我正在尝试实现我自己的成本函数，具体来说是下面的这个函数：
我知道这个问题在这个网站上已经被问过多次，我读到的答案通常是类似于下面的内容：
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)，然后就可以继续进行。没有人真正提到在代码中的某个地方y_true=something和y_pred=something。这是我必须在我的模型中指定的内容吗？
我的代码
我不确定我是否正确地使用.predict()来获取模型在训练过程中的运行预测：
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() # 第一层 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'])) # 第二层及以后 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'])) # 最后一层 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)到目前为止我的目标函数
‘log_risk’ 将是y_true，而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) # 获得exp(hx) cph_output = pd.DataFrame(cph.summary).T # 求和风险比 hazard_ratio_sum = cph_output.iloc[1,].sum() # -log(sum(exp(hxj))) neg_log_sum = -np.log(hazard_ratio_sum) # 正事件（死亡==1）的总和 sum_noncensored_events = (x_train.death==1).sum() # 负对数似然 neg_likelihood = -(log_risk + neg_log_sum)/sum_noncensored_events return neg_likelihood如果我尝试运行会出现的错误
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 timeAttributeError: 'Tensor' object has no attribute 'copy'回答：
