Age | Commit message (Collapse) | Author |
|
* Added Quantizer test for StandIn Layer
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I48bb9cadb48e20ee8e5b3dcf9e2f9fdb3b68351d
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Iab9b234d233591391a8e8626b7e8df3b7b0770a0
|
|
Signed-off-by: Sadik Armagan <sadik.armagan@arm.com>
Change-Id: I907f9b585f7ecd079c9cdd3c2edb6c473bf1d215
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I175008c81da028fb5bdc71e0abff06bc6e58734c
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I144c04f920ba3329886367f5e73fe758505ab96e
|
|
Change-Id: I7582a9ee36b4d1764a5a137cefe9b7b7dfe30254
Signed-off-by: Nikhil Raj <nikhil.raj@arm.com>
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I72bc00888d416fee177ea2e6e5006f8ff04f612e
|
|
Signed-off-by: FinnWilliamsArm <Finn.Williams@arm.com>
Change-Id: I3f8e716ae432737bb314e26792d18aa518aa1952
|
|
* Implemented VisitStackLayer
* Added unit test for Stack layer quantization
Signed-off-by: Matthew Jackson <matthew.jackson@arm.com>
Change-Id: I6f708543711c3600fa6c78d6d1f41ef14bbb90bb
|
|
!android-nn-driver:1451
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: Ieedbce1f6e95891137a250fdd07e2f7e4e1f4828
|
|
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: Ibfd4725bb04a5859488e968513cf11ac450fd277
|
|
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Change-Id: I26997d7770585055b2b3256baad2800a4c5ed7e8
|
|
* Implemented VisitPreluLayer
* Added unit test for Prelu layer quantization
Change-Id: I0442053f69608a400d295654b103cfd2429a0341
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
on inputs and output of Concat layer
Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
Change-Id: Idd79e44dbf49345aced3ddeeb8a53c9776f9f5d5
|
|
Change-Id: Ic08e38fe10ca1abd79c6e4b1a83dc9a929686b56
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
* Add function to calculate bias tensor quantization scale
from input and weights scales.
* Change visitor method of Conv2d, DepthwiseConv and FullyConnected to use
the new function.
* Fix Unit tests to expect correctly calculated quantization parameters.
Change-Id: Ic36f47ceea81243c813d74ccf791e984c819cc71
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
!android-nn-driver:1210
Change-Id: I940b3b9e421c92bfd55ae996f7bc54ac077f2604
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Used the new ARMNN_DEPRECATED_MSG macro instead of @deprecated
* Refactored the code to no longer use the deprecated methods where
applicable
!android-nn-driver:1126
Change-Id: Ib0578d3d6fc5a763f5fb922f67ba91fafc7796f6
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
!android-nn-driver:1120
Change-Id: I5192fa3deb4ea9766d38ad0bf4dfbfa0b4924c41
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
input/output types
* Also add unit tests for new preserve type option
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
Change-Id: I860759072f2e3546698118d1bcd5e79eb4e805ec
|
|
Change-Id: Iba91e3f3625639f01d66f81a9f3e419e0e285d66
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Also update unit tests for the quantizer to check the input and output
shape of the network
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
Change-Id: Ie804d852f2a4770d98dfb4dab6415f3d0fdd2ce4
|
|
* Add quantization test under QSymm16 scheme for all layers
* Refactor existing tests to reduce code duplication
Change-Id: I66c9437b3247d78acbb4ebc2c2481f3238268038
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
Change-Id: Ia7c305c30c39ec0e9db447a461479be17fde250c
Signed-off-by: Nattapat Chaimanowong <nattapat.chaimanowong@arm.com>
|
|
parameters
Change-Id: Ie67ce4966c5e5fef618876b027292da429de1485
Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com>
|
|
* Add check for infinity and negative infinity in quantize()
* Add assert for NaN value in quantize and dequantize()
* Add unit tests for infinity and negative infinity
Change-Id: Ie60e1e15b289ccbf99df4a3281f067b82cc9f9bf
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
Change-Id: I44b12c5c246b7aacc789420dbe55a16efaab6f98
|
|
Change-Id: Iff0902ea2751b079563ce82fbbec6db5157c3392
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
Change-Id: I0daffd23f32cc094d8309aed822cc46bb2aaa46f
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: I8e44866336dcd5a9694309cf9bb954a4991e61fd
Signed-off-by: Francis Murtagh <francis.murtagh@arm.com>
|
|
Change-Id: Iaefa145b8a218b3708c8a9208fdabd4984376ae9
Signed-off-by: Nina Drozd <nina.drozd@arm.com>
|
|
Change-Id: I19f01698a6f9b361cd1737d76e6ec2020fab77a6
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
* Added VisitConstantLayer to QuantizerVisitor
* Added unit tests and refactored QuantizerTest.cpp
* Code cleanup
Change-Id: I118fd2be085fc98879c5cfaa09698a7c98ba13f0
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: Ica9c48adad741840b201047bb65541a19aac17f7
Signed-off-by: FrancisMurtagh <francis.murtagh@arm.com>
|
|
* Some refactor of the existing QuantizePermute test for reuse
Change-Id: Ifaf1afc476bad348f260fa5340c0153e7ade2703
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: I4f208d18f7ac6bb04423cc26ecf61adf0ccc5d26
Signed-off-by: FrancisMurtagh <francis.murtagh@arm.com>
|
|
Change-Id: I1b409e5dac7922859e04a554893b982afc5ad1e7
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: Iab0d5aed243aca921661e4d39770fe02b1330442
Signed-off-by: FrancisMurtagh <francis.murtagh@arm.com>
|
|
Change-Id: I68cf5072aca6e3a8b3b8c57e19b6d417cd5813fc
Signed-off-by: Mike Kelly <mike.kelly@arm.com>
|
|
Change-Id: I216344ee10bbffadb648d4aef1d9a0d9dbb4a341
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
Signed-off-by: ruoyan01 <ruomei.yan@arm.com>
|
|
DepthwiseConvolution2D and FullyConnected
Change-Id: I3048504ff699fdb266488e7c07b7262e5843d4b0
Signed-off-by: Aron Virginas-Tar <Aron.Virginas-Tar@arm.com>
|
|
Change-Id: If7985a54eba97f7c61413e0804879e4afbf65c4d
Signed-off-by: Jim Flynn <jim.flynn@arm.com>
|
|
Change-Id: Ib18085e7e4b2e9d55e29b14122410732e3bdd088
Signed-off-by: FrancisMurtagh <francis.murtagh@arm.com>
|
|
* Minor code cleanup and refactoring
Change-Id: I9c6390c15944686134ddf4b47839762f2bb13922
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
* Added the OverrideInputRange method to the Quantizer API
* Created OverrideInputRangeVisitor to implement the override mechanism
* Moved the quantizer utility functions to the new NetworkQuantizerUtils files
* Moved the map of quantization ranges out of the StaticRangeVisitor
and into the NetworkQuantizer
* Added unit tests
* Code refactoring and cleanup
Change-Id: I9c1d006c1b6a35fbc04584a832fbe489f8f9276d
Signed-off-by: Matteo Martincigh <matteo.martincigh@arm.com>
|
|
Change-Id: Ia9afd15d002d4454ec72f219c5cf214704f6ae31
Signed-off-by: Nina Drozd <nina.drozd@arm.com>
|
|
Change-Id: I7b847112a0322ffc8b88a0708d8439bfb97cfe2c
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|
|
Change-Id: I6c61df213278e6ba65807932548bb2eaa159deba
Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
|