RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x3 and 2048x1000)

1

I am new to AI and python, I’m trying to build an architecture for inference but up till now, I couldn’t understand how to get the inputs and outputs correctly. I keep seeing the error:

RuntimeError: mat1 and mat2 shapes cannot be multiplied (1x3 and 2048x1000)

Any suggestions on how to resolve ?

class RN50(torch.nn.Module):

def __init__(self, rn50):
    super(RN50, self).__init__()
    self.avgpool = rn50.avgpool
    self.fc = rn50.fc

def forward(self, x):
    x = self.avgpool(x)
    x = torch.flatten(x, 1)
    x = self.fc(x)

    return x

def calibration(model_path):
    end_model=torch.jit.load(model_path)

    for i, (images, target) in enumerate(cal_loader):
       output = end_model(images) 

r50end = RN50(rn50)
x = torch.rand([112, 2048, 7, 7 ], dtype=torch.float32).contiguous()
with torch.no_grad():
    model = torch.jit.trace(r50end, x).eval()

model.save("rn50.pt")
calibration("rn50.pt")
2

This issue seems to be a duplicate (or at least very similar) to this topic you’ve created and I guess both issues can be solved with the same approach so let’s follow up in the other thread.