Matheus Correia Ferreira
Matheus Correia Ferreira
I'm trying to fine-tune a Mask2Former segmentor with a custom dataset by using MMSEGMENTATION plus the code made available in this repository. However, I'm running into some trouble because of...
In the recently released [segmentation notebook](https://github.com/facebookresearch/dinov2/blob/main/notebooks/semantic_segmentation.ipynb), a trained Mask2Former segmenter is loaded. In its strucutre, it's possible to see a ViT-Adapter is used as a backbone and not a standard...
I'm pretty sure it's not currently possible to train the SETR segmenter while freezing the weights of the backbone. So has anyone implemented such a feature? I'm trying to run...
I've got a few segmentation datasets that have the structure below, with all folders being filled with .png files. ``` dataset/ images/ /train /val /test annotations/ /train /val /test ```...
Has anyone, by any chance, ever implemented code that allows MMSEGMENTATION to train with NPY files rather than images? I've got really large datasets (which are all larger than a...
I am installing mmsegmentation on a sif image exactly as it is recommended on this official [Dockerfile](https://github.com/open-mmlab/mmsegmentation/blob/main/docker/Dockerfile). The only big difference is that I am using an Nvidia base image....
I need to train a segmentor that uses a Transformer that has been pre-trained with `patch_size=14`. I've done some adaptations in the `ViT-Adapter/segmentation/mmseg_custom/models/backbones/vit_adapter.py` file to allow for that, since at...
I am trying to run a basic training script with the ADE20K dataset via the following command: `python tools/train.py configs/SETR/SETR_PUP_DeiT_512x512_160k_ade20k_bs_16_MS.py` And I am running into this error: `ImportError: cannot import...
# ❓ Questions and Help Is there a way to install Xformers with CUDA 12? I'm trying to use Xformers on a Singularity image that employs, as a base, an...