-
This is related to the issue of "differential cross sections", but loosely speaking (ignoring non-isotropic materials for now) one of the two variables (E,mu) is sampled and the other is used as a dif…
-
Hi, I am trying to evaluate the model trained on Cityscapes by running `python train_net.py --config-file configs/cityscapes/panoptic-segmentation/maskformer2_R50_bs16_90k.yaml --eval-only MODEL.WEIGH…
-
Currently random prime generation starts from a random number and runs a sieve until a prime is found. This can introduce bias, selecting primes with large leads more often. Some assorted consideratio…
-
I tried to test the script from scripts/cogvideox/fastercache_sample_cogvideox5b.sh, and the model is downloaded from https://huggingface.co/THUDM/CogVideoX1.5-5B-SAT/tree/main, but I got error as the…
-
Hi,
Thanks a lot for the excellent work. I'm trying your code out on a single view case where I want to enable the shadow visibility gradients. How can I do that in the code, i.e. how to reproduce …
-
D:\anaconda3.9\envs\zj\python.exe F:/1chen/DETR/jin/dn/DN-DETR/main.py
Not using distributed mode
[08/13 08:31:54.869]: git:
sha: a59a5de5bf784f196e15bffed3145d05d5a9126a, status: has uncommited …
-
Pose a question about one of the following articles:
“[Deep neural networks are more accurate than humans at detecting sexual orientation from facial images](https://psycnet.apa.org/doiLanding?doi…
-
Post your questions here about: “[The Datome - Finding, Wrangling and Encoding Everything as Data](https://docs.google.com/document/d/1vg-W55u3naN1gPmMyPhBWyIS8dJovdvlh6NUKMiFEjo/edit?usp=sharing)”, “…
-
## Instructions To Reproduce the Issue:
I attempted to train a mask-rcnn model with a custom dataset. I ran the following code.
```
import os
from detectron2.data.datasets import register_co…
-
### 🐛 Describe the bug
When using FSDP (Fully Sharded Data Parallel) to save a model, some parameters are not fully gathered on rank 0 and therefore not properly saved. This issue occurs specifical…