Defaults for ImageClassification API #4415
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
eerhardt
reviewed
Oct 31, 2019
eerhardt
reviewed
Nov 1, 2019
…s been update to show how to get the output to console from the log.
harshithapv
force-pushed
the
ImageClassificationDefaults
branch
from
740a6fc
to
47ac5cd
Compare
codemzs
reviewed
Nov 1, 2019
| @@ -29,13 +29,15 @@ public static void Example() | |||
| //Download the image set and unzip | |||
| string finalImagesFolderName = DownloadImageSet( | |||
| imagesDownloadFolderPath); | |||
| //string finalImagesFolderName = "flower_photos"; | |||
There was a problem hiding this comment.
//string finalImagesFolderName = "flower_photos"; [](start = 12, length = 49)
remove #Closed
codemzs
reviewed
Nov 1, 2019
| @@ -60,7 +62,7 @@ public static void Example() | |||
| IDataView testDataset = trainTestData.TestSet; | |||
|
|
|||
| var pipeline = mlContext.MulticlassClassification.Trainers | |||
| .ImageClassification(featureColumnName:"Image", validationSet:testDataset) | |||
| .ImageClassification(featureColumnName:"Image", validationSet:null) | |||
There was a problem hiding this comment.
, validationSet:null [](start = 70, length = 20)
no need, default is null. #Resolved
codemzs
reviewed
Nov 1, 2019
| @@ -532,6 +532,12 @@ internal ImageClassificationTrainer(IHostEnvironment env, Options options) | |||
| options.ValidationSetBottleneckCachedValuesFileName = _options.ValidationSetBottleneckCachedValuesFileName; | |||
| } | |||
|
|
|||
| if ( options.MetricsCallback == null ) | |||
There was a problem hiding this comment.
[](start = 16, length = 1)
space #Closed
codemzs
reviewed
Nov 1, 2019
| @@ -532,6 +532,12 @@ internal ImageClassificationTrainer(IHostEnvironment env, Options options) | |||
| options.ValidationSetBottleneckCachedValuesFileName = _options.ValidationSetBottleneckCachedValuesFileName; | |||
| } | |||
|
|
|||
| if ( options.MetricsCallback == null ) | |||
There was a problem hiding this comment.
[](start = 48, length = 1)
space #Closed
frank-dong-ms-zz
pushed a commit
to frank-dong-ms-zz/machinelearning
that referenced
this pull request
Nov 4, 2019
* Changed some defaults * Changed metrics callback default * metricsCallback will write to mlcontext log by default. The sample has been update to show how to get the output to console from the log. * deleted unnecessary comments * Addressed comments * Minor clean up. * Disable unstable test.
frank-dong-ms-zz
pushed a commit
to frank-dong-ms-zz/machinelearning
that referenced
this pull request
Nov 4, 2019
* Changed some defaults * Changed metrics callback default * metricsCallback will write to mlcontext log by default. The sample has been update to show how to get the output to console from the log. * deleted unnecessary comments * Addressed comments * Minor clean up. * Disable unstable test.
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.
Changed EarlyStopping to run by default with ExponentialLR Decay for learning rate scheduling.
This combination seems to give most optimal results with a trade-off balance between the accuracy and training time.