search

lucidrains / metnet3-pytorch

Implementation of MetNet-3, SOTA neural weather model out of Google Deepmind, in Pytorch
MIT License
202 stars 26 forks source link

Kernel process dies while running #4

Open Processoriented opened 9 months ago

Processoriented commented 9 months ago

Hi @lucidrains,

I'm trying to run the snipit from your README on my local machine, and every time it is crashing my kernel with the following as the last line in the console:

19:55:21.658 [error] Disposing session as kernel process died ExitCode: undefined, Reason: 0.00s - Debugger warning: It seems that frozen modules are being used

it seems that the Kernel dies on the following statement:

total_loss, loss_breakdown = metnet3(
    lead_times = lead_times,
    hrrr_input_2496 = hrrr_input_2496,
    hrrr_stale_state = hrrr_stale_state,
    input_2496 = input_2496,
    input_4996 = input_4996,
    precipitation_targets = precipitation_targets,
    surface_targets = surface_targets,
    hrrr_target = hrrr_target
)

Any recommendations on what to try next?

Thanks in advance.

Vincent

Makada-cyber commented 1 month ago

Wrap the call to metnet3 in a try-except block to catch any exceptions that might provide more insight: python Copy code try: total_loss, loss_breakdown = metnet3( lead_times=lead_times, hrrr_input_2496=hrrr_input_2496, hrrr_stale_state=hrrr_stale_state, input_2496=input_2496, input_4996=input_4996, precipitation_targets=precipitation_targets, surface_targets=surface_targets, hrrr_target=hrrr_target ) except Exception as e: print(f"An error occurred: {e}")