DeepSpeed + Accelerate ↗
An unfinished outline on integrating DeepSpeed with Accelerate.
Notes & explorations.
Ideas and engineering notes on models, memory, and perception. Older entries reflect what I was exploring at the time.
Memory Definition in LLM Applications ↗
Notes on personalized models, long-term memory, and the representation of individual experience.
Seq2seq Model with Attention ↗
Sequence-to-sequence models are deep learning models that have achieved a lot of success in tasks like machine translation, text summarization, and image captioning.
How to remotely edit your project without having to use VIM ↗
Remotely editing your work when your server does not have public IP address and you don't want to spend any money is not so easy. Maybe you can use Team viewer or Anydesk or even chrome remote desktop, but ther
You only look once (YOLO) -- (2) ↗
YOLO has higher localization errors and the recall (measure how good to locate all objects) is lower, compared to SSD. YOLOv2 is the second version of the YOLO with the objective of improving the accuracy signi
Pooling Layer in CNN (1) ↗
Today I didn't have the mood to continue my work on map merging of different cameras. So I read the paper from DeepMind of Learned Deformation Stability in Convolutional Neural Networks recommended by Wang Chen
SVO相关问题 ↗
Engineering notes on SVO, ORB-SLAM, depth estimation, and VIO drift.