After loading the saved ann2snn converted model, it cannot load tensors with time dimension #602
Unanswered
gwgknudayanga
asked this question in
Q&A
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
Uh oh!
There was an error while loading. Please reload this page.
-
I saved the ann2snn converted model as follows.
model_converter = ann2snn.Converter(mode='max', dataloader=train_loader)
snn_model = model_converter(net)
functional.set_step_mode(net, step_mode='m')
torch.save(snn_model, 'converted_snn_model_3.42Quant_new.pth')
After saving, i loaded the model as follows.
net = torch.load('converted_snn_model_3.42Quant_new.pth')
but when i tried to load input (5,8,3,32,32) (which is first dimesion is time, second dimension is batch, third is channel and so on.)
it says model expect 3 or 4 dimesional input. Is there a issue about the way i saved or saved ?
Beta Was this translation helpful? Give feedback.
All reactions