OpenImagingLab / OpenImagingLab/FlashVSR

RTX4090 results

Open
#37 5 comments 0 reactions 0 assignees View on GitHub

Nobody has claimed this yet.

Dominant language
Python
Stars
1.9k
Forks
152
PR merge metrics
No merged PRs in 30d

Description

Managed to install and run FlashVSR on my GPU in Windows. It's working :-)
4x upscale of example videos from this repository uses shared VRAM on my system therefore it's slow.
2x upscale fit in the 24GB VRAM, therefore it's fast,
I am getting this waring during interference:

UserWarning: The given NumPy array is not writable, and PyTorch does not support non-writable tensors. This means writing to this tensor will result in undefined behavior. You may want to copy the array to protect its data or make it writable before converting it to a tensor. This type of warning will be suppressed for the rest of this program. (Triggered internally at C:\actions-runner\_work\pytorch\pytorch\pytorch\torch\csrc\utils\tensor_numpy.cpp:209.)

upscale_x4_tiny_log.txt
upscsale_x2_tiny_log.txt

Is there something I can do about this warning ?

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

Research direction

Start with the attached upscale_x4_tiny_log.txt and upscsale_x2_tiny_log.txt files, then reproduce the warning on the Windows RTX4090 setup described in the issue. Trace the non-writable NumPy array conversion that produces the PyTorch warning; the work is done when the warning is addressed without breaking the reported 2x and 4x upscaling runs.

Written by the indexing model from the issue text.

Assessment

Tech stack
python, pytorch
Domain
computer-vision, machine-learning
Issue type
Bug
Difficulty
3/5
Estimated time
1-2 days
Activity status
Stale
Clarity
Needs clarification
Newbie friendliness
35/100

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.