rvandeghen
rvandeghen
### 🐛 Describe the bug Since we have `multiscale` and `lsj` augmentations which use fix sizes, we no longer resize the images in the transforms of `GeneralizedRCNNTransform`. However, we still...
Hello, I'm using EffNets as backbones of EffDets and I'm facing issues with batch sizes and BatchNorm layers due to memory consumptions of large models. To counter that problem I've...
Hello, I'm using your code and i managed to understand almost everything expect this line: `regression_loss = torch.where( torch.le(regression_diff, 1.0 / 9.0), 0.5 * 9.0 * torch.pow(regression_diff, 2), regression_diff -...
### Describe the question. Hi, I would like to use DALI to extract frames at a rate of 2 FPS, while the original videos are encoded at 25 FPS. Note,...
### Describe the question. Hi, I would like to know how I can create 2 pipelines with 2 different sources, and use them in the same dataloader using `DALIGenericIterator`, or...
### Describe the question. Hello, I was wondering if there is a way to obtain the motion vectors you compute when you decode a video on GPU? Thanks ### Check...
Hello, Are you interested to have an implementation of 3D Convex Splatting ([paper](https://arxiv.org/abs/2411.14974), [project page](https://convexsplatting.github.io/)) to gsplat ? Renaud