Onnx load model #5782
Merged
Onnx load model #5782
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
tarekgh
reviewed
May 3, 2021
tarekgh
reviewed
May 3, 2021
tarekgh
reviewed
May 3, 2021
tarekgh
reviewed
May 3, 2021
| @@ -348,7 +347,7 @@ public static OnnxModel CreateFromBytes(byte[] modelBytes) | |||
| public static OnnxModel CreateFromBytes(byte[] modelBytes, int? gpuDeviceId = null, bool fallbackToCpu = false, | |||
| IDictionary<string, int[]> shapeDictionary = null) | |||
| { | |||
| var tempModelFile = Path.GetTempFileName(); | |||
| var tempModelFile = Path.Combine(MLContext.TempFilePath, Path.GetRandomFileName()); | |||
There was a problem hiding this comment.
If we add this, it should be internal. We don't want to expose it publicly.
There was a problem hiding this comment.
Its a new random file path each time, so we probably wouldn't want it to be a property. I could add an internal method that returned that though.
tarekgh
approved these changes
May 3, 2021
eerhardt
reviewed
May 3, 2021
eerhardt
reviewed
May 3, 2021
eerhardt
reviewed
May 3, 2021
eerhardt
reviewed
May 3, 2021
eerhardt
previously requested changes
May 3, 2021
Codecov Report
@@ Coverage Diff @@
## main #5782 +/- ##
==========================================
+ Coverage 68.35% 68.40% +0.04%
==========================================
Files 1131 1131
Lines 241210 241203 -7
Branches 25039 25039
==========================================
+ Hits 164887 164989 +102
+ Misses 69819 69727 -92
+ Partials 6504 6487 -17
Flags with carried forward coverage won't be shown. Click here to find out more.
|
michaelgsharp
force-pushed
the
onnx-load-model
branch
from
eef96f0 to
02bab82
Compare
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 4, 2021
eerhardt
reviewed
May 12, 2021
eerhardt
reviewed
May 12, 2021
eerhardt
reviewed
May 13, 2021
Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com>
michaelgsharp
force-pushed
the
onnx-load-model
branch
from
35ef427 to
0313706
Compare
darth-vader-lg
pushed a commit
to darth-vader-lg/ML-NET
that referenced
this pull request
May 19, 2021
* fixed onnx temp model deleting * random file path fixed * updates from pr * Changes from PR comments. * Changed how auto ml caches. * PR fixes. * Update src/Microsoft.ML.AutoML/API/ExperimentSettings.cs Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com> * Tensorflow fixes from PR comments * fixed filepath issues Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com>
michaelgsharp
added a commit
that referenced
this pull request
May 27, 2021
…#5796) * Raised the limit of recursions in the creation of the CodedInputStream in the OnnxTransformer (as the default value in the Google.Protobuf). Otherwise some models cannot be loaded (ex. TF2 Efficentdet). * Updated arcade to the latest version (#5783) * updated arcade to the latest version * updated eng/common correctly * Fixed benchmark test. * Use dotnet certificate (#5794) * Use dotnet certificate * Update 3.1 SDK Co-authored-by: Prashanth Govindarajan <prgovi@microsoft.com> Co-authored-by: Michael Sharp <51342856+michaelgsharp@users.noreply.github.com> * Arm build changes (#5789) * arm testing * initial commit with build working on arm64 * windows changes * build fixes for arm/arm64 with cross compilation * cross build instructions added * renamed arm to Arm. Changed TargetArchitecture to default to OS architecture * fixed some formatting * fixed capitilization * fixed Arm Capitilization * Fix cross-compilation if statement * building on apple silicon * removed non build related files * Changes from PR comments. Removal of FastTreeNative flag. * Changes from pr comments. * Fixes from PR comments. * Changed how we are excluding files. * Onnx load model (#5782) * fixed onnx temp model deleting * random file path fixed * updates from pr * Changes from PR comments. * Changed how auto ml caches. * PR fixes. * Update src/Microsoft.ML.AutoML/API/ExperimentSettings.cs Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com> * Tensorflow fixes from PR comments * fixed filepath issues Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com> Co-authored-by: Michael Sharp <51342856+michaelgsharp@users.noreply.github.com> Co-authored-by: Matt Mitchell <mmitche@microsoft.com> Co-authored-by: Prashanth Govindarajan <prgovi@microsoft.com> Co-authored-by: Eric Erhardt <eric.erhardt@microsoft.com>
ghost
locked as resolved and limited conversation to collaborators
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
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.
Fixes #5766 and #5764 by letting the user specify a temp path location, which defaults to the current location to keep existing behavior, and by make sure the temp onnx model file gets cleaned up by opening it with a delete on close flag.