JLC

I am having trouble training on my own images (Synthetic aperture radar images). It seems the training loss is going down but evaluation loss on a test dataset is increasing...

## Summary of the bug Building the docker or creating the conda environment given the .yml file on ubuntu the installation hangs. ## Steps to reproduce the bug ``` conda...

Larger error for MNIST MLP baseline supervised compared to paper's results

4

Hello, I did not find if anyone tried this TF version of the ladder network fully supervised to compare with the paper's baseline MLP result from table 1 so I...

What do output values/coordinates from the model represent?

1

I am confused about what the model should be outputting by the model here: https://github.com/eriklindernoren/PyTorch-YOLOv3/blob/47b7c912877ca69db35b8af3a38d6522681b3bb3/detect.py#L77 I would expect coordinates [0,1] representing the center of the object, but the values are...

What is the difference for the two options for the swav backbone? What is the use case for choosing obj_embedding_head = "head" or "intermediate"?

I want to replicate the office and visda models on pretrained imagenet features; is that code available? Thank you.

Hi, It's unclear to me if you evaluated the original classification model (teacher model) with the data it was trained on? I assume an attacker would want to attack the...