Tony Boston

icon indicating an email [email protected]

icon company Australian National University icon location Canberra, Australia

Results 4 issues of Tony Boston

Using a different backbone?

12 comment

My question is how to load weights from a custom backbone (not from the set already supported by qubvel segmentation_models)? I have trained ImageNet models such as ResNet50 for image...

RuntimeError: Given groups=1, weight of size [64, 11, 3, 3], expected input[1, 6 72, 672, 11] to have 11 channels, but got 672 channels instead

Running Demo.ipynb yields runtime error at line: prediction = torch.sigmoid(model(input_img)).data[0].cpu().numpy() RuntimeError: Given groups=1, weight of size [64, 11, 3, 3], expected input[1, 6 72, 672, 11] to have 11 channels,...

How to use WaterNet for other sat images

Hi Tim @treigerm, Thanks very much for your code - very well written and easy to understand. I have a similar question to @aasemaase. When I run waterNet it creates...

Is a scale_factor of 3 supported?

When I try either of the examples (poutyne_example.py or pytorch_lightning_example.py), they both fail when scale_factor is changed from 2 to 3 with this error: `pytorch_lightning_example.py:28: Using a target size (torch.Size([32,...