Add SAM decoder & output masks as png #418
Merged
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
added 9 commits
July 21, 2023 17:41
… size - Also filter based on the iou treshold - Additionally filtering based on the stability score and crop boxes should be done
|
The initial version is finished as the GGML version outputs masks close to the ones the PyTorch model outputs for hardcoded point inputs. For the point harcoded in the code (414.375, 162.796875) and this image:
the PyTorch model outputs this mask: and the GGML version outputs this: There are multiple things to be finished that I will begin doing now. Here are some with high priority:
|
YavorGIvanov
changed the title
YavorGIvanov
changed the title
YavorGIvanov
pushed a commit
that referenced
this pull request
Aug 17, 2023
* Add loading of decoder layers in Model * Multiply by hypernet_layer_cnt for ctx_size on model load * Add decoder layers to py conversion script * Fix wrong and reversed tensor sizes for decoder * Add decoder transformer implementation * Add decoder hypernet and iou prediction mlps * Add transpose convolution operation and unit test * Finish mask decoder and write the decoder output in the model state * Output masks to png after removing padding and upsampling to original size - Also filter based on the iou treshold - Additionally filtering based on the stability score and crop boxes should be done * Add stb image write in order to output masks from SAM * Add transpose convolution 2d name and symbol to ggml ops static arrays * Comment out debug print in transpose convolution test to fix compilation
YavorGIvanov
pushed a commit
that referenced
this pull request
Aug 17, 2023
* Add loading of decoder layers in Model * Multiply by hypernet_layer_cnt for ctx_size on model load * Add decoder layers to py conversion script * Fix wrong and reversed tensor sizes for decoder * Add decoder transformer implementation * Add decoder hypernet and iou prediction mlps * Add transpose convolution operation and unit test * Finish mask decoder and write the decoder output in the model state * Output masks to png after removing padding and upsampling to original size - Also filter based on the iou treshold - Additionally filtering based on the stability score and crop boxes should be done * Add stb image write in order to output masks from SAM * Add transpose convolution 2d name and symbol to ggml ops static arrays * Comment out debug print in transpose convolution test to fix compilation ggml-ci
ggerganov
added a commit
that referenced
this pull request
Aug 18, 2023
* sam : image + prompt encoder, store embeddings * sam : add the dense img pe in SAM state (#401) * Add SAM decoder & output masks as png (#418) * Add loading of decoder layers in Model * Multiply by hypernet_layer_cnt for ctx_size on model load * Add decoder layers to py conversion script * Fix wrong and reversed tensor sizes for decoder * Add decoder transformer implementation * Add decoder hypernet and iou prediction mlps * Add transpose convolution operation and unit test * Finish mask decoder and write the decoder output in the model state * Output masks to png after removing padding and upsampling to original size - Also filter based on the iou treshold - Additionally filtering based on the stability score and crop boxes should be done * Add stb image write in order to output masks from SAM * Add transpose convolution 2d name and symbol to ggml ops static arrays * Comment out debug print in transpose convolution test to fix compilation ggml-ci * Multithread GGML_OP_ADD_REL_POS operation * ggml : fix GGML_OP_NAME array * Disable and comment out debug prints in SAM example * Add README for the SAM example * Calculate & filter based on stability score and calculate bounding box ggml-ci --------- Co-authored-by: Yavor Ivanov <yivanov@viewray.com>
CCLDArjun
pushed a commit
to CCLDArjun/ggml
that referenced
this pull request
Dec 18, 2023
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.
With this additions, the SAM decoder and therefore the whole SAM ggml implementation for point input is almost finished. The things left are:
ЕDIT: Also there is a difference of part of the elements of some decoder results compared to the PyTorch model. The difference seems to be due to accumulating floating point error or due to the linear interpolation result numeric difference when preprocessing the image in the beggining.