aboutsummaryrefslogtreecommitdiff
path: root/ethosu/vela/tflite_graph_optimiser.py
AgeCommit message (Collapse)Author
2022-04-21MLBEDSW-5384 FC layers run on NPU if underlying shape is 2DAyaan Masood
*Added generic function which checks if underlying shape of FullyConnected operation is 2D and performs shape reduction *Fully connected operation >2 dimensions now run on NPU if the above case is satisfied *constraint_fc_output_2d and rewrite_fully_connected_input refactored *Added unit test to confirm this functionality Signed-off-by: Ayaan Masood <Ayaan.Masood@arm.com> Change-Id: I0e29c767e5b84841eb53bbc44464b36a454f7b38
2022-04-20MLBEDSW-6407: Vela fails with TypeError in npu_performanceTim Hall
- This is due to calling range() on a non-integer value which in turn is due to a change in the behaviour of round() on numpy.float64 values - The fix is to always force the output of the round() to be an integer and thereby stop whole number floating point values propagating into the kernel dimensions which later feed into the range(). Signed-off-by: Tim Hall <tim.hall@arm.com> Change-Id: Ic75cb6ba85a90c81c1d762067d89a10caaa13b92
2022-03-30Update version of Black to 22.3.0Jonas Ohlsson
Update version of Black to 22.3.0 due to updated dependencies. Updates to fix reported issues due to new version. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: I60056aae452093ce8dcea1f499ecced22b25eef1
2022-03-21MLBEDSW-6298: MLCE: Unable to find a valid block configTim Hall
- Fixed a bug due to ResizeBilinear modifying the attributes of a shared IFM - The ifm_resampling_mode is now an attribute of an operator rather than a tensor - Changed all calls to try_block_config() to use the attribute rather than recalculating it in multiple places Signed-off-by: Tim Hall <tim.hall@arm.com> Change-Id: I4641e9cd6b049bd4186776d98e3e751c5e5bcc06
2022-03-17MLBEDSW-5332: Bug fix optimise_strided_convLouis Verhaard
Added check that horizontal padding is unaffected when applying graph optimization "optimise_strided_conv". Signed-off-by: Louis Verhaard <louis.verhaard@arm.com> Change-Id: I7032a44163e300cdf62cf615b4b10a1417e38eaa
2022-03-11Vela: Fix diff in mean opDiqing Zhong
- Extend ifm/ofm dimensions explicitly in mean op This fix a bug when ifm/ofm shape has different dimensions e.g. IFM=1x19x18x25 axis=2 OFM=1x19x25, the ofm_shape should be 1x19x1x25, not 1x1x19x25 - Fix wrong weight shape Change-Id: I269eb71ea56c09deee2aa6c6433d9b2baa98a113 Signed-off-by: Diqing Zhong <diqing.zhong@arm.com>
2022-02-24MLBEDSW-6247: MLCE: Issue when running a model with PaddingTim Hall
- The bug is that TransposeConv does not support explicit padding which is needed in order to combine it with a proceeding Pad op - The fix is to exclude such combination Signed-off-by: Tim Hall <tim.hall@arm.com> Change-Id: Ide03d034dc32b5fc9bcaaf291ab713482223a042
2022-02-02MLBEDSW-3623: Diff on semantic_segmentationRickard Bolin
The root cause of this diff is precision errors caused by rounding several times when performing a resize bilinear upscaling to more than twice the initial size. This is solved by rewriting the algorithm to perform nearest neighbour upscaling to the correct size and then applying one larger average pool instead of several 2x2 pools. Avgpool with padding is limited to kernel size 8x8, which constraints the largest possible bilinear upscaling to 8 times the input size. Signed-off-by: Rickard Bolin <rickard.bolin@arm.com> Change-Id: I846232f309ba26aab6c385e593cbe25b646c6668
2021-12-20MLBEDSW-5844: Inconsistent calculation of read shapesTim Hall
- This bug causes a regression in the use of unpack and split operators - The bug is due to the read_shapes attribute being an absolute calculation for slice and strided_slice, but a relative one for unpack and split - The fix is to consistently treat the attribute as a shape relative to the read_offset Signed-off-by: Tim Hall <tim.hall@arm.com> Change-Id: I4504b161be507ea22ca6ee40fbe7808bfe049405
2021-12-16MLBEDSW-5554: Place MEAN op exceeding max height with axis==1 on CPURickard Bolin
Signed-off-by: Rickard Bolin <rickard.bolin@arm.com> Change-Id: I87dc5963972a7ef91db467b2ff8e0261e9899372
2021-11-05MLBEDSW-5209 Vela: output diff depthwise with non-zero zero pointsFredrik Svedberg
Fixed by adjusting zero points for ops with int8 IFM and asymmetric weights since the reference does not support asymmetric weights for int8 IFM and ignores the zero points. Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com> Change-Id: I2a206a01a471a53aa864a6a3616aa23d2a5a23c8
2021-10-28MLBEDSW-5440 MLCE: Vela crashing due to mismatch in padding shape in OFMJames Ward
Change convert_pad optimiser to use op.ifm_shapes attribute in place of the fickle op.ifm.shape (which in this case had changed due to the optimised-out reshape) Signed-off-by: James Ward <james.ward@arm.com> Change-Id: I13fbd846ac8d3342afd7844d1041cfa15aaae124
2021-10-13MLBEDSW-5315 MLCE: Vela to handle skip TensorFredrik Svedberg
Removed graph optimizations no longer needed that caused problems with FullyConnected operators running on CPU being consumed by elementwise operators in Vela. Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com> Change-Id: Ic7e66141ccd5e9aa8f0022c5ab9e7fd1ba3f6786
2021-09-15TOSA: Support for TABLE operator (int8)Patrik Gustavsson
Added support to map TABLE operator to LUT. Limitations: -Only supported for int8 -TABLE input must be constant This also adds the support for TFLite legalisation of Tanh/Sigmoid (int8/uint8). Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I1a95f61fb02fdd42c4a690494418cc0765c8b275
2021-09-15MLBEDSW-5102 Update removal of memory only operatorsJonas Ohlsson
Memory only operators such as Reshape, Squeeze and ExpandDims are removed in the graph optimiser step. - Added semantic check that memory only operators have same quantisation parameters on ifm/ofm. - Added support for the ExpandDims operator. - Addition and cleanup of related unit tests. - Removed TOSA from the generated SUPPORTED_OPS.md documentation. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: If848d8afc58c18806e10997ed94e4dae83f30879
2021-09-15MLBEDSW-5052 Fix RELU scalingFredrik Svedberg
Fixed scaling for RELUs with different IFM/OFM scaling. Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com> Change-Id: I0ac96326b3960c0fb025b885e06a259d24b2e684
2021-09-07TOSA: Added RESHAPE, SLICE and CONCATPatrik Gustavsson
Added support for Data layout ops RESHAPE, SLICE and CONCAT. -No support for bool_t -Support limited to Rank <= 4 and N = 1 Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I487ac494b6506a2a6ba947ee758aa193194dd796
2021-09-03TOSA: Added Depthwise supportPatrik Gustavsson
This is mainly to add support for depthwise conv2d with dephmultiplier = 1. (But there are no testcases suited, all I have sourced has depth_multiplier set to 2, which is not supported.) -Added support for depthwise conv2d. -Added support for removing Transpose of constant data -Added support for removing reshape Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I143e6246becfa78fd9f7510af0bf0d6b3fbbf2c7
2021-09-03MLBEDSW-5056 Output diff wav2letter (int16)Fredrik Svedberg
Fixed output diff for wav2letter int16 by correcting the scaling used for LeakyRelu. Signed-off-by: Fredrik Svedberg <fredrik.svedberg@arm.com> Change-Id: I8be1e14c25d223dc6e42c4ec498ff4d3d9de65d7
2021-09-03TOSA: Support for AVGPOOL, MAXPOOL and CONV2DPatrik Gustavsson
Added support for -AVGPOOL and CONV2D with TFLite correspondence -MAXPOOL -additional support for replacing RESCALE ops with avgpool. No support for breaking down tensors over the size supported by NPU. Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: I1d2aa50ac30a26283b3e6f1fe88cba1544b7c189
2021-08-25Handle sg input and output for Squeeze operator3.1.0.rc2Jonas Ohlsson
Update to handle the case when the Squeeze Op ifm/ofm are the subgraph ifm/ofm, to facilitate the removal of the Squeeze Op. Adding NOP to maintain the original tensors. Updated pytests for squeeze operator. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: I623cae05e696fb16ccf29dedc42fd822601e9fd9
2021-08-23MLBEDSW-4913 Fix inception_v1/v3 output diffJonas Ohlsson
Fix inception_v1/v3 output diffs. Removing the Squeeze operator in the graph optimisation step. The squeeze operator removes dimensions of size 1 from tensor shape. The memory layout is preserved. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: I4ceffcbb141af5ed50b0d1a9d1d67622e638c2a1
2021-07-28MLBEDSW-4974: create_const_tensor invalid argumentTim Hall
- Fix bug with MEAN ops calling create_const_tensor using the quant_value_dtype keyword argument. Signed-off-by: Tim Hall <tim.hall@arm.com> Change-Id: I8cff542ae840fb110ea97c0cc86bb761d5a884d3
2021-07-27MLBEDSW-4853: Refactor supported operatorsJonas Ohlsson
Refactor supported operators by breaking out model semantics into its own class. Model semantics checked right after model read. Signed-off-by: Jonas Ohlsson <jonas.ohlsson@arm.com> Change-Id: If442b189efcd91dda01af60b2b3adedfacdf2fad
2021-07-26MLBEDSW-4892: Fix crash affecting biases without quantization.James Peet
Remove quant_values attribute from Tensor class. It only needs a single values attribute, holding either quantized or unquantized values as appropriate. Change-Id: Ie96f80ac58061b6077e0f7048dc60209fdfbcafa Signed-off-by: James Peet <james.peet@arm.com>
2021-07-08MLBEDSW-4838 Added basic TOSA support.Patrik Gustavsson
Added basic TOSA support, enabling Vela to read and compile a .tosa file corresponding to CONV2D + Rescale + Clamp, and writing it to an optimized .tflite file. The optimized .tflite file, will in this case, hold a commandstream where the Rescale and Clamp has been fused into the CONV2D. The optimized tflite file is not output from Vela. -Added support to read .tosa file into Vela internal structure. - Added tosa_reader.py, tosa_mapper.py and helper files stored under tosa/ - Support for this limited to ~10 ops -Added reader_util.py for functions common for TOSA and TFLite -Added tosa_graph_optimiser.py -Added support to fuse Rescale into convolution -Modified handling for padding -Added support to fuse Clamp to previous op -Added graph_optimiser_util.py -Moved functions common for TOSA/TFLite graph optimization to this file. -Renamed graph_optimiser.py to tflite_graph_optmiser.py -Added separate tosa_supported_operators.py -Added supported_operator_util.py -For functions in common for TOSA/TFLite Signed-off-by: Patrik Gustavsson <patrik.gustavsson@arm.com> Change-Id: Ic3c540504ec8c5eb4771397fdc6882050ecf33ab
generated by cgit v1.2.1 (git 2.23.0) at 2024-07-10 16:28:15 +0000