[ <<< Lição 1 | Lição 3 >>> ]
Lesson 2: Deeper Dive into Computer Vision (30/10/2019 - UnB - Brasília)
Este tópico permite que os membros do Grupo de IA da UnB (Brasília) estudem coletivamente (em reuniões presenciais e on-line) a lição 2 (parte 1) do curso fastai, mas de um jeito aberto para ajudar também pelas questões, respostas e pelos recursos publicados todos os leitores em português interessados em DL.
Lesson resources
- Lesson 2 official resources and updates
- Lesson 2 chat
- Lesson 2: further discussion
- Notebooks:
- Detailed lesson notes - thanks to @hiromi
- Lesson notes - thanks to @PoonamV
- Lesson 2 in-class discussion
- Links to different parts in the video - thanks to @melonkernel
Other resources
- How (and why) to create a good validation set by @rachel
- There’s no such thing as “not a math person” by @rachel
- Responder - a web app framework built on top of Starlette
- Post about an alternative image downloader/cleaner by @cwerner
- A tool for excluding irrelevant images from Google Image Search results by @melonkernel
- Machine Learning is Fun - source of image/number GIF animation shown in lesson
- A systematic study of the class imbalance problem in convolutional neural networks , mentioned by @jeremy as a way to solve imbalanced datasets.
- Gradient descent in images
- Medium article about how to put your model into production
- Using the fastai Data Block API