0

我使用 Roberta 模型编写了包含两个类的文本分类代码，现在我想绘制混淆矩阵。如何根据罗伯塔模型绘制混淆矩阵？

RobertaTokenizer = RobertaTokenizer.from_pretrained('roberta-base',do_lower_case=False)
roberta_model = TFRobertaForSequenceClassification.from_pretrained('roberta-base',num_labels=2)

input_ids=[]
attention_masks=[]

for sent in sentences:
    bert_inp=RobertaTokenizer.encode_plus(sent,add_special_tokens = True,max_length =128,pad_to_max_length = True,return_attention_mask = True)
    input_ids.append(bert_inp['input_ids'])
    attention_masks.append(bert_inp['attention_mask'])
    

input_ids=np.asarray(input_ids)
attention_masks=np.array(attention_masks)
labels=np.array(labels)
#split
train_inp,val_inp,train_label,val_label,train_mask,val_mask=train_test_split(input_ids,labels,attention_masks,test_size=0.5)
print('Train inp shape {} Val input shape {}\nTrain label shape {} Val label shape {}\nTrain attention mask shape {} Val attention mask shape {}'.format(train_inp.shape,val_inp.shape,train_label.shape,val_label.shape,train_mask.shape,val_mask.shape))
#
log_dir='tensorboard_data/tb_roberta'
model_save_path='/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/callbacks.py'

callbacks = [tf.keras.callbacks.ModelCheckpoint(filepath=model_save_path,save_weights_only=True,monitor='val_loss',mode='min',save_best_only=True),keras.callbacks.TensorBoard(log_dir=log_dir)]

print('\nBert Model',roberta_model.summary())

loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
metric = tf.keras.metrics.SparseCategoricalAccuracy('accuracy')
optimizer = tf.keras.optimizers.Adam(learning_rate=2e-5,epsilon=1e-08)

roberta_model.compile(loss=loss,optimizer=optimizer,metrics=[metric])

history=roberta_model.fit([train_inp,train_mask],train_label,batch_size=16,epochs=2,validation_data=([val_inp,val_mask],val_label),callbacks=callbacks)
4

1 回答 1

0 
trained_model = TFRobertaForSequenceClassification.from_pretrained('roberta-base',num_labels=2)
trained_model.compile(loss=loss,optimizer=optimizer, metrics=[metric])
trained_model.load_weights(model_save_path)    
preds = trained_model.predict([val_inp,val_mask],batch_size=16)
    pred_labels = np.argmax(preds.logits, axis=1)
    conf_matrix = confusion_matrix(labels2,pred_labels)
    print('conf_matrix ',conf_matrix)
    
    fig, ax = plt.subplots(figsize=(7.5, 7.5))
    ax.matshow(conf_matrix, cmap=plt.cm.Blues, alpha=0.3)
    for i in range(conf_matrix.shape[0]):
        for j in range(conf_matrix.shape[1]):
            ax.text(x=j, y=i,s=conf_matrix[i, j], va='center', ha='center', size='xx-large')
     
    plt.xlabel('Predictions', fontsize=18)
    plt.ylabel('Actuals', fontsize=18)
    plt.title('Confusion Matrix(without preprocessing)', fontsize=18)
    plt.show()
于 2021-07-27T10:41:39.840 回答