Maybe I'm not understanding something but with the following code summary throws an error:
import torch
from torchvision import models
from torchsummary import summary
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
model = models.segmentation.deeplabv3_resnet50(pretrained=True).eval().to(device)
summary(model, (3, 224, 224))
Actual:
Throws 'collections.OrderedDict' object has no attribute 'size'
Expected:
Show the architecture