visualise model Summary

[waqarsqureshi]

I like to know how can I use the pytorch info to get a summary of the model

import tensorboard
from torchinfo import summary
model = create_model(
        'swinv2_base_window12to24_192to384_22kft1k',
        pretrained=False, 
        num_classes=10
        )
summary(model,(3, 384, 384))

I want to print the summary

[waqarsqureshi]

something on this lines i want

https://paperswithcode.com/lib/timm/resnet#

[klae01]

More details are included in the code in the following article: https://androidkt.com/visualize-pytorch-model-graph-with-tensorboard/

short summary:

from torch.utils.tensorboard import SummaryWriter
writer=SummaryWriter()
writer.add_graph(model, torch.randn(1, 3, 384, 384))

[waqarsqureshi]

from torch.utils.tensorboard import SummaryWriter writer=SummaryWriter() img = PIL.Image.open('test9.jpg') img_tensor = transforms(img).unsqueeze(0).to(device) writer.add_graph(model, img_tensor)

Yes it worked, I had to change the input dimension though. Thanks