| Age | Commit message (Collapse) | Author | Files | Lines |
|---|
|
* [exo-tflite] Adding ReluConverter into convert_to_TFLNodes()
This adds ReluConverter and type/shape inference into convert_to_TFLNodes().
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* saturate -> restart
|
|
This will skip canonical nodes fix shapes that is done as loco service
- Pull and Push nodes are still called as they exist in import
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
This will fix SquaredDifferenceCanonicalizer to check input nodes shape
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
This will remove not used anymore ForwardShapeInferenceAlgorithm
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
This commit introduces bino, a library that facilitates std::pair
manipulation.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
Changing TODO list from (wrong) TFL node list to canonical node list.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This commit replaces all the loco::shape_get calls in ForwardShapeInferenceAlgorithm
implemention with "node_shape" method to facilitate refactoring.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
Let's reuse common test code.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
This will remove Canonical Concat IR test for axis
- Canonical IRs will not be handled in shape inference anymore
- Current Concat axis calculation is done in shape inference step
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
Add `dumpGraph` function as a future replacement of `IrDotDumper`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Return IVisitor as a strict version of Visitor
Propose to not use IVisitor outside of MIR component
Add missing includes and licenses
Signed-off-by: Efimov Alexander <a.efimov@samsung.com>
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Add missing include of `Visitor.h`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Add missing include of `Visitor.h`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Make `Shape` constructor explicit again.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Remove implicit conversions of strides to `Shape`.
Add helper functions to work with strides.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
This will enable UNIT_StopGradient_001 that is rank 4 test of StopGradient
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
This will enable UNIT_StopGradient_001 that is rank 4 test of StopGradient
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
TypeInferencePass annotates dtype of nodes (canonical/TFL/COp nodes).
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
* [exo-tflite] Introducing ProgressReporter listner
ProgressReporter is copied from moco-tf to print information before/after phase.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
* CI error -> remove unused parameter
|
|
This adds list of converters as TODO.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This adds slots for template initialization in CanonicalNodeConverter, which prevents code conflict.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This will return value from loco shape inference in ShapeInferencePass
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
This will revise import to use loco shape instead of ShapeInferenceData
- also add guards for safety
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
Now 1) TypeInference::to()returns bool 2) checks previously inferred dtype
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This converter converts loco::Relu to locoex::TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
The current implementation of FuseBinaryIntoPreceding gets stuck when
it encounters scalar constants.
Let's make FuseBinaryIntoPreceding skip on this case.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
The current implementation of CanonicalNodeSummaryBuilder implements its
own TensorShape formatter.
Let's replace this local formater with the shared one.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
LinearV1 Graph Formatter now shows domain if domain(shape) is known.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
This will run Shape and Type inference while TF dialect optimizations
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
|
|
ShapeInferencePass annotates shape of nodes (canonical/TFL/COp nodes).
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This adds type inference for TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This adds shape inferene for TFLRelu.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This includes CanonicalTypeInferenceRule check. This is required for future change of loco::TypeInference, which looks into the dtype of all input nodes. So, the type of loco::Pull should be inferred to infer the type of locoex::COpCall.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
* [moco-tf] Use ShapeInferenceData for rule
This will revise TFShapeInferenceRule infer to directly use ShapeInferenceData
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* change scope
|
|
(#7203)
This creates a slots for visit() of each TFL node.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
Currently, PermutingCodec internally declares TensorAxis alias.
Let's extract this as a separate header and reuse it!
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
This commit allows usersr to add multi-line comments to NodeSummary, and
revises LinearV1 Graph Formatter to show these comments properly.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
* Introduce tfts v0.1
This commit introduces TensorFlow Testcase Service (tfts) v0.1.
The current version supports basic shape check on TensorFlow testcases
through nnkit-tf.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
* Use simple tfts_check instead of tfts_shape_check
|
|
Instead of using TFLShapeAnnot and TFLTypeAnnot, we will have type and shape inference for each TFL Nodes. So these annot classes is removed.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
|
This helper is no longer meaningful.
Signed-off-by: Jonghyun Park <jh1302.park@samsung.com>
|
|
* [loco] Revise shape inference condition
This will add condition to ShapeInference to infer when target node shape is unknown and input(s) shape is ready
Signed-off-by: SaeHie Park <saehie.park@samsung.com>
* remove print code
|
|
Fixes compilation error of mobilenet.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` parameter of convolutional operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
Change the type of `strides` argument of `Conv2D` and `DepthwiseConv2D` operations to `vector<int32_t>`.
Signed-off-by: Sergei Barannikov <s.barannikov@samsung.com>
|
|
This introduce loco::BiasDecode, which translate Bias domain to Tensor domain.
Signed-off-by: Hyun Sik Yoon <hyunsik.yoon@samsung.com>
|
