-
I wanted to turn training in depth, so I tried to turn it by typing this bash in gmflow_scale1_train.sh in colab as an example.
`!CHECKPOINT_DIR=checkpoints_flow/chairs-gmflow-scale1 && \
mkdir …
-
I want to reproduce the results of Figure 4 in the paper, segmenting unannotated categories in the dataset.
Do i need to modify the cfg file and then train from scratch, or i can use the model weight…
-
Hi Jonas! This is a fantastic job.
When I train on the scannet dataset, I met a problem about the dataset prepare module. In semseg.py line 194, when the code runs to "self._labels = self._select_c…
-
Hi authors!
Thank you for releasing this amazing work!
# What I did
I'm trying to use the pretrained weight for a quick demo of ScanNet val (lightweight). I've downloaded the pretrained checkpoin…
-
It seems that there is something wrong in the multi-GPU process when I run the code. It exits in 660 epochs when I run scannet 4 dataset, and it exits in 300 epochs when I run scannet 1 dataset.
``…
-
Dear Authors,
Thanks for this amazing work!
There is a quick question that I did not directly find Chamfer distance computation in your evaluation py files, could you give me some guidance on t…
-
Hi @nihalsid, this is really interesting work!
In the paper, you have provided the aggregated IoU/PQ/SQ/RQ metrics for the datasets. Can you please also provide the metrics you obtained on each of…
-
Thanks for this great repo! One question: do you consider incorporating works in the interactive segmentation domain? In my opinion, interactive segmentation models are trained in a class-agnostic man…
-
after i run: python2 reader.py --filename ~/data/ScanNet/scannet/scans/scene0024_00/scene0024_00.sens --output_path ~/data/ScanNet/objnerf/ --export_depth_images --export_color_images --export_poses -…
-
Hi, thanks for your interesting work!
I'm wondering how you got captions' corresponding point indices, in other words, how did you get these pickle files(e.g.,scannetv2_entity_vit-gpt2_matching_idx.p…