Time Series Data Encoding for Deep Learning, PyTorch (10.1)

Поділитися
Вставка
  • Опубліковано 25 жов 2023
  • Navigate the intricate landscape of PyTorch sequences with our comprehensive video guide. PyTorch, one of the leading deep learning frameworks, offers powerful tools to handle sequential data, a cornerstone for tasks ranging from time series analysis to natural language processing. In this tutorial, we'll break down the structure of PyTorch sequences, diving deep into tensors, shapes, and the various functions and modules designed for sequence processing. Whether you're a beginner aiming to get a clear grasp or a seasoned developer looking for a refresher, this video promises clarity, depth, and actionable insights.
    Code for This Video:
    github.com/jeffheaton/app_dee...
    ~~~~~~~~~~~~~~~ COURSE MATERIAL ~~~~~~~~~~~~~~~
    📖 Textbook - Coming soon
    😸🐙 GitHub - github.com/jeffheaton/app_dee...
    ▶️ Play List - • 2023 PyTorch Version A...
    🏫 WUSTL Course Site - sites.wustl.edu/jeffheaton/t8...
    ~~~~~~~~~~~~~~~ CONNECT ~~~~~~~~~~~~~~~
    🖥️ Website: www.heatonresearch.com/
    🐦 Twitter - / jeffheaton
    😸🐙 GitHub - github.com/jeffheaton
    📸 Instagram - / jeffheatondotcom
    🦾 Discord: / discord
    ▶️ Subscribe: ua-cam.com/users/heatonresea...
    ~~~~~~~~~~~~~~ SUPPORT ME 🙏~~~~~~~~~~~~~~
    🅿 Patreon - / jeffheaton
    🙏 Other Ways to Support (some free) - www.heatonresearch.com/suppor...
    ~~~~~~~~~~~~~~~~~~~~~~~~~~~~
    #PyTorch #Sequences #Tensors #DeepLearning #PyTorchBasics #SequentialData #NLP #TimeSeries #PyTorchTutorial #TensorShapes
  • Наука та технологія

КОМЕНТАРІ • 2

  • @maximinmaster7511
    @maximinmaster7511 8 місяців тому

    Thank you Jeff.

  • @pwdrhrn
    @pwdrhrn 5 місяців тому

    Hi Jeff, a couple of minor comments on the your notebook.
    at In [6] you say
    "Now we get to sequence format. We want to predict something over a sequence, so the data format needs to add a dimension. You must specify a maximum sequence length. The individual sequences can be of any size."
    But it's not obvious where you are specifying that dimension. I think you just mean that the data must have a 3rd dimension resulting in multiple rows. Also, you introduced a data element starting with 35 which seemed to just appear, possibly to make the data precess as you duplicate it from row to row. That wasn't super clear.