Sarah Hannah Alves

Hi, in another sentence: do you plan train cm3 from scratch as in the paper?

Hi! I've been having the same problem. I did a workaround as others to set just one gpu, although there's 2 available. Could you help me out on how to...

Hi! I think I might have miss something on the math, but isn’t the V and S matriz de clause matrix? You mean the difficulty because they’re not ternary?

I'm having this error when running pip install or build or python install. Does anyone has any idea? cuda_11.2.r11.2 Python 3.7.9 tensorflow '2.10.0' torch '1.11.0+cu113' 

> It's mostly the path/lib problem for the NVCC toolchain on Windows. To try the package, I recommend using it on [Google Colab](https://colab.research.google.com/drive/1dRfepPLEE8N6BBZhXz8bbLDcPnRKaOcJ#forceEdit=true&offline=true&sandboxMode=true). If there is a necessity to run...

The exact same command that is suggested on the readme file. The fist command. python main.py \ --dataset nyuv2 \ --dataset-path ./datasets/nyuv2 \ --tasks semantic scene instance orientation \ --enable-panoptic...

same here.

Hi! Great work! Tks for sharing it all! believe it's hard to keep it all on track, but I have the same issue previous fellows. I tried to extract commands...

> When building realtime-img2img demo I added the following two lines to requirements.txt > > numpy==1.26.4 huggingface_hub==0.25.2 > > Prevents numpy 2 and latest version of huggingface_hub from being pulled...

Additionally, I'm trying to run the experiments with the readme commands, and it seems to need the datasets shard files for instance: train_shards: "/home/ubuntu/movi_e/train/shard-{000000..000679}.tar" train_size: 9749 val_shards: "/home/ubuntu/movi_e/val/shard-{000000..000017}.tar" val_size: 250...