TANG Zhiye
TANG Zhiye
**Environment:** 1. Framework: (TensorFlow, Keras, PyTorch, MXNet) TensorFlow 2. Framework version: 1.14.0 3. Horovod version: 0.25.0 4. MPI version: 5. CUDA version: 6. NCCL version: 7. Python version: 3.6.6 8....
Try to this [webpages](https://github.com/tesseract-ocr/tessdata_fast) and this [one](https://github.com/tesseract-ocr/tessdata_best).
I'm using a conda-env with Py-38 and CUDA-11.7. When I was trying to install torch-points-kernels via neither conda nor build from source, it fails. In README seems a PyTorch >=...
Noticed that in `scene/__init__.py`, the class `Scene` receives a variable `load_iteration`, which seems to support fine-tuning. However, in the following lines: ```{Python} if self.loaded_iter: self.gaussians.load_ply(os.path.join(self.model_path, "point_cloud", "iteration_" + str(self.loaded_iter), "point_cloud.ply"))...
I've run the released code. During training, the anchors will be adjusted adaptively. However, the anchors in the generated PLY file can not be constructed as an octree because of...
The [BungeeNeRF dataset](https://github.com/city-super/BungeeNeRF?tab=readme-ov-file) is also a representative real-world, large-scale dataset for the NVS task. Many works in 3DGS compression have been evaluated on the BungeeNeRF dataset. Adding this dataset to...
According to the released code, `torchac` seems only to support 16-bit symbols (in fact, the number of effective bits is 15). I've made some attempts. However, the magic numbers in...