Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
armnn
/
ec67a0f08e0f96a5aebf3cac65331c67f6649f5e
« Previous
49937f3
IVGCVSW-2773 Integrate new CL tuner into ArmNN
by Ruomei Yan
· 5 years ago
d78b891d
IVGCVSW-3021 Add end-to-end flow control integration test
by Matthew Bentham
· 5 years ago
386681a
IVGCVSW-2993: Investigate TfLite Parser test output shape validation
by Narumol Prangnawarat
· 5 years ago
ff05cc5
IVGCVSW-2405 Rename SubGraph to SubgraphView
by Derek Lamberti
· 5 years ago
6870b98
IVGCVSW-2948 Add DeepSpeech v1 support to TensorFlowLiteSupport.md
by Narumol Prangnawarat
· 5 years ago
18515e2
IVGCVSW-2983 activation layers support for QSymm16 !armnn:1023
by Teresa Charlin
· 5 years ago
e05e38e
Fixing a broken link to MLPlatform.org
by Brian Joyce
· 5 years ago
dc2f7f4
IVGCVSW-2843 Support QSymm16 via Command-line quantizer tool
by Sadik Armagan
· 5 years ago
ae2c5f0
IVGCVSW-2982 Refactor reference Activation workload
by Nattapat Chaimanowong
· 5 years ago
bb73e57
IVGCVSW-2773 Update clframework pin for the jenkins timing tests
by Ruomei Yan
· 5 years ago
13a9fa6
IVGCVSW-2396 Go back to using offset memory manager
by Sadik Armagan
· 5 years ago
501f4d4
IVGCVSW-2996 Add Reshape layer to ParseFullyConnected in TfLite parser
by Narumol Prangnawarat
· 5 years ago
c01b391
IVGCVSW-3007 ArmnnConverter: Fix bug with optional --input-tensor-shape argument
by Matthew Bentham
· 5 years ago
b855470
IVGCVSW-2657: Fix to force correct quantisation parameters for QASYMM8 Softmax
by David Monahan
· 5 years ago
04a8b05
IVGCVSW-3005 Correct the order of inputs and outputs of deepspeech v1
by Narumol Prangnawarat
· 5 years ago
3dcc1c6
MLCE-111: ONNX parser raw data bug
by Pablo Tello
· 5 years ago
d49b70f
IVGCVSW-2993: Investigate TfLite Parser test output shape validation
by Nina Drozd
· 5 years ago
672de57
IVGCVSW-2994 Add Reshape layer to ParseUnpack in TfLite parser
by Narumol Prangnawarat
· 5 years ago
4a95611
Remove incorrect documentation line
by Matthew Bentham
· 5 years ago
a820e02
IVGCVSW-2657: New Mobilenet Timings test which includes quantisation and softmax
by David Monahan
· 5 years ago
dc27979
IVGCVSW-2657: Model update to fix failing timings test: TfLiteVGG16Quantized
by David Monahan
· 5 years ago
4de9f67
IVGCVSW-2918 Implement ExecutionFrame.
by Teresa Charlin
· 5 years ago
8271f81
IVGCVSW-2899 Create a tool to preprocess the images, generating the RAW tensor data from the image files
by Sadik Armagan
· 5 years ago
861985f
IVGCVSW-2925: Combine Pad with Convolution2d in the Optimizer
by Nina Drozd
· 5 years ago
17660e6
IVGCVSW-2987 Modify ParseSplit in TfLite parser
by Narumol Prangnawarat
· 5 years ago
7997a35
IVGCVSW-2980 Build ArmNN with the latest version of the driver stack library
by Matteo Martincigh
· 5 years ago
c2ebc63
IVGCVSW-2855 Update Command Line Processing of commonOptions
by Jim Flynn
· 5 years ago
4818d46
IVGCVSW-2849 Add TfLite Parser support for Rank-0 operands and unit tests
by Narumol Prangnawarat
· 5 years ago
0790dce
IVGCVSW-2957 MergerLayer subtensor optimization now backend agnostic
by Derek Lamberti
· 5 years ago
b98bbcf
IVGCVSW-2425 Add unit test for Logistic (Sigmoid) in NEON
by Narumol Prangnawarat
· 5 years ago
e571d33
IVGCVSW-2855 Create TfLite reference test for DeepSpeechV1
by Jim Flynn
· 5 years ago
aab6aff
IVGCVSW-2959: Update TfLiteResNetV2-50-Quantized-Armnn test
by Nina Drozd
· 5 years ago
507f39d
MLCE-103: MDK changes for running multiple inferences qasymm8
by Pablo Tello
· 5 years ago
472d4e0
IVGCVSW-2965: Add ResnetV2 50 Timings job in CI
by Nina Drozd
· 5 years ago
3e68b97
IVGCVSW-2928 Fix issue with GPU profiling
by Matthew Bentham
· 5 years ago
200e380
IVGCVSW-2848 - Add TfLite Parser support for Unpack layer
by Nina Drozd
· 5 years ago
b1390fc
IVGCVSW-2959 Update TfLiteResNetV2-50-Quantized-Armnn test
by nikraj01
· 5 years ago
2b03d64
IVGCVSW-2955 Update the Quantizer Tool to take an additional parameter for the user to specify a CSV file
by Sadik Armagan
· 5 years ago
7b4886f
IVGCVSW-2543 Add timing for ExecuteNetwork inference
by James Conroy
· 5 years ago
774f6f1
IVGCVSW-2912 Change get_compute_libary.sh -p exit code to 0
by Jim Flynn
· 5 years ago
7c23b33
IVGCVSW-2873 Update documentation for Serializer/Deserializer
by Sadik Armagan
· 5 years ago
d4f0fea
IVGCVSW-2947 Remove boost dependency from include/TypesUtils.hpp
by Aron Virginas-Tar
· 5 years ago
f30f7d3
IVGCVSW-2946 RefElementwiseWorkload configures prior to first execute
by Derek Lamberti
· 5 years ago
82fbe7c
IVGCVSW-2912 Make get_compute_library.sh sole source for clframework pin
by Jim Flynn
· 5 years ago
2999a02
IVGCVSW-2862 Extend the Elementwise Workload to support QSymm16 Data Type
by Sadik Armagan
· 5 years ago
9985176
IVGCVSW-2845: Add TfLite Parser support for TanH activation layer
by Nina Drozd
· 5 years ago
2e6dc3a
IVGCVSW-2861 Refactor the Reference Elementwise workload
by Sadik Armagan
· 5 years ago
0324f48
IVGCVSW-2844: Add TfLite Parser support for Split layer
by Nina Drozd
· 5 years ago
1b63d6c
IVGCVSW-2927 Fix Streamline annotations
by Matthew Bentham
· 5 years ago
eff363d
IVGCVSW-2914 Add Switch Layer and no-op factory method
by Sadik Armagan
· 5 years ago
1f88630
IVGCVSW-2915 Add Merge Layer and no-op factory method
by Nattapat Chaimanowong
· 5 years ago
647aab3
IVGCVSW-2926 Add test for ResNetV2 50 quantized tflite model
by nikraj01
· 5 years ago
bb190a6
IVGCVSW-2539 Improve ExecuteNetwork error logging
by Francis Murtagh
· 5 years ago
2fcce08
IVGCVSW-2802 Ability to run FP16 turbo mode through ExecuteNetwork
by Ruomei Yan
· 5 years ago
afa4e3a
IVGCVSW-2875 Enable QuantisedSymm16 support for ref Dequantize workload
by Nattapat Chaimanowong
· 5 years ago
a0beb3b
IVGCVSW-2872 Unit tests for Quantize layer and reference workload
by Nattapat Chaimanowong
· 5 years ago
2ab0bfa
IVGCVSW-2832 (Part 2) update clframework pin to b4a44ff3aa98d2b51f1621a7525db3f81108a1bd
by Jim Flynn
· 5 years ago
5f400d6
IVGCVSW-2871 Ref QuantizeLayer workload
by Derek Lamberti
· 5 years ago
8a54ac0
IVGCVSW-2875 Reference implementation and unit tests for Dequantize
by Nattapat Chaimanowong
· 5 years ago
317cae5
IVGCVSW-2866 Implement RegisterDebugCallback for RefDebugWorkload
by Nattapat Chaimanowong
· 5 years ago
83add21
MLCE-101 Deeplab v3+ (Add Tf Lite Parser Dilation Check)
by Kevin May
· 5 years ago
10e6be4
IVGCVSW-2885 fix ArmnnConverter help text
by Les Bell
· 5 years ago
e4294fd
IVGCVSW-2874 Add DequantizeLayer and no-op factory method
by Nattapat Chaimanowong
· 5 years ago
61f5463
IVGCVSW-2880 Refactor order of methods
by Derek Lamberti
· 5 years ago
8b6df4d
IVGCVSW-2827: adding Validation file for TfLiteInceptionV4Quantized
by Nina Drozd
· 5 years ago
87acb27
IVGCVSW-2870 Serialize quantize layer
by Derek Lamberti
· 5 years ago
a9cca6a
IVGCVSW-2870 Support QuantizeLayer on frontend
by Derek Lamberti
· 5 years ago
045ea78
IVGCVSW-2884:Add Validation.txt for TfliteInceptionV3
by nikraj01
· 5 years ago
5eb30d9
IVGCVSW-2817 Inherit SerializerVisitor from the ILayerVisitor interface class
by Francis Murtagh
· 5 years ago
964e955
IVGCVSW-2881 Remove DebugDescriptor
by Nattapat Chaimanowong
· 5 years ago
44db7c3
IVGCVSW-2832 Update CL pin to 2761c2f0b60175469e959982a25ff0abdca6c9ce
by Jim Flynn
· 5 years ago
313e1c8
IVGCVSW-2882 Fix include order in armnn public headers
by Matthew Bentham
· 5 years ago
47bfac4
IVGCVSW-2865 add missing include of functional
by Matthew Bentham
· 5 years ago
9fc8c0f
Use unique names for temporary files
by Matthew Bentham
· 5 years ago
ef38d5d
IVGCVSW-2861 Refactor the Reference Elementwise workloads
by Sadik Armagan
· 5 years ago
6e94820
IVGCVSW-2865 Extend IRuntime to add a new method RegisterDebugCallback(...)
by Nattapat Chaimanowong
· 5 years ago
2a304ed
IVGCVSW-2859 Add unit tests for QSymm16 quantization
by Nattapat Chaimanowong
· 5 years ago
11af375
IVGCVSW-2694: serialize/deserialize LSTM
by Jim Flynn
· 5 years ago
db059fd
IVGCVSW-2850 Fix Circular Dependency Issue
by Sadik Armagan
· 5 years ago
7ac07f3
IVGCVSW-2858 Add support for QSymm16 quantization
by Nattapat Chaimanowong
· 5 years ago
2a434a8
IVGCVSW-2814 AllTypesAreEqualImpl handles odd num params correctly.
by Derek Lamberti
· 5 years ago
50db4e8
IVGCVSW-2814 Extensive ref IsSupported for Activation & Addition
by Derek Lamberti
· 5 years ago
03acd68
IVGCVSW-2788 Modify Serializer test to use introspection API
by Nattapat Chaimanowong
· 5 years ago
cd5ac23
IVGCVSW-2839 Add QuantisedSymm16 support to the ArmNN frontend
by Nattapat Chaimanowong
· 5 years ago
2a326b5
MLCE-105 Fix use of std::unique_lock in LoadedNetwork
by Matthew Bentham
· 5 years ago
3e14a9d
IVGCVSW-2686 Add Serializer and Deserializer for DetectionPostProcess
by Nattapat Chaimanowong
· 5 years ago
65d3096
IVGCVSW-2354 Caffe SqueezeNet through armnn Cl and Neon
by Narumol Prangnawarat
· 5 years ago
222c753
IVGCVSW-2429 Add Detection PostProcess Parser to TensorFlow Lite Parser
by keidav01
· 5 years ago
232cfc2
IVGCVSW-2574 Create a converter application for all the supported ArmNN Networks
by Sadik Armagan
· 5 years ago
db7c391
IVGCVSW-2735 Failure to find flatbuffers is not a fatal build error
by Ruomei Yan
· 5 years ago
18ce338
IVGCVSW-2709 Serialize / de-serialize the Splitter layer
by Jim Flynn
· 5 years ago
1b4d7b1
IVGCVSW-2800 Update CL pin to latest master
by Conor Kennedy
· 5 years ago
b99480b
IVGCVSW-2792 Update Neon Mul/Sub workload for latest CL master
by Conor Kennedy
· 5 years ago
a6d45c7
IVGCVSW-2769 Don't process node if already visited
by Derek Lamberti
· 5 years ago
495701f
IVGCVSW-2693 Serialize/de-serialize L2Normalization
by Narumol Prangnawarat
· 5 years ago
ac25a1b
IVGCVSW-2697 Add Serialize/Deserialize for the Merger Layer
by Jim Flynn
· 5 years ago
d469faf
IVGCVSW-2783 Fix Deserializer connections for layer with multiple outputs
by Nattapat Chaimanowong
· 5 years ago
ac97c8c
IVGCVSW-2696 Serialize / de-serialize the Mean layer
by Sadik Armagan
· 5 years ago
c192f35
IVGCVSW-2689 Fix Floor Deserilizer discarding layer name
by Nattapat Chaimanowong
· 5 years ago
f81edaa
IVGCVSW-2691 Add Serialize/Deseralize Gather layer
by Matteo Martincigh
· 5 years ago
Next »