Laurent Weingart

demo examples not working, ' terminated by signal SIGSEGV (Address boundary error)

9

Hello team, I just finished installing mmpose on a Jetson AGX Xavier and decided to run the demos, to verify that everything was working well. I first ran the example...

src/tcmalloc.cc:333] Attempt to free invalid pointer

6

Hello Guys, I have just successfully completed the build of openpose on my Mac, and I tried to run the example command you gave in some of your README, but...

Need a tiny bit of help to use custom caffemodel with detectNet

6

Dear dusty-nv, I'm not sure this falls under your duty but maybe you could still give me a hand ? I'm trying to use detectNet with a caffemodel and from...

Hi guys, I had a jetson AGX Xavier on which I developed an action recognition app using your torch2trt and trt_pose, and it worked well. This was in January 2021....

Error: batch_size should be a positive integer value, but got batch_size=0

1

Hello guys, Thank you very much for your work. I'm trying to train my model based on my own dataset, but when running the training command it always fails with...

Hi team, I would love to use your model to train a custom dataset, so I cloned the repo, setup the env with conda and added my dataset according to...

How to continue training from a checkpoint ?

2

Hello guys, Thank you very much for your work, it's amazing. I trained a low and high res model, but it was far from enough to get a good result....

video_object_detection.py issue

1

Hello, I simply cloned the repo and tried to run the video_objet_detection.py, but it directly fails with: ``` $ python3 video_object_detection.py Traceback (most recent call last): File "video_object_detection.py", line 4,...

Hi guys, I'm finally able to start the training, but I'm encountering these errors: ``` AssertionError: Recovering T5LayerNorm requires the original layer to be apex's Fused RMS Norm.Apex's fused norm...

Training gets a KeyError 'Height'

5

Hello guys, I just followed your precess to prepare my own dataset as described [here](https://github.com/hpcaitech/Open-Sora/blob/main/docs/data_processing.md) and I must admit it went impressively well, no error whatsoever. Then I went on...