[OpenLRM] inference, training, evaluation codes #824
Conversation
This file contains 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
add visual results
chenyingshu
requested review from
CaitinZhao,
SamitHuang and
zhanghuiyao
as code owners
SamitHuang
reviewed
Feb 5, 2025
| **render_results, # 'images_rgb', 'images_depth', 'images_weight' | ||
| } | ||
|
|
||
| def construct_train( |
There was a problem hiding this comment.
original construct() is never used. I have replaced construct() with new construct_train() in latest revision. [commit#62d1021]
| perceptual_weight: 1.0 | ||
| tv_weight: 5e-4 | ||
| optim: | ||
| # lr: 4e-4 # args.start_learning_rate |
There was a problem hiding this comment.
unnecessary configs/comments were removed.
examples/openlrm/eval.py
Outdated
| logger.info("Batch time cost: %.3fs.", batch_time) | ||
|
|
||
| target_images = data_batch["target_images"] # [M, C, H, W] | ||
| # print(f"target_images {target_images.shape}") |
There was a problem hiding this comment.
remove redundant comments. pls also check the other parts
There was a problem hiding this comment.
all redundant comments were removed.
|
|
||
| ### Inference Performance | ||
| - Input a single image, here reports speed of image-to-3D and image rendering. | ||
|
|
There was a problem hiding this comment.
pls describe the ms version and graph/pynative mode that are used in testing, referring to the mindone wiki page
There was a problem hiding this comment.
I added ms version and pynative mode that are used in "inference performance" and "training performance" in README. [commit#307d51a]
CaitinZhao
approved these changes
Feb 7, 2025
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
What does this PR do?
This PR adds OpenLRM Inference, Training, and Evaluation codes in
examples/openlrm:Main modules include:
openlrm/models/modeling_lrm.pyopenlrm/runners/inferopenlrm/runners/trainandopenlrm/models/lrm_with_loss.pyeval.py@SamitHuang