Single Shot Detection (SSD) - Lite Version SSDLite is widely used to demonstrate a new backbone's detection capability. It was first introduced in MobileNetV2. 2022-05-12 Machine learning Deep learning detection SSDLite
The evolution of DeepLab semantic segmentation system Deep labelling (DeepLab) is one of the most popular tricks to improve semantic segmentation performance. It may be the most accepted method to improve your proposed method performance. 2022-05-11 Machine learning Deep learning deepLab semantic segmentation
hexo 博客創建和模板 Dave經過一年多博客的撰寫營運，積累了一些寫hexo博客的技巧，並且有自己的一套模板，這裡分享一下。 2022-04-24 HTML blogs generation template
how to solve "pdf unsupported data" It is stupid that printer print an blank paper with "pdf unsupported data". Actually, we can avoid the problem by formatting the pdf files. 2022-04-24 Others pdf printer format
Active learning can select the data it wants Active learning is a subfield of artificial intelligence. It is curious to select the data which it learns during training. 2022-04-20 Machine learning Deep learning review meta learning active learning
Towards giving lab sessions - class review Teaching a lab session not only need our professional knowledge, but also you need to know how to guide your students properly. 2022-04-15 Scientific Research/科研 scientific research graduate school teaching assistant
Towards giving lectures - class review Teaching is one of my favourite things and hobbies. Luckily, I have a chance to learn the fundamental theories about teaching students. 2022-04-15 Scientific Research/科研 scientific research graduate school teaching assistant
A note taking for meta learning Meta learning, or learning to learn, has seen a dramatic rise in interest in recent years. Someone says the development of artificial intelligence is, machine learning -> deep learning -> deep reinfor 2022-04-04 Machine learning Deep learning review meta learning
What are the differences between model.tran() and model.eval() The model.train() and model.eval() are the setting for network tuning on PyTorch. Someone may ask why do we need them for a same network? 2022-04-02 Machine learning Deep learning pytorch
Multimodal in deep learning Mountains of forms can represent information. For instance, someone who has a headache can be shown by medical instruction text, CT, face expression image, body temperature, etc. With some of this com 2022-03-22 Machine learning Deep learning multimodal
