oft
oft copied to clipboard
tom-roddick
The Kitti path in readme.md was 'data/kitti/objects' where in the dataloader code is 'data/kitti/object' The letter 's' was removed from 'objects'
In the paper, you said "We use the same scale factor σ as described in Section 3.4 to normalize the position offsets within a sensible range". But in your code...
running OFT gets me the following warnings: torch/nn/functional.py:3828: UserWarning: Default grid_sample and affine_grid behavior has changed to align_corners=False since 1.3.0. Please specify align_corners=True if the old behavior is desired. See...
Hello @tom-roddick, Are you going to provide some pre-trained model?
Hi Tom, first of all, thanks for updating the repo and providing the inference script. However, there seems to be an issue now with the heatmap based scores during training....
Would changing the number of classes in the model compile from 1 automatically retrieve the labels for the other classes, or the code for label preparation would also need changing?
Why only use x coordinate of projection of an object's position to determine visible when doing random_crop?
In the paper you said "The model is trained using SGD for 600 epochs with a batch size of 8, momentum of 0.9 and learning rate of 10−7". Why we...
