armnn.git -

Age	Commit message (Collapse)	Author
2019-06-26	Update the CL pin to the latest master	Ferran Balaguer
	* Update SoftMaxUint8Workload for CL and NEON to deal with quantization parameters as vectors. * Change Sigmoid Activation function QAsymm8 tests to use scale=1.f/256.f and offset=0 as quatization output parameters. !android-nn-driver:1417 Signed-off-by: Ferran Balaguer <ferran.balaguer@arm.com> Change-Id: Ief91f10193fbbbad0c0124ece41f0bf4e0dcd992
2019-06-14	IVGCVSW-3278 Cl and Neon TensorHandles inherit from common base interface	Derek Lamberti
	Change-Id: Ia68da09d8f0fb0a04af9cb61062d7edaa5f1b887 Signed-off-by: Derek Lamberti <derek.lamberti@arm.com>
2019-03-15	IVGCVSW-2354 Caffe SqueezeNet through armnn Cl and Neon	Narumol Prangnawarat
	* Compute Softmax Acl axis for Cl and Neon * Add unittests for Softmax in 3D and 4D * Correct input and output layer names in CaffeSqueezeNet inference test Change-Id: I2d369d9a2db19c40f2af3341039dd33f0c5637b1 Signed-off-by: Narumol Prangnawarat <narumol.prangnawarat@arm.com>
2019-01-08	Refactor: Don't include all ComputeLibrary function definitions everywhere.	Matthew Bentham
	Just include the function definition that is specifically needed for each workload. Also, tighten up the scope where Compute Library functions are available. Knocks about 30seconds off a 4m30s single-threaded compile of the Neon workloads. Change-Id: Idac438f3bc77ff978295fbc9505cb42447def145
2018-10-10	IVGCVSW-1899 : Neon backend folder structure	David Beck
	armnn:149855 Change-Id: I26e8cf83422a65049386a5ebdb6d0001627aefaa