Comments (1)
tracyn-arm
commented on May 27, 2024
The Gather operator in the Compute Library used by Arm NN will build the output shape in a specific way:
The docs for arm_compute::misc::shape_calculator::compute_gather_shape() are:
/** Calculate the gather output shape of a tensor
*
* @param[in] input_shape Input tensor shape
* @param[in] indices_shape Indices tensor shape. Only supports for 2d and 3d indices
* @param[in] actual_axis Axis to be used in the computation
*
* @note Let input_shape be (X,Y,Z) and indices shape (W,O,P) and axis 1
* the new shape is computed by replacing the axis in the input shape with
* the indice shape so the output shape will be (X,W,O,P,Z)
*
* @return the calculated shape
*/
In the failing case provided, we have:
* @note Let input_shape be [1,40,20,4] and indices shape [1] and axis 3
* the new shape is computed by replacing the axis in the input shape with
* the indice shape so the output shape will be [1,40,20,1]
This results in the generated error where: [1,40,20] != [1,40,20,1] as Arm NN is conforming to the requirements of the library it uses and failing on the output tensor shape that was set in the model.
from armnn.
Related Issues (20)
- Gather operator dimension check error HOT 10
- Armnn insert reshape node before fullyconnected HOT 4
- I want config the gpu core number for armnn HOT 3
- Explicit padding for Transpose Convolution fails HOT 8
- opencv failed to call opencl HOT 1
- ScatterND not support HOT 3
- Building ARM NN via Docker approach with specific GLIBC , GLIBCXX versions ... HOT 3
- Link error on older Android devices HOT 8
- BUG: using delegate with transformer | AttributeError: 'NoneType' object has no attribute 'c_void_p' HOT 22
- About the configuration setting of externalMemoryManagementEnabled HOT 1
- The mali gpu computation capability is only used no more than 15% when inference resnet50 with ArmNN HOT 1
- onnx deployment fail HOT 7
- Another error on another model and by now it's two out of three :( HOT 22
- Unsupported Operation "Transpose" in armNN::OnnxParser while loading the onnx model file (in the goal to run inference) HOT 8
- Build Issues -Werrors on armbian 24 HOT 1
- nvalid attempt to construct ConstTensor from non-constant TensorInfo HOT 1
- Profiler service warnings seen in ArmNN v24.02 HOT 3
- Does ExecuteNetwork support "GpuAcc" runtime ? HOT 10
- Running YOLOv5 ONNX model with onnx parser of armnn fails with unsupported operation HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from armnn.