Age | Commit message (Collapse) | Author |
|
Change-Id: Ie6c553798eac732f37148d81970366e5a4ede1be
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I4166c0bbb5ba7f8b8884e71134c21f43d1fc27b0
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
* change MobileNet SSD input to uint8
* get quantization scale and offset from the model
* change data layout to NHWC as TensorFlow lite layout
* update expected output as result from TfLite with quantized data
Change-Id: I07104d56286893935779169356234de53f1c9492
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
|
|
Change-Id: I5656b23d9783e7f953e677001d16e41eedeb42b2
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I1a61a1da2258bd07b39da6063d22a5bd22c1884d
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: Ieb99ac1aa347cee4b28b831753855c4614220648
|
|
Change-Id: Ie31eee48cc14ada37526130998da7a482d56b1ea
|
|
Change-Id: Iad57395b0231a0960e7fc27c1d487bdee8a1f464
|
|
Change-Id: If45696594503cd093c7d5f3b5001b20e9bb2e573
|
|
Change-Id: I6ed434b798c617f85ca1faa7c5eef4cdabff4a07
|
|
Change-Id: I0896c5f74d4e432a2ea8eff3cbe2db0702aa9ed9
|
|
certain backends
* Read compute devices from the CL as strings and convert them into BackendId objects afterwards
Change-Id: Icded1c572778f5a213644e3052ff6dfe7022128b
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: I7e8d377cdbddf0176ae05d8b6b2fd03c6f614168
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: I69eac52c9c944a5d209c5c7432c1b7f46e64f05b
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: If7ee1efa3ee79d9eca41c5a6219b3fc42e740efe
|
|
InferenceModel
Change-Id: I64d724367d42dca4b768b6c6e42acda714985950
|
|
Change-Id: If8d6516286557a6381561805cd53b5659b38f6a6
|
|
separate branch) and master
* Brings in all the changes done for the pluggable backends
* Added sub-graph support and tests
* Added precompiled layer support and tests
* Moved BackendSettings to a separate file
* Removed the backend-specific code
* Ported DebugLayer and associated functionality
* Included fixes to make those changes work with master
Change-Id: Id7028fa7917527b844628d5aff5732e3d94c0488
|
|
in favor of a type-indepent implementation that takes void-pointers
* The new implementation requires the size of the type to be passed
to the function
* Updated all the usages accordingly
* Removed the old implementation no longer used
!android-nn-driver:469
Change-Id: I37f4e6d62a38fbb8ec8c39bb559a2c54c83365d4
|
|
* Wrap Resize function call with conditional checking
if height and/or width need to be changed.
Change-Id: Ic33c3ed29cc985c147d29db8e9dd237ab9c741d1
|
|
* add IBackendContext interface
* add ClBackendContext implementation
Change-Id: I13e4d12b73d4c7775069587675276f7cee7d630b
|
|
Change-Id: I663a0a0fccb43ee960ec070121a59df9db0bb04e
|
|
I had forgotten that as a workaround for the testing using a different
number of test cases for different hardware backends, we repeat
the expected test results an arbitrary number of times
Change-Id: I4d1ea8daa1cbfd63ebcd7ac93ac30acb5806fafe
|
|
Change-Id: Iaf03755b0d30598f5d09ca36af8eeeb369191950
|
|
Change-Id: Ib7ea0a0b809bdfe1d705b31a08f42e1b7815b0d2
|
|
Remove incorrect early out from image resize
Change-Id: I58014680f5cbe43dfc6b4af66638db67c070a146
|
|
When looking for the top probability, use the 'first' result not the 'second'.
This avoids an issue where for batched tests the classification index was reported wrongly.
Still doesn't correctly handle multiple results with the exact probabibility, or batched testing,
but it's slightly more correct than before.
Change-Id: I57d33552754667613e222d9d2037e12c87a96854
|
|
* In ImagePreprocessor, typecasted the number of image elements
(unsigned int) to a const_iterator::difference_type (int)
Change-Id: Idb8611185f6471751678a0a77d8225bceb204a34
|
|
Change-Id: I99498a633d75a2b4bdcd059627b07beaa9984890
|
|
implement test for TfLite VGG16 quantized
Change-Id: I2061f62f62684b963fa0f090718f1dcffe5c93ce
|
|
in the network
Change-Id: Ide594db8c79ff67642721d8bad47624b88621fbd
|
|
tests) / ExecuteNetwork
!referencetests:154790
Change-Id: Iaf9608ae1e66460079f2546b30d7fbc9b55bb7dd
|
|
Change-Id: Ie7549fd27378acfa97e68d098e338b8c9d4ea5d2
|
|
* Changed message to 'Prediction for test case <N>
is incorrect: Expected (<X>) but predicted (<Y>)'
Change-Id: Ie54b70683bf5bb26de2f2a6bcf4a162c99ba5474
|
|
!devenv:148227
Change-Id: I550c885c125f2fe12951e38d4157276562cb49ec
|
|
Change-Id: Ib0d59015aa104909f3922f9749e3787e15c7c86e
|
|
flag is set,
false by default, use this globally same as concurrent flag, removed -e option from RunCsvTest options,
this is passed in from main
Change-Id: I246c2c40b1a113b896be0d41aba528e79ecdba0d
|
|
Tf(http://download.tensorflow.org/models/mobilenet_v1_2018_08_02/mobilenet_v1_1.0_224.tgz)
Change-Id: I3a07d7a161c8ac81c6a94cc0b3557ee7fa5e48e5
|
|
* Call the Print() function on the Profiler when profiling is enabled.
Change-Id: I4c06ce9bfa961ac8d81d02a516502337d1fbc968
|
|
All changes are the same:
//
// Copyright © 2017 ARM Ltd. All rights reserved.
-// See LICENSE file in the project root for full license information.
+// SPDX-License-Identifier: MIT
//
Change-Id: I37eae011411133663ca9d2b059714d92f8bf8e24
|
|
|
|
|
|
|
|
Change-Id: Id3c11dc5ee94ef664374a988fcc6901e9a232fa6
|