Gitiles
Code Review
Sign In
review.mlplatform.org
/
ml
/
ComputeLibrary
/
5daeffdd96c5e46ac2482431d578dfaf9b300cde
« Previous
8e1f3c0
COMPMID-1451 - Reduced dataset for YOLOLayer
by Gian Marco Iodice
· 6 years ago
8bab0ee
COMPMID-1584 - Collapse batch size in CLChannelShuffleLayerKernel
by Gian Marco Iodice
· 6 years ago
651540f
COMPMID-1451: Cleanup reference implementation
by Isabella Gottardi
· 6 years ago
3b6cdbb
COMPMID-1587: Automatically build examples from the 3rdparty/examples folder
by Anthony Barbier
· 6 years ago
16934a5
COMPMID-1227 Implementing Space to Batch on OpenCL
by Michalis Spyrou
· 6 years ago
0dd2391
COMPMID-1451: Move DragonBench tests with bias to nightlies
by Georgios Pinitas
· 6 years ago
952aeb1
COMPMID-1551: NEWinograd 1x3 and 3x1 mismatches.
by Pablo Tello
· 6 years ago
148b075
COMPMID-1563: Added a tag to ISCheduler::run_workloads to identify workloads
by Anthony Barbier
· 6 years ago
7302302
COMPMID-1539 Implement YOLOLayer on CL
by Giorgio Arena
· 6 years ago
555d110
COMPMID-1577: Add NormalizePlanarYUVLayer to graph API
by Michele Di Giorgio
· 6 years ago
c98b990
COMPMID-1451 Fix YOLOv3 android compilation issue
by Michalis Spyrou
· 6 years ago
a53a7bb
[MLCE-54] graph_alexnet example throw an exception
by Michele Di Giorgio
· 6 years ago
000d33a
COMPMID-1552: support kernels sizes 1x7, 7x1, 1x5, 5x1 in NEWinograd
by Pablo Tello
· 6 years ago
e70ebc1
COMPMID-1451: Add QASYMM8 in DragonBench
by Georgios Pinitas
· 6 years ago
177a9a5
COMPMID-1460 Create Yolo v3 graph example
by Michalis Spyrou
· 6 years ago
00809e3
COMPMID-1451 Move NEFlattenLayerKernel to the correct folder
by Michalis Spyrou
· 6 years ago
23e2479
COMPMID-1556 - Add ReorgLayer to graph API
by Gian Marco Iodice
· 6 years ago
fd7e853
COMPMID-1451: Print output quant info
by Georgios Pinitas
· 6 years ago
7cd7021
COMPMID-1555: Fix mismatch in EqualizeHistogram function
by Michele Di Giorgio
· 6 years ago
efbf6c8
[COMPMID-386] Github: Support SoftmaxLayer on different number of dimensions?
by giuros01
· 6 years ago
477531c
COMPMID-1527 - Implementing ReorgLayer on OpenCL
by Gian Marco Iodice
· 6 years ago
4854fc3
COMPMID-1538: DragonBench queries
by Georgios Pinitas
· 6 years ago
e1a352c
COMPMID-1333: Add CLSplit
by Georgios Pinitas
· 6 years ago
b3309e6
[COMPMID-1482] Auto-initialize the output tensor of im2col and col2im in NEGEMMConvolutionLayer
by Giuseppe Rossini
· 6 years ago
09d3451
COMPMID-1548: NEON FP16 mismatches on CannyEdge and HarrisCorners.
by Georgios Pinitas
· 6 years ago
b57be0d
COMPMID-1330: Add support for NormalizePlanarYUV operator in CL
by Michele Di Giorgio
· 6 years ago
a34286e
COMPMID-1553: Add GPU detection for G52.
by Georgios Pinitas
· 6 years ago
71ecf39
COMPMID-1266 : support for FP16 in CLWinogradConvolutionLayer
by Vidhya Sudhan Loganathan
· 6 years ago
553b999
COMPMID-1517 - Add validate method to CLScale
by Isabella Gottardi
· 6 years ago
aa6a04a
COMPMID-1528: Add ReorgLayer on NEON
by Georgios Pinitas
· 6 years ago
72686fa
COMPMID-1550: Winograd integrate RSH changes.
by Pablo Tello
· 6 years ago
0d2b48c
COMPMID-1451: Add FP16 on NEON DragonBench
by Georgios Pinitas
· 6 years ago
565bf2d
COMPMID-1514: Add validate to NEFloor and CLFloor
by Georgios Pinitas
· 6 years ago
bda6e4b
COMPMID-1247:Integrate kernel size 1x3 & 3x1 support in NEWinogradLayer.
by Pablo Tello
· 6 years ago
238c97c
COMPMID-1451: Fix misssing comment in helpers.h
by Georgios Pinitas
· 6 years ago
c1a7245
COMPMID-1332: Implement Slice for CL
by Georgios Pinitas
· 6 years ago
6a8d3b6
COMPMID-1218 Implementing Batch to Space on OpenCL
by Michalis Spyrou
· 6 years ago
da19dab
COMPMID-1547: HarrisCorner's validation output spams the log file
by Georgios Pinitas
· 6 years ago
87e896a
[COMPMID-1353] Add support for 4D Softmax layer on OpenCL
by Giuseppe Rossini
· 6 years ago
e3d24ce
COMPMID-708 Fix AccessWindowTranspose
by Giorgio Arena
· 6 years ago
427bbbf
COMPMID-1522: Add ElementWiseOperation node in the graph API
by Georgios Pinitas
· 6 years ago
ea9e0dc
COMPMID-1469: Add validate in NEGEMMMatrixAdditionKernel
by Georgios Pinitas
· 6 years ago
8479763
[COMPMID-1483] Add validate method to CLReshapeLayer
by Giuseppe Rossini
· 6 years ago
77589b5
COMPMID-1235: Implements StridedSlice for CL
by Georgios Pinitas
· 6 years ago
2aa0ec4
COMPMID-1246 Fix mobilenet QASYMM8 on CL
by Giorgio Arena
· 6 years ago
3e570db
COMPMID-1304: NEDepthConvert : Add support for FP32 -> FP16 and FP16 -> FP32 + validate() function
by Michele Di Giorgio
· 6 years ago
daa3855
COMPMID-1433: Use Arm macro to check whether we support dot product instructions
by Georgios Pinitas
· 6 years ago
50c4b4f
COMPMID-1091: Disabled git-lfs in data repo
by Anthony Barbier
· 6 years ago
1c28ab4
COMPMID-1543: Unable to include ImageLoader.h in multiple object files
by Anthony Barbier
· 6 years ago
cf3fe94
COMPMID-1545: Fix FP16 CLRNNLayer mismatches
by Michele Di Giorgio
· 6 years ago
b79b5d4
COMPMID-1545: Fix FP16 CLRNNLayer mismatches
by Michele Di Giorgio
· 6 years ago
6513ccb
COMPMID-1544: Update linux toolchains in doxygen
by Michele Di Giorgio
· 6 years ago
3783116
COMPMID-1474: Automatically generate DragonBench benchmarks
by Georgios Pinitas
· 6 years ago
6a90b69
[COMPMID-1301] Add validate() method to NEReshapeLayer
by Giuseppe Rossini
· 6 years ago
d8b8be2
COMPMID-1091: Switch to use git.research.arm.com for data submodule
by Anthony Barbier
· 6 years ago
419f33a
COMPMID-1542: Nightly: NEON and CL FullyConnectedLayer FP32 mismatches
by Michele Di Giorgio
· 6 years ago
4dbc0a9
COMPMID-1541: Remove dependency on tests/ headers in utils/TypePrinter.h
by Anthony Barbier
· 6 years ago
226e4b9
COMPMID-1470 Add auto-init of the output in NECol2im
by Giorgio Arena
· 6 years ago
35aea37
COMPMID-1534 - Fixed GEMMDilated and FullyConnected tests for FP16
by Gian Marco Iodice
· 6 years ago
e6bb3c6
COMPMID-1533 Implementing CLDepthWiseConvolutionLayer with FP16 (NHWC)
by Giorgio Arena
· 6 years ago
32963c6
COMPMID-1534 - Fix tolerance issue in Normalization Layer test for FP16
by Gian Marco Iodice
· 6 years ago
0e72c69
COMPMID-1246: Always re-generate arm_compute_version.embed
by Anthony Barbier
· 6 years ago
9fb6c7e
COMPMID-1529 Optimize PoolingLayer NHWC on NEON
by Giorgio Arena
· 6 years ago
fb62908
COMPMID-1494 Optimise NEON im2col and weights reshape for NHWC
by Giorgio Arena
· 6 years ago
66cbafb
COMPMID-1246 Fix NEON mobilenet NCHW
by Giorgio Arena
· 6 years ago
fbf3ecc
COMPMID-1534 - Fix GEMM and Magnitude test for FP16
by Gian Marco Iodice
· 6 years ago
1fa17c2
COMPMID-1246: Print arguments passed to the tests / benchmarks
by Anthony Barbier
· 6 years ago
cedb78f
COMPMID-1536: Github PR: Removed redundant const qualifier on cast
by Kohei Takahashi
· 6 years ago
ba1ffe9
COMPMID-1537: Fix weights retention in CLFullyConnectedLayer
by Michele Di Giorgio
· 6 years ago
3ada2b7
COMPMID-1534: Fix LSTM/RNN Layers for NEON and FP16
by Georgios Pinitas
· 6 years ago
f2cde9b
COMPMID-1534 - Fix NENormalizationLayer for FP16
by Gian Marco Iodice
· 6 years ago
13d96e0
COMPMID-1534: Fix 2x2 NEPoolingLayer for FP16
by Georgios Pinitas
· 6 years ago
41acb76
COMPMID-1534 - Fixing FP16 tests on NEON
by Gian Marco Iodice
· 6 years ago
02baf01
COMPMID-1521: Update doxygen for 18.08
by Michele Di Giorgio
· 6 years ago
cdd68c0
COMPMID-1534: Prevent graphs with missing NEON F16 features from running
by Anthony Barbier
· 6 years ago
31fa0d6
COMPMID-1534: Fix NESoftmaxLayer for FP16
by Georgios Pinitas
· 6 years ago
3463a8b
COMPMID-1534: Fix NEActivationLayer for FP16
by Georgios Pinitas
· 6 years ago
2113b9d
COMPMID-1246: Don't call CLFinish at the end of benchmark / validation if opencl is not available
by Anthony Barbier
· 6 years ago
890ad1b
COMPMID-1246: Fix bug in handling backends that can't be loaded in the Graph API
by Anthony Barbier
· 6 years ago
aaba4c6
COMPMID-1188: Add support for activation in NEBatchNormalization.
by Georgios Pinitas
· 6 years ago
630d941
COMPMID-1246: Cleaned up 3rdparty folder and updated data folder (3RDPARTY_UPDATE)(DATA_UPDATE)
by Anthony Barbier
· 6 years ago
8a04211
COMPMID-1188: Revert change to DummyAccessor, fixed NPY and Image loaders
by Anthony Barbier
· 6 years ago
80040bc
COMPMID-1246: Check OpenCL is available before re-creating the CL Context and Queue
by Anthony Barbier
· 6 years ago
84cb75d
COMPMID-1524 - Release Branch: CL GEMMDilatedConvolutionLayer FP16 mismatches
by Gian Marco Iodice
· 6 years ago
a7cbc74
COMPMID-1188 - Fixed DummyAccessor
by Gian Marco Iodice
· 6 years ago
368e635
COMPMID-1047 Extract Flatten function from Im2Col for NEON
by Giorgio Arena
· 6 years ago
125bb5b
COMPMID-1144:(3RDPARTY_UPDATE)(DATA_UPDATE) Add DragonBench Headers
by Georgios Pinitas
· 6 years ago
be2772a
COMPMID-1508: Add Inception ResNet V2 model
by Georgios Pinitas
· 6 years ago
6c95c2d
COMPMID-1188: Static tuning of CLScale
by Georgios Pinitas
· 6 years ago
1049020
COMPMID-1188: Set all arguments to const in NEDepthwiseConvolutionLayer::validate()
by Georgios Pinitas
· 6 years ago
bcafc4d
COMPMID-1486 - CLGEMMDilatedConvolutionLayer FP16 / FP32 failing in nightlies
by Gian Marco Iodice
· 6 years ago
2a2db59
COMPMID-1505: Add native grouping support at graph level
by Georgios Pinitas
· 6 years ago
c1961b5
COMPMID-1509: (Nightly) CLDeconvolution fails for QASYMM8
by Michele Di Giorgio
· 6 years ago
25f45a4
COMPMID-1060 LSTM FP32 NEON
by Michalis Spyrou
· 6 years ago
26b2216
COMPMID-1480 Add support for NHWC QASYMM8/FP32(non-optimized) to NEON DepthwiseConvolution
by Giorgio Arena
· 6 years ago
bc92a34
COMPMID-1188: Fix subtensor check
by Georgios Pinitas
· 6 years ago
1d38259
COMPMID-1366 Implement NECopy
by Michalis Spyrou
· 6 years ago
3941295
COMPMID-1506 NPY Loader doesn't work for NHWC pipelines
by Michalis Spyrou
· 6 years ago
d30714a
COMPMID-1188 - Fix CLWinogradConvolutionLayer for NHWC
by Gian Marco Iodice
· 6 years ago
1b65807
COMPMID-1188 - Enabled NHWC in graph_squeezenet_v1 for NEON
by Gian Marco Iodice
· 6 years ago
Next »