classifier-multi-label icon indicating copy to clipboard operation
classifier-multi-label copied to clipboard

多标签文本分类,多标签分类,文本分类, multi-label, classifier, text classification, BERT, seq2seq,attention, multi-label-classification

Results 12 classifier-multi-label issues
Sort by recently updated
recently updated
newest added

classifier_multi_label_textcnn 显示没有,这个是什么问题

tf1 版本转tf2问题,当不添加textcnn网络时,训练预测均没有问题。但是当加入textcnn时训练时loss与acc都不错,但是预测都是错误的。以下tf2实现的textcnn基本都是直接转的。此外我还尝试tf.keras.layers.Conv2D()以及conv1d实现。但是效果都不行,本来考虑是不是训练周期等参数问题,但是跟您的项目参数保持一致,训练出来的模型就是有问题(有进行dropout),所以想请教一下您。 ```Python def textcnn(x): pooled_outputs = [] filter_sizes = [2, 3, 4, 5, 6, 7] inputs_expand = tf.expand_dims(x, -1) for filter_size in filter_sizes: filter_shape = [filter_size, 312, 1, 128]...

训练结束后predict.py脚本获取不到标签问题 知乎上也有很多人说predict.py脚本获取到的标签为空,其实不是训练数据有问题或者轮次不够,作者的get_label 函数逻辑有一些小小的问题,我这里简单修改了一下,可以成功获取到标签,新的predict.py 的get_label 函数如下: ``` def get_label(sentence): """ Prediction of the sentence's label. """ feature = get_feature_test(sentence) fd = {MODEL.albert.input_ids: [feature[0]], MODEL.albert.input_masks: [feature[1]], MODEL.albert.segment_ids:[feature[2]], } prediction = MODEL.sess.run(MODEL.albert.predictions, feed_dict=fd)[0]...

from tensorflow.contrib import tpu as contrib_tpu ModuleNotFoundError: No module named 'tensorflow.contrib'

Traceback (most recent call last): File "predict.py", line 43, in MODEL = ModelAlbertTextCNN() File "predict.py", line 26, in __init__ self.albert, self.sess = self.load_model() File "predict.py", line 39, in load_model saver.restore(sess,...

您好,能分享下最后版本的requirements.txt吗? 看了您的知乎文章,tf=1.14.0,但是安装了之后依旧报错,如题。

May I ask if there will be a related version of pytorch released in the future?

大佬有尝试使用大模型解决类似问题么,例如开源的百川&chatglm等

Failed to find any matching files for /root/autodl-tmp/classifier_multi_label/albert_small_zh_google/albert_model.ckpt,您好,请问这个albert_model.ckpt文件是需要自己添加吗