Pieris Kalligeros
Pieris Kalligeros
Hey Nick, **TL;DR** 1. Any ideas for better input features than HKS with code available? 2. How many epochs did you train the pre-trained models for to get such good...
I cannot access the files on Dropbox (error message is "link temporarily disabled") and the Baidu Linux client is not working. Could you provide an alternative way to access the...
Hey again Nazir, I'm trying to use the end-to-end RbA architecture (Mask2Former architecture with semantic segmentation heads, class/mask matcher etc.), outside of the detectron2 framework, because it's causing me some...
Hey again Nazir, sorry for double posting on the Issues. I have a couple of questions about OOD Finetuning: 1. Do outlier masks need to have a specific value for...
Hey Nazir, Quick questions: 1. Are all the trained models in the RbA Model Zoo using (trained on) only the 19 STUFF classes (semantic segmentation) defined in the `mask2former/datasets/data/register_cityscapes_partial.py` file?...
Hey Nazir, Yet another question. In Fig. 4 of your paper you cluster the logits using a K-means clustering (with k=4 if I follow correctly). In the code I couldn't...
Hey Nazir, thank you for your exciting research and work on RbA! I'm trying to potentially run the model for multiple images/frames in a directory in batches. I noticed that...
### Describe the bug Similar to #3787, but also when running `xtts_v2` model with voice cloning (vocoder model), using `device='cpu'` results to the following error: ``` RuntimeError: CUDA error: CUBLAS_STATUS_NOT_INITIALIZED...
### What happened? ### Reproduction steps 1. ran `conda env create -f ./environment.yml` (file is from [here](https://github.com/nmwsharp/diffusion-net/blob/master/environment.yml)) this failed with output: ``` CondaValueError: prefix already exists: /root/miniconda3 ``` 1. I...
Hey Nazir, I have a question about the modified part of Pixel Decoder. I'm trying to navigate the code to understand what you changed from the Mask2Former architecture to only...