openclimatefix / metnet

PyTorch Implementation of Google Research's MetNet and MetNet-2
MIT License
237 stars 49 forks source link

It seems to be a very interesting project for weather forecasting, could you help me with the steps needed to run the system on my IDE, I am actually using vscode Ide. #52

Open Nagessen opened 1 year ago

Nagessen commented 1 year ago

Arxiv/Blog/Paper Link

Detailed Description

Context

jacobbieker commented 1 year ago

Hi,

A few questions:

  1. Have you setup a virtual environment or conda environment?
  2. Have you tried pip install metnet?
  3. What does your data look like?
Nagessen commented 1 year ago

Thanks for your response, Yes I have already set up a virtual environment and installed pip metnet on my ide,but for the data could you tell me how should i set it? and what should be done next.Thanks.

On Thu, May 11, 2023 at 4:24 PM Jacob Bieker @.***> wrote:

Hi,

A few questions:

  1. Have you setup a virtual environment or conda environment?
  2. Have you tried pip install metnet?
  3. What does your data look like?

— Reply to this email directly, view it on GitHub https://github.com/openclimatefix/metnet/issues/52#issuecomment-1543901188, or unsubscribe https://github.com/notifications/unsubscribe-auth/A7W2CFU2KB3MVNHQFK7XV33XFTK73ANCNFSM6AAAAAAX566DHA . You are receiving this because you authored the thread.Message ID: @.***>

jacobbieker commented 1 year ago

The data loading and format is more up to you. What MetNet takes is a series of multi-channel images, with the input being of the format [Batch, Channels, Timesteps, Width, Height], as long as that is the case, it should work getting the data into the model. How you organize the data that way is up to you, the MetNet and MetNet-2 papers have the ways they do it, which has worked for us before. But it depends on what you want to do.