Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
- The best way to deal with different sized images is to downscale them to match dimensions from the smallest image available.
Convolutional Neural Networks
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
CS231n: Convolutional Neural Networks for Visual Recognition is a great introduction of CNN.
References
http://vision.stanford.edu/teaching/cs231n/
Handle Imbalanced Data in Machine Learning
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
scikit-learn-contrib/imbalanced-learn is a Python Package to Tackle the Curse of Imbalanced Datasets in Machine Learning.
Type of Imbalanced Data
- Intrinsic (imbalance is a direct result of the nature of the …
Tips on LSTM
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
http://colah.github.io/posts/2015-08-Understanding-LSTMs/
POS Tagging in NLP
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
https://nlpoverview.com/#a-pos-tagging
Andor et al. (2016) showed a transition-based approach that produces competitive result with a simple feed-forward neural network.
The GPT-2 Model in NLP
Things on this page are fragmentary and immature notes/thoughts of the author. Please read with your own judgement!
Code for the paper "Language Models are Unsupervised Multitask Learners"
The project huggingface/transfomer has implementation of transfomer based modles (such as GPT-2 ) .
References
https://openai …