Ruslan Rakhimov
Ruslan Rakhimov
first of all, thx for implementation! the question is about proper masking inside the model 1. shift_down and shift right in the beginning of PixelSnail module have already taken care...
Hello, first of all, thanks for the beautiful implementation! However, certain things seem to be buggy. Please correct me if I am wrong: ### Problem 1. `NDCGridRaysampler` does not work...
Hi! First of all, thank you for sharing code! Could you, please, say what heatmap size is actually used for densepose task: 64 or 128? I have not found that...
Hi! Thanks for your work! I would like to run the pretrained model on a single image without downloading any datasets to get the landmarks prediction. Unfortunately I did not...
Hi! Thank you for your work! In the equation (9) in the paper: `\tilde{\alpha}(z_0,z_1)=\frac{t(z_1)-t(z_0)}{1-t(z_0)}` the denominator = `1-t(z_0)` While in [code](https://github.com/liuyuan-pal/NeuRay/blob/main/network/dist_decoder.py#L139): `alpha_value = torch.log(hit_prob / (visibility - hit_prob + eps)...
## What this does This pull request introduces a custom `DataLoader` class, `MultiEpochsDataLoader`, along with a supporting sampler class, `_RepeatSampler`, to address the issue of lag when obtaining the first...
### System Info ```Shell - `lerobot` version: 0.1.0 - Platform: Linux-6.5.0-41-generic-x86_64-with-glibc2.35 - Python version: 3.10.14 - Huggingface_hub version: 0.23.4 - Dataset version: 2.20.0 - Numpy version: 1.26.4 - PyTorch version...
Hello! Thank you for your work. I met a problem with reading of certain encoding. The video ffmpeg encoding information: ``` "vcodec": "libsvtav1", "pix_fmt": "yuv420p", "g": 2, "crf": 30 ```...