-
@Knight825 I also built csp resnet50 from ```csresnet.cfg``` file in ```https://github.com/WongKinYiu/CrossStagePartialNetworks``` repo. And i didn't know that is it correct. Could you help me to chec…
-
I am trying to implement Dynamic Samplers in Pytorch. This seems impossible with the existing train_loader api's. As the weighted the samplers only allow weights to be set once. I was thinking that we…
-
Hello, I've uploaded my code for training RAFT-Stereo with NeRF supervision: https://github.com/husheng12345/Unofficial-NeRF-Supervised-Deep-Stereo.
Despite my best efforts to replicate the experimen…
-
First of all, thanks for the interesting paper and code.
However, I am having problems reproducing the results reported in the paper.
I tried reproducing the results reported on the "I2B2 2006…
-
I change the renderer size from 256*256 to H*W and add focal to camera. But the output is all 1.0 in render_pkg["render"]
-
Hello,
I noticed that if I use vehicle models with the ChronoBaseEnv(), there is a memory leak in the vectorized environments. I have noticed this for the [offroad_gator.py](gym-chrono/gym_chrono/e…
-
I love the benchmarks by @faroit on audio read speeds. I too have tried a number of different libraries, and have generally been using scipy.io.wavfile.read() for its speed whenever possible, but sw…
-
### System Info
```Shell
- `Accelerate` version: 0.30.1
- Platform: Linux-5.4.0-144-generic-x86_64-with-glibc2.35
- `accelerate` bash location: /root/miniconda3/envs/qec/bin/accelerate
- Python ve…
-
@weifengpy @wanchaol
I've seen various mentions of `sequence parallel` (which I believe is subsumed by `tensor_parallel` per #162) training when searching through commits / PRs. Is there an "offi…
-
Hi! when I try to run a python [scripts](https://github.com/pytorch/PiPPy/blob/main/examples/llama/pippy_llama.py) for llm inference in pipeline parallelism on single server with multi GPUs. It turned…