PyTorch_Learning

learning pytorch step by step

the repo contains the following parts:

1. pytorch tensor learning
2. pytorch linear regression
3. CV pretrained model usage
4. MLP Model for binary classification
5. MLP Model for multi classification
6. CNN model for MNIST
7. CNN model for digital captcha recognition
8. CNN model for variable length math operation captcha recognition
9. Bi-LSTM CRF Model for Chinese Named Entity Recognize
10. HuggingFace Transformers NLP tasks learning

• language model
• multiclass text classification
• English named entity recognition
• Chinese named entity recognition

11. onnx model serving:

• official SSD model
• IRIS dataset MLP multiclass classification Model
• captcha recognition CNN Model
• transformers BERT text classification Model

12. HuggingFace Learning, include Datasets, Trainer, BERT dynamic quantization

references:

1. PyTorch Tutorial: How to Develop Deep Learning Models with Python: https://machinelearningmastery.com/pytorch-tutorial-develop-deep-learning-models/
2. Named Entity Recognition (NER) using BiLSTM CRF: https://github.com/Gxzzz/BiLSTM-CRF
3. transformers 示例教程: http://pytorchchina.com/2020/03/04/transformers-示例教程/
4. 手把手教你用Pytorch-Transformers——实战（二）: https://www.cnblogs.com/dogecheng/p/11911909.html
5. transformers_ner: https://colab.research.google.com/github/abhimishra91/transformers-tutorials/blob/master/transformers_ner.ipynb
6. Datasets: https://www.huaxiaozhuan.com/%E5%B7%A5%E5%85%B7/huggingface_transformer/chapters/2_datasets.html
7. Huggingface详细入门介绍之dataset库：https://zhuanlan.zhihu.com/p/554678463
8. Stream: https://huggingface.co/docs/datasets/stream
9. HuggingFace教程 Datasets基本操作: Process: https://zhuanlan.zhihu.com/p/557032513
10. Introduction to Quantization on PyTorch
11. DYNAMIC QUANTIZATION ON BERT
12. RFC-0019-Extending-PyTorch-Quantization-to-Custom-Backends