Skip to content

chore: use larger dataset for integration test of image_classification_v2 #968

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 6 commits into from
Mar 13, 2025
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 4 additions & 4 deletions flutter/assets/tasks.pbtxt
Original file line number Diff line number Diff line change
Expand Up @@ -42,10 +42,10 @@ task {
}
tiny {
name: "Imagenet dataset for integration test"
input_path: "https://mobile.mlcommons-storage.org/app-resources/datasets/v0_7/imagenet_tiny.zip"
input_checksum: "42cb83d80d0341d6719d68b32322adf2"
groundtruth_path: "https://mobile.mlcommons-storage.org/app-resources/datasets/v3_0/imagenet_tiny-groundtruth.txt"
groundtruth_checksum: "cc6d83ca25daeb2475f36c079e53bc26"
input_path: "https://mobile.mlcommons-storage.org/app-resources/datasets/v5_0/imagenet_tiny.zip"
input_checksum: "2cde6f1d741b9c1834db261ac6e43a6e"
groundtruth_path: "https://mobile.mlcommons-storage.org/app-resources/datasets/v5_0/imagenet_tiny_val.txt"
groundtruth_checksum: "086f99eff3d1b93fd41e7f35498570a7"
}
}
model {
Expand Down
23 changes: 18 additions & 5 deletions flutter/integration_test/expected_accuracy.dart
Original file line number Diff line number Diff line change
Expand Up @@ -18,16 +18,29 @@ key: <accelerator> OR <accelerator>|<backendName>
*/

const Map<String, Interval> _imageClassificationV2 = {
'cpu': Interval(min: 0.82, max: 0.84),
'npu': Interval(min: 0.80, max: 0.82),
'tpu': Interval(min: 0.82, max: 0.84),
'ane': Interval(min: 0.69, max: 0.91),
'cpu&gpu&ane': Interval(min: 0.69, max: 0.91),
// TODO (anhappdev): check expected accuracy for snpe_dsp, psnpe_dsp
'snpe_dsp': Interval(min: 0.0, max: 1.0),
'psnpe_dsp': Interval(min: 0.0, max: 1.0),
'neuron-mdla': Interval(min: 0.81, max: 0.83),
'samsung_npu': Interval(min: 0.83, max: 0.85),
};

const Map<String, Interval> _imageClassificationOfflineV2 = {
'cpu': Interval(min: 0.88, max: 0.91),
'npu': Interval(min: 0.69, max: 0.91),
'tpu': Interval(min: 0.88, max: 0.91),
'npu': Interval(min: 0.69, max: 0.71),
'tpu': Interval(min: 0.89, max: 0.91),
'ane': Interval(min: 0.69, max: 0.91),
'cpu&gpu&ane': Interval(min: 0.69, max: 0.91),
// TODO (anhappdev): check expected accuracy for snpe_dsp, psnpe_dsp
'snpe_dsp': Interval(min: 0.0, max: 1.0),
'psnpe_dsp': Interval(min: 0.0, max: 1.0),
'neuron-mdla': Interval(min: 0.79, max: 0.91),
'samsung_npu': Interval(min: 0.99, max: 1.0),
'neuron-mdla': Interval(min: 0.79, max: 0.81),
'samsung_npu': Interval(min: 0.98, max: 1.0),
};

const Map<String, Interval> _objectDetection = {
Expand Down Expand Up @@ -105,5 +118,5 @@ const benchmarkExpectedAccuracy = {
BenchmarkId.naturalLanguageProcessing: _naturalLanguageProcessing,
BenchmarkId.superResolution: _superResolution,
BenchmarkId.stableDiffusion: _stableDiffusion,
BenchmarkId.imageClassificationOfflineV2: _imageClassificationV2,
BenchmarkId.imageClassificationOfflineV2: _imageClassificationOfflineV2,
};
Loading