基于字符级卷积神经网络的细粒度的中文情感分析以及具体的应用,将顾客打分和评论情感进行两极映射,使用数据自动标注和基于弱监督预训练的数据增强方式自动扩充和优化数据集,实验证实了在情感分类中,使用本文的字符级卷积神经网络(C-CNN-SA)可以在不依赖分词的情况下,达到的精度和 F 值均高于词级粒度。并将模型上线使用,利用tensoflow+flask restful做出的后端服务化,具体的项目细节和讲解看右面的ppt
- Updated
Jan 16, 2020 - HTML
TensorFlow is an open source library that was created by Google. It is used to design, build, and train deep learning models.
基于字符级卷积神经网络的细粒度的中文情感分析以及具体的应用,将顾客打分和评论情感进行两极映射,使用数据自动标注和基于弱监督预训练的数据增强方式自动扩充和优化数据集,实验证实了在情感分类中,使用本文的字符级卷积神经网络(C-CNN-SA)可以在不依赖分词的情况下,达到的精度和 F 值均高于词级粒度。并将模型上线使用,利用tensoflow+flask restful做出的后端服务化,具体的项目细节和讲解看右面的ppt
Image Classification Web Appl built using Tensorflow.js & Google Cloud AutoML Vision.
Sentiment Analysis Projects
Little example of TensorFlowJS using a pre loaded Artificial Neural Network (ANN). 🧠
Final Thesis Dissertation in Fulfillment of our Bachelor of Science in Engineering (B.Sc.Engg) with major in Computer Science and Engineering. This research is entitled *Optimized Human-Emotion Detection in Written-Text using Hybrid Machine Learning Classification Algorithm*, with codename *OEHML* Framework.
Tensorflow introduction (predictions, classification) from webcam
Created by Google Brain Team
Released November 9, 2015