Pablo Villanueva Domingo
Pablo Villanueva Domingo
### Checklist - [X] I have searched for [similar issues](https://github.com/isl-org/Open3D-ML/issues). - [X] I have tested with the [latest development wheel](http://www.open3d.org/docs/latest/getting_started.html#development-version-pip). - [X] I have checked the [release documentation](http://www.open3d.org/docs/release/) and the...
I would like to use DeepSpeed for post-training compression with CUDA, using quantization or pruning. I'm using a pretrained ResNet as a simple example to test how DeepSpeed works, in...
Hi, I'm working with a Graph Neural Network which makes use of `scatter` from torch_scatter to aggregate the hidden features from the nodes of the full graph. During inference, I...
Hi, I tried to run `torch_cluster.radius_graph` in CUDA with bfloat16 data and I got the following error: ``` return torch.ops.torch_cluster.radius(x, y, ptr_x, ptr_y, r, ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
Is it possible to visualize evolution of loss using tensorboard when training with `Trainer()`? Thanks!
### 🐛 Bug I'm training a SAC policy in a Mujoco's Humanoid environment for some iterations. After finishing training, I save the model, to resume training later. However, when restarting...
### Bug description I can run once a training script with pytorch-lightning. However, after the training finishes, if train to run it again, the code freezes when the `L.Trainer` is...
In the `ue5-dev` branch, it is required to add a vertical offset of ~1m in the transform for spawning a pedestrian, otherwise there is a collision and it does not...
The following code is a simple script to spawn pedestrians, adding a controller to each one to walk around. While it works as expected in asynchronous mode, walkers are not...
I'm trying the [export html demo](https://github.com/medialab/ipysigma/blob/master/notebooks/Demo%20HTML%20Export.ipynb) without modifying these settings. The html is correctly generated and renders successfully. However, when I push the button to enter into fullscreen mode, the...