_train, x_val, y_val)
到目前为止我的 objective 功能
'log_risk' 将是 y_true 并且 x_train 将用于计算 y_pred:
def avg_partial_likelihood(x_train, log_risk):
from lifelines import CoxPHFitter
cph = CoxPHFitter()
cph.fit(x_train, duration_col='survival_fu_combine', event_col='death',
show_progress=False)
# obtain exp(hx)
cph_output = pd.DataFrame(cph.summary).T
# summing hazard ratio
hazard_ratio_sum = cph_output.iloc[1,].sum()
# -log(sum(exp(hxj)))
neg_log_sum = -np.log(hazard_ratio_sum)
# sum of positive events (death==1)
sum_noncensored_events = (x_train.death==1).sum()
# neg_likelihood
neg_likelihood = -(log_risk + neg_log_sum)/sum_noncensored_events
return neg_likelihood
如果我尝试 运行
会出错
AttributeError Traceback (most recent call last)
<ipython-input-26-cf0236299ad5> in <module>()
----> 1 model(x_train, y_train, x_val, y_val)
<ipython-input-25-d0f9409c831a> in model(x_train, y_train, x_val, y_val)
45 model.compile(loss=avg_partial_likelihood,
46 optimizer=keras.optimizers.adam(lr=params['lr']),
---> 47 metrics=['accuracy'])
48
49 history = model.fit(x_train, y_train,
~\Anaconda3\lib\site-packages\keras\engine\training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
331 with K.name_scope(self.output_names[i] + '_loss'):
332 output_loss = weighted_loss(y_true, y_pred,
--> 333 sample_weight, mask)
334 if len(self.outputs) > 1:
335 self.metrics_tensors.append(output_loss)
~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in weighted(y_true, y_pred, weights, mask)
401 """
402 # score_array has ndim >= 2
--> 403 score_array = fn(y_true, y_pred)
404 if mask is not None:
405 # Cast the mask to floatX to avoid float64 upcasting in Theano
<ipython-input-23-ed57799a1f9d> in avg_partial_likelihood(x_train, log_risk)
27
28 cph.fit(x_train, duration_col='survival_fu_combine', event_col='death',
---> 29 show_progress=False)
30
31 # obtain exp(hx)
~\Anaconda3\lib\site-packages\lifelines\fitters\coxph_fitter.py in fit(self, df, duration_col, event_col, show_progress, initial_beta, strata, step_size, weights_col)
90 """
91
---> 92 df = df.copy()
93
94 # Sort on time
AttributeError: 'Tensor' object has no attribute 'copy'
No one really mentions that somewhere in the code that
y_true=something and y_pred=something ...
他们不提是因为您不需要这样做！实际上，在每次传递结束时（即一批前向传播），Keras 使用该传递模型的真实标签和预测来提供 y_true 和 y_pred。因此，您根本不需要在模型中定义 y_true 和 y_pred。只需使用后端函数（即 from keras import backend as K）定义你的损失函数，一切都会正常工作（永远不要在你的损失函数中使用 numpy）。要获得一个想法，请查看 built-in loss functions in Keras and see how they have been implemented. And here 是可用后端函数的（可能不完整）列表。
我正在尝试实现我自己的成本函数，具体如下：
现在我知道这个问题已经在这个网站上被问过好几次了，我读到的答案通常如下所示：
def custom_objective(y_true, y_pred):
....
return L
人们似乎总是使用 y_true 和 y_pred 然后说你只需要编译模型 model.compile(loss=custom_objective) 然后从那里开始。没有人真正提到代码中的某处 y_true=something 和 y_pred=something。这是我必须在我的模型中指定的东西吗？
我的代码
不确定我是否使用 .predict() 正确地从正在训练的模型中获得 运行ning 预测：
params = {'lr': 0.0001,
'batch_size': 30,
'epochs': 400,
'dropout': 0.2,
'optimizer': 'adam',
'losses': 'avg_partial_likelihood',
'activation':'relu',
'last_activation': 'linear'}
def model(x_train, y_train, x_val, y_val):
l2_reg = 0.4
kernel_init ='he_uniform'
bias_init ='he_uniform'
layers=[20, 20, 1]
model = Sequential()
# layer 1
model.add(Dense(layers[0], input_dim=x_train.shape[1],
W_regularizer=l2(l2_reg),
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.add(BatchNormalization(axis=-1, momentum=momentum, center=True))
model.add(Activation(params['activation']))
model.add(Dropout(params['dropout']))
# layer 2+
for layer in range(0, len(layers)-1):
model.add(Dense(layers[layer+1], W_regularizer=l2(l2_reg),
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.add(BatchNormalization(axis=-1, momentum=momentum, center=True))
model.add(Activation(params['activation']))
model.add(Dropout(params['dropout']))
# Last layer
model.add(Dense(layers[-1], activation=params['last_activation'],
kernel_initializer=kernel_init,
bias_initializer=bias_init))
model.compile(loss=params['losses'],
optimizer=keras.optimizers.adam(lr=params['lr']),
metrics=['accuracy'])
history = model.fit(x_train, y_train,
validation_data=[x_val, y_val],
batch_size=params['batch_size'],
epochs=params['epochs'],
verbose=1)
y_pred = model.predict(x_train, batch_size=params['batch_size'])
history_dict = history.history
model_output = {'model':model,
'history_dict':history_dict,
'log_risk':y_pred}
return model_output
然后创建模型：
model(x_train, y_train, x_val, y_val)
到目前为止我的 objective 功能
'log_risk' 将是 y_true 并且 x_train 将用于计算 y_pred:
def avg_partial_likelihood(x_train, log_risk):
from lifelines import CoxPHFitter
cph = CoxPHFitter()
cph.fit(x_train, duration_col='survival_fu_combine', event_col='death',
show_progress=False)
# obtain exp(hx)
cph_output = pd.DataFrame(cph.summary).T
# summing hazard ratio
hazard_ratio_sum = cph_output.iloc[1,].sum()
# -log(sum(exp(hxj)))
neg_log_sum = -np.log(hazard_ratio_sum)
# sum of positive events (death==1)
sum_noncensored_events = (x_train.death==1).sum()
# neg_likelihood
neg_likelihood = -(log_risk + neg_log_sum)/sum_noncensored_events
return neg_likelihood
如果我尝试 运行
会出错 AttributeError Traceback (most recent call last)
<ipython-input-26-cf0236299ad5> in <module>()
----> 1 model(x_train, y_train, x_val, y_val)
<ipython-input-25-d0f9409c831a> in model(x_train, y_train, x_val, y_val)
45 model.compile(loss=avg_partial_likelihood,
46 optimizer=keras.optimizers.adam(lr=params['lr']),
---> 47 metrics=['accuracy'])
48
49 history = model.fit(x_train, y_train,
~\Anaconda3\lib\site-packages\keras\engine\training.py in compile(self, optimizer, loss, metrics, loss_weights, sample_weight_mode, weighted_metrics, target_tensors, **kwargs)
331 with K.name_scope(self.output_names[i] + '_loss'):
332 output_loss = weighted_loss(y_true, y_pred,
--> 333 sample_weight, mask)
334 if len(self.outputs) > 1:
335 self.metrics_tensors.append(output_loss)
~\Anaconda3\lib\site-packages\keras\engine\training_utils.py in weighted(y_true, y_pred, weights, mask)
401 """
402 # score_array has ndim >= 2
--> 403 score_array = fn(y_true, y_pred)
404 if mask is not None:
405 # Cast the mask to floatX to avoid float64 upcasting in Theano
<ipython-input-23-ed57799a1f9d> in avg_partial_likelihood(x_train, log_risk)
27
28 cph.fit(x_train, duration_col='survival_fu_combine', event_col='death',
---> 29 show_progress=False)
30
31 # obtain exp(hx)
~\Anaconda3\lib\site-packages\lifelines\fitters\coxph_fitter.py in fit(self, df, duration_col, event_col, show_progress, initial_beta, strata, step_size, weights_col)
90 """
91
---> 92 df = df.copy()
93
94 # Sort on time
AttributeError: 'Tensor' object has no attribute 'copy'
No one really mentions that somewhere in the code that
y_true=somethingandy_pred=something...
他们不提是因为您不需要这样做！实际上，在每次传递结束时（即一批前向传播），Keras 使用该传递模型的真实标签和预测来提供 y_true 和 y_pred。因此，您根本不需要在模型中定义 y_true 和 y_pred。只需使用后端函数（即 from keras import backend as K）定义你的损失函数，一切都会正常工作（永远不要在你的损失函数中使用 numpy）。要获得一个想法，请查看 built-in loss functions in Keras and see how they have been implemented. And here 是可用后端函数的（可能不完整）列表。