-
Hi,
Is Kymatio able to work with complex signals, given that the wavelets are already analytic wavelets. Essentially, the constant-Q fitlers banks need to cover the whole digital frequency to 1, in…
-
Thanks for your exciting work!
I try to use `eval/vcgbench/inference/run_ddp_inference.sh` to reproduce the performance on VCGBench with 4*A100 GPUs, but the generated texts are garbled as follows:…
-
Hello, is it possible to fine tune the vision model with multiple images?
-
Hi! Thank you for your great work.
I have a problem when I want to do merging weights.
1. I have a fake small data to do lora fine tuning. Getting 6 files, **adapter_config.json adapter_model.safet…
-
Hi, I'm trying to perform SFT training with Phi-3-vision, I followed the example with llava here https://github.com/huggingface/trl/blob/main/examples/scripts/vsft_llava.py. That however didn't work o…
-
Hey, I am trying to integrate your phi-3-vision script into LitServe.
How can I use the already loaded image (bytes) and pass it to the processor? (I don't want to save it as local/tmp file)
Tha…
-
Abstract
Motion capture is facing some new possibilities brought by the inertial sensing technologies which do not suffer from occlusion or wide-range recordings as vision-based solutions do. Howev…
-
"We use an off-the-shelf face detection and pose-extraction pipeline to both identify the face region and label the image with a pose"
Would it be possible to add the code to generate camera pose l…
-
### 🚀 The feature, motivation and pitch
Hi,
To warp some data according to a (batch) of affine transformations, two functions called sequentially need to be used:
1. [affine_grid](https://p…
-
### Anything you want to discuss about vllm.
I was wondering why does this happen? I am new to this space and was playing around with different machines, models and frameworks.
I am able to infere…