fix: respect model device in image preprocessing#318
Open
Mr-Neutr0n wants to merge 1 commit intoDepthAnything:mainfrom
Open
fix: respect model device in image preprocessing#318Mr-Neutr0n wants to merge 1 commit intoDepthAnything:mainfrom
Mr-Neutr0n wants to merge 1 commit intoDepthAnything:mainfrom
Conversation
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Bug
image2tensorin bothdepth_anything_v2/dpt.pyandmetric_depth/depth_anything_v2/dpt.pyhardcodes device selection viatorch.cuda.is_available()instead of using the model's actual device. This causes device mismatch errors when the model is on a different device (e.g., MPS, a specific CUDA GPU, or CPU when CUDA is available but the model was intentionally placed on CPU).Fix
Replaced the hardcoded device detection with
next(self.parameters()).deviceto infer the device directly from the model's parameters. This ensures the input tensor is always placed on the same device as the model, regardless of how the model was loaded or moved.