Add resize cubic mode #4266
Draft
Add resize cubic mode #4266
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
Generate the following test cases One that mirrors customer workoad (one using a specific coefficient) one with scales one with sizes Get parser tests started looking at the model and then use these to test what we're seeing with the depth anything model resizes
… we do convolution
TedThemistokleous
added
roadmap
Work in progress. will need to be tested/validated and other items ironed out
Use this to generate keyvalues based on the input sampling selected to be used for generating the proper 1d convolution kernel. Remove this for now and perform Remove previous way to things as this needs to be handle on a per input basees after the up/downsample
Use this to generate the approrpaite matrix for each channels cubic coefficients to perform the required interpolation per dimension. Should handle up and down scales
Supporting calls (Kronker product and co) still in works but the overall structure for this should be repeatable regardless of what kernel is used here
Matrix setup and muls for each dimension
…al alloc Work on the preocmputed matrix data to get a smaller and optimized matrix instead of relying on our const propigation to fold a bunch of literals during ocmpile time. This results in one final matrix after all transformations have been precomputed based on the scale per dimension
TedThemistokleous
force-pushed
the
add_resize_cubic_mode
branch
from
42f2884 to
166d513
Compare
This build is not recommended to merge 🔴 |
❌bert-mrpc-tf: ERROR - check error outputerror: unknown warning option '-Wnrvo' [-Werror,-Wunknown-warning-option]error: unknown warning option '-Wnrvo' [-Werror,-Wunknown-warning-option] 2025-09-15 00:19:34.712290: I tensorflow/core/platform/cpu_feature_guard.cc:210] This TensorFlow binary is optimized to use available CPU instructions in performance-critical operations. To enable the following instructions: SSE3 SSE4.1 SSE4.2 AVX AVX2 FMA, in other operations, rebuild TensorFlow with the appropriate compiler flags. Traceback (most recent call last): File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 359, in main() File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 306, in main graph = load_tf_graph(model_name) File "/src/AMDMIGraphX/tools/accuracy/accuracy_checker.py", line 300, in load_tf_graph graph_def.ParseFromString(f.read()) File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/lib/io/file_io.py", line 116, in read self._preread_check() File "/usr/local/lib/python3.10/dist-packages/tensorflow/python/lib/io/file_io.py", line 77, in _preread_check self._read_buf = _pywrap_file_io.BufferedInputStream( tensorflow.python.framework.errors_impl.UnimplementedError: File system scheme '[local]' not implemented (file: '/new-saved-models/tf-misc/bert_mrpc1.pb') 🔴bert_large_uncased_fp16: FAILED: MIGraphX is not within tolerance - check verbose output🔴mask-rcnn: FAILED: MIGraphX is not within tolerance - check verbose output |
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.
Motivation
Add cubic resize functionality for resize op
Technical Details
Related to customer support and or adding functionality to resize we're seeing in the depthanything model
Changelog Category