Gitiles
Code Review
Sign In
gerrit-public.fairphone.software
/
platform
/
test
/
mlts
/
benchmark
/
d6e8a55ad3bc43fea56cb9d5290dbc2f12f14195
d6e8a55
Enable relaxed mode (fp16) in TFLite intepreter. am: 5c5258ee1b am: e3a7bc9c5a
by Przemyslaw Szczepaniak
· 6 years ago
245b598
Add MobileNetV2 models to scoring benchmark am: b366b5d3f0 am: cba3ab3a0c
by Przemyslaw Szczepaniak
· 6 years ago
e3a7bc9
Enable relaxed mode (fp16) in TFLite intepreter. am: 5c5258ee1b
by Przemyslaw Szczepaniak
· 6 years ago
cba3ab3
Add MobileNetV2 models to scoring benchmark am: b366b5d3f0
by Przemyslaw Szczepaniak
· 6 years ago
5c5258e
Enable relaxed mode (fp16) in TFLite intepreter.
by Przemyslaw Szczepaniak
· 6 years ago
b366b5d
Add MobileNetV2 models to scoring benchmark
by Przemyslaw Szczepaniak
· 6 years ago
9255622
Corrects the calculation of Word Error Rate. am: 23b6748cff am: ccb3979e59
by Viet Dang
· 6 years ago
ccb3979
Corrects the calculation of Word Error Rate. am: 23b6748cff
by Viet Dang
· 6 years ago
7e20aca
Add README.txt, add version to manifest. am: 745eca3d4d am: 658aa73dc4
by Przemyslaw Szczepaniak
· 6 years ago
0a76217
Keep screen on during benchmark using FLAG_KEEP_SCREEN_ON. am: 06a8d3627e
by Przemyslaw Szczepaniak
· 6 years ago
4e3c58f
Fix ASR accuracy result formatting. am: 93e493f845 am: 0a357f9959
by Przemyslaw Szczepaniak
· 6 years ago
f9af525
Move latency graphs below latency/accuracy table. am: 31363a9e80 am: a54e77af70
by Przemyslaw Szczepaniak
· 6 years ago
6e31718
Add ASR to scoring run and parsing. am: c057541c30 am: c1714ac367
by Przemyslaw Szczepaniak
· 6 years ago
9c4b599
Allow MLTS/build_and_run_benchmark.sh to work on release images. am: f1e9334965
by Przemyslaw Szczepaniak
· 6 years ago
fa5fd1d
Fix for AssetManager.list() not working on some devices. am: 80758caa28
by Przemyslaw Szczepaniak
· 6 years ago
92009f1
Expose validation errors in score summary. am: 507d3f6298 am: 24c5f8eeb1
by Przemyslaw Szczepaniak
· 6 years ago
4b345cd
Add baseline comparisons for latency and accuracy. am: 4ccdf7ec90 am: bf8fd1feb3
by Przemyslaw Szczepaniak
· 6 years ago
3fc669f
Add MelCepLogF0 evaluator results to HTML results am: f8f017d4de am: 79059a0022
by Przemyslaw Szczepaniak
· 6 years ago
2874d37
Add mobilenet variants to scoring test am: e7989ddbaf am: f73b63197c
by Przemyslaw Szczepaniak
· 6 years ago
23b6748
Corrects the calculation of Word Error Rate.
by Viet Dang
· 6 years ago
658aa73
Add README.txt, add version to manifest. am: 745eca3d4d
by Przemyslaw Szczepaniak
· 6 years ago
5b87ef5
Keep screen on during benchmark using FLAG_KEEP_SCREEN_ON. am: 06a8d3627e
by Przemyslaw Szczepaniak
· 6 years ago
0a357f9
Fix ASR accuracy result formatting. am: 93e493f845
by Przemyslaw Szczepaniak
· 6 years ago
a54e77a
Move latency graphs below latency/accuracy table. am: 31363a9e80
by Przemyslaw Szczepaniak
· 6 years ago
c1714ac
Add ASR to scoring run and parsing. am: c057541c30
by Przemyslaw Szczepaniak
· 6 years ago
a4e11c1
Allow MLTS/build_and_run_benchmark.sh to work on release images. am: f1e9334965
by Przemyslaw Szczepaniak
· 6 years ago
ae16e2a
Fix for AssetManager.list() not working on some devices. am: 80758caa28
by Przemyslaw Szczepaniak
· 6 years ago
24c5f8e
Expose validation errors in score summary. am: 507d3f6298
by Przemyslaw Szczepaniak
· 6 years ago
bf8fd1f
Add baseline comparisons for latency and accuracy. am: 4ccdf7ec90
by Przemyslaw Szczepaniak
· 6 years ago
79059a0
Add MelCepLogF0 evaluator results to HTML results am: f8f017d4de
by Przemyslaw Szczepaniak
· 6 years ago
f73b631
Add mobilenet variants to scoring test am: e7989ddbaf
by Przemyslaw Szczepaniak
· 6 years ago
745eca3
Add README.txt, add version to manifest.
by Przemyslaw Szczepaniak
· 6 years ago
06a8d36
Keep screen on during benchmark using FLAG_KEEP_SCREEN_ON.
by Przemyslaw Szczepaniak
· 6 years ago
93e493f
Fix ASR accuracy result formatting.
by Przemyslaw Szczepaniak
· 6 years ago
31363a9
Move latency graphs below latency/accuracy table.
by Przemyslaw Szczepaniak
· 6 years ago
c057541
Add ASR to scoring run and parsing.
by Przemyslaw Szczepaniak
· 6 years ago
f1e9334
Allow MLTS/build_and_run_benchmark.sh to work on release images.
by Przemyslaw Szczepaniak
· 6 years ago
80758ca
Fix for AssetManager.list() not working on some devices.
by Przemyslaw Szczepaniak
· 6 years ago
507d3f6
Expose validation errors in score summary.
by Przemyslaw Szczepaniak
· 6 years ago
4ccdf7e
Add baseline comparisons for latency and accuracy.
by Przemyslaw Szczepaniak
· 6 years ago
f8f017d
Add MelCepLogF0 evaluator results to HTML results
by Przemyslaw Szczepaniak
· 6 years ago
e7989dd
Add mobilenet variants to scoring test
by Przemyslaw Szczepaniak
· 6 years ago
331f68d
Adds validation for the ASR model. am: 843387f2ab am: a000b93815
by Viet Dang
· 6 years ago
a000b93
Adds validation for the ASR model. am: 843387f2ab
by Viet Dang
· 6 years ago
843387f
Adds validation for the ASR model.
by Viet Dang
· 6 years ago
760627d
Merge "Renames AssetUtils to IOUtils and moves readFloats() there." am: 456f75a4b5
by Viet Dang
· 6 years ago
2f91306
Merge "Renames AssetUtils to IOUtils and moves readFloats() there."
by Viet Dang
· 6 years ago
456f75a
Merge "Renames AssetUtils to IOUtils and moves readFloats() there."
by Viet Dang
· 6 years ago
1d61a5c
Adjust mobilenet test name am: e3d1a4e22d am: 35055f3ab9
by Przemyslaw Szczepaniak
· 6 years ago
35055f3
Adjust mobilenet test name am: e3d1a4e22d
by Przemyslaw Szczepaniak
· 6 years ago
28a57ca
Fix input dataset size calculation am: 3b903b9120 am: a48538be7f
by Przemyslaw Szczepaniak
· 6 years ago
c793235
Run whole dataset in scoring benchmark. am: bf3f04189e am: e5c26adafb
by Przemyslaw Szczepaniak
· 6 years ago
64d1c89
Generate results summary HTML page. am: 9429af4a19 am: a28729d6d2
by Przemyslaw Szczepaniak
· 6 years ago
64ee425
Remove "example" from package names am: 1dbcfd5e67 am: d71903bf91
by Przemyslaw Szczepaniak
· 6 years ago
b59e43e
Remove #testNNAPI.* tests from TFLiteTest am: a4bcd91b1b am: 98286b97a0
by Przemyslaw Szczepaniak
· 6 years ago
a48538b
Fix input dataset size calculation am: 3b903b9120
by Przemyslaw Szczepaniak
· 6 years ago
e5c26ad
Run whole dataset in scoring benchmark. am: bf3f04189e
by Przemyslaw Szczepaniak
· 6 years ago
a28729d
Generate results summary HTML page. am: 9429af4a19
by Przemyslaw Szczepaniak
· 6 years ago
d71903b
Remove "example" from package names am: 1dbcfd5e67
by Przemyslaw Szczepaniak
· 6 years ago
98286b9
Remove #testNNAPI.* tests from TFLiteTest am: a4bcd91b1b
by Przemyslaw Szczepaniak
· 6 years ago
e3d1a4e
Adjust mobilenet test name
by Przemyslaw Szczepaniak
· 6 years ago
3b903b9
Fix input dataset size calculation
by Przemyslaw Szczepaniak
· 6 years ago
bf3f041
Run whole dataset in scoring benchmark.
by Przemyslaw Szczepaniak
· 6 years ago
9429af4
Generate results summary HTML page.
by Przemyslaw Szczepaniak
· 6 years ago
1dbcfd5
Remove "example" from package names
by Przemyslaw Szczepaniak
· 6 years ago
a4bcd91
Remove #testNNAPI.* tests from TFLiteTest
by Przemyslaw Szczepaniak
· 6 years ago
9cb72d9
Renames AssetUtils to IOUtils and moves readFloats() there.
by Viet Dang
· 6 years ago
7b1042e
Adds validation for the TTS model. am: 4b63f233f5 am: 5cde853348
by Viet Dang
· 6 years ago
5cde853
Adds validation for the TTS model. am: 4b63f233f5
by Viet Dang
· 6 years ago
828e5bb
Makes evaluator field an object and refactors asset reading logic. am: b8cf22452b
by Viet Dang
· 6 years ago
6a72537
Makes evaluator field an object and refactors asset reading logic.
by Viet Dang
· 6 years ago
4b63f23
Adds validation for the TTS model.
by Viet Dang
· 6 years ago
2f666a6
(re)Enable NNAPI in UI-started benchmark. am: c7bb5f21d4 am: c86df627ef
by Przemyslaw Szczepaniak
· 6 years ago
b8cf224
Makes evaluator field an object and refactors asset reading logic.
by Viet Dang
· 6 years ago
c86df62
(re)Enable NNAPI in UI-started benchmark. am: c7bb5f21d4
by Przemyslaw Szczepaniak
· 6 years ago
69c3db2
Utility for dumping intermediate tensors. am: 94771d0ae6 am: 9fbe539df2
by Przemyslaw Szczepaniak
· 6 years ago
9fbe539
Utility for dumping intermediate tensors. am: 94771d0ae6
by Przemyslaw Szczepaniak
· 6 years ago
c7bb5f2
(re)Enable NNAPI in UI-started benchmark.
by Przemyslaw Szczepaniak
· 6 years ago
94771d0
Utility for dumping intermediate tensors.
by Przemyslaw Szczepaniak
· 6 years ago
c4986c8
Moves evaluator field one level up in the model config loader. am: 26b3d80118
by Viet Dang
· 6 years ago
e15e73a
Moves evaluator field one level up in the model config loader. am: 26b3d80118
by Viet Dang
· 6 years ago
26b3d80
Moves evaluator field one level up in the model config loader.
by Viet Dang
· 6 years ago
51c56bb
Removes the workaround for resetting TFLite state tensors for 18-input LSTM. am: 2b46eaec45
by Viet Dang
· 6 years ago
935c90e
Removes the workaround for resetting TFLite state tensors for 18-input LSTM.
by Viet Dang
· 6 years ago
2b46eae
Removes the workaround for resetting TFLite state tensors for 18-input LSTM.
by Viet Dang
· 6 years ago
20eba35
Switch the benchmark app to using the new NNAPI Delegate. am: bcdd25958a
by Viet Dang
· 6 years ago
3bfe670
Switch the benchmark app to using the new NNAPI Delegate. am: bcdd25958a
by Viet Dang
· 6 years ago
cf69d28
Move dataSize field one level up in test list parser. am: 04f845ba21
by Lev Proleev
· 6 years ago
8532e13
Move dataSize field one level up in test list parser. am: 04f845ba21
by Lev Proleev
· 6 years ago
bcdd259
Switch the benchmark app to using the new NNAPI Delegate.
by Viet Dang
· 6 years ago
7b1ebcb
Support datasets and top-k evaluation in mlts am: 7cfcee7e1e am: ac21725258
by Mika Raento
· 6 years ago
ac21725
Support datasets and top-k evaluation in mlts am: 7cfcee7e1e
by Mika Raento
· 6 years ago
04f845b
Move dataSize field one level up in test list parser.
by Lev Proleev
· 6 years ago
7cfcee7
Support datasets and top-k evaluation in mlts
by Mika Raento
· 6 years ago
13beeb9
Adds support for input/output sequence to the benchmark. am: 6063374e9c
by Viet Dang
· 6 years ago
3545304
Adds support for input/output sequence to the benchmark. am: 6063374e9c
by Viet Dang
· 6 years ago
6063374
Adds support for input/output sequence to the benchmark.
by Viet Dang
· 6 years ago
f254e46
Support TFLite-only execution in benchmark am: c6b1aab1dc am: 9c59ef4533
by Mika Raento
· 6 years ago
7390244
Add benchmark run flags am: e1059cb570 am: 35a35a245d
by Przemyslaw Szczepaniak
· 6 years ago
55a4eb2
Add max single element error to benchmark output am: ddf02b54b1 am: bf4a136aee
by Mika Raento
· 6 years ago
Next »