变量是自我解释的：

def f1_weighted(true, pred): #shapes (batch, 4)

    #for metrics include these two lines, for loss, don't include them
    #these are meant to round 'pred' to exactly zeros and ones
    #predLabels = K.argmax(pred, axis=-1)
    #pred = K.one_hot(predLabels, 4) 

    ground_positives = K.sum(true, axis=0) + K.epsilon()       # = TP + FN
    pred_positives = K.sum(pred, axis=0) + K.epsilon()         # = TP + FP
    true_positives = K.sum(true * pred, axis=0) + K.epsilon()  # = TP
        #all with shape (4,)
    
    precision = true_positives / pred_positives 
    recall = true_positives / ground_positives
        #both = 1 if ground_positives == 0 or pred_positives == 0
        #shape (4,)

    f1 = 2 * (precision * recall) / (precision + recall + K.epsilon())
        #still with shape (4,)

    weighted_f1 = f1 * ground_positives / K.sum(ground_positives) 
    weighted_f1 = K.sum(weighted_f1)

    
    return 1 - weighted_f1 #for metrics, return only 'weighted_f1'

字符串

重要提示：

这种损失将分批工作（如任何Keras损失）。
因此，如果您使用小批量，则每个批次之间的结果将不稳定，并且您可能会得到一个坏结果。使用大批量，足以包括所有类别的大量样本。
由于这种损失会导致批量大小崩溃，因此您将无法使用某些依赖于批量大小的Keras功能，例如样本权重。

我创建了自定义weigted_f1函数，并在model.compile（）过程中将其传递到“metrics =”中。
请参见函数和模型.compile（）

def f1_weighted(true, pred): #shapes (batch, 4)

    #for metrics include these two lines, for loss, don't include them
    #these are meant to round 'pred' to exactly zeros and ones
    #predLabels = K.argmax(pred, axis=-1)
    #pred = K.one_hot(predLabels, 4) 

    ground_positives = K.sum(true, axis=0) + K.epsilon()       # = TP + FN
    pred_positives = K.sum(pred, axis=0) + K.epsilon()         # = TP + FP
    true_positives = K.sum(true * pred, axis=0) + K.epsilon()  # = TP
        #all with shape (4,)
    
    precision = true_positives / pred_positives 
    recall = true_positives / ground_positives
        #both = 1 if ground_positives == 0 or pred_positives == 0
        #shape (4,)

    f1 = 2 * (precision * recall) / (precision + recall + K.epsilon())
        #still with shape (4,)

    weighted_f1 = f1 * ground_positives / (K.sum(ground_positives) + K.epsilon())
    weighted_f1 = K.sum(weighted_f1)

    return weighted_f1 #for metrics, return only 'weighted_f1'

字符串
model.compile如下：

vocab_size = len(tokenizer.word_index) + 1

# build model
model = Sequential()
model.add(Embedding(input_dim=vocab_size, # Size of the vocabulary
                    output_dim=50, # Length of the vector for each word
                    input_length = MAX_SEQUENCE_LENGTH)) # Maximum length of a sequence
model.add(SpatialDropout1D(0.5))
model.add(LSTM(50, dropout=0.5, recurrent_dropout=0.5))
model.add(Dense(25,input_shape=y_train.shape, activation='softmax'))
model.add(Dropout(0.2))
model.add(Dense(20, activation='softmax'))
model.add(Dropout(0.2))
model.add(Dense(num_top_labels,activation='softmax'))
#model.add(Dense(1))
model.compile(loss = 'categorical_crossentropy', 
              optimizer=Adam(learning_rate=0.001), 
              metrics=['f1_weighted'])

print(model.summary())

型
在此之后，当我运行model.fit时，我得到ValueError：未知度量函数：'f1_weighted'

history = model.fit(X_train, y_train, 
                    class_weight=class_weights, # fix class imbalance
                    epochs = 5, 
                    batch_size=batch_size, 
                    #validation_split=0.2,
                    validation_data=(X_test, y_test), 
                    callbacks=[
                      EarlyStopping(monitor = "val_loss", patience = 10, restore_best_weights = True),
                       ReduceLROnPlateau(monitor='val_loss', factor=0.2, patience=2, mode='min') 
                    ]
                   )

型
请帮助我调试此错误。基本上，我想在每个时期之后绘制/跟踪训练和验证f1分数