Comments (4)
Good catch!
The model has multiple "root" nodes which is not handled yet by the backend. This is an extract of the model rendered with netron:
Two things to do:
- setting a more explicit error message
- implement the feature
I will split this into two issues.
from onnx-go.
I am changing the title of this issue; I have created a "project" to follow the implementation steps to make the SSD model working.
Note: I have analyzed the model, and it will require a lot of effort to make it work with gorgonia.
from onnx-go.
There is a work-in-progress with the branch issue-48 but it needs some more investigation.
The actual design of "gorgonnx" does not handle operators with multiple output.
the signature of the apply method will probably require some changes:
type operator interface {
// apply analyse the graph to find the children of the node
// then extract its gorgonia.Node references
// and assign the result of the operation to the node n
apply(g *Graph, n *Node) error
// init the operator with name and attributes as carried by the onnx.Operator
init(o onnx.Operation) error
}
from onnx-go.
PR #115 fixes this error, but it introduces a breaking change.
The OperationCarrier
interface needed to be changed to handle nodes with multiple outputs.
Lines 19 to 27 in f9baf80
This will require to change any backend implementation.
As far as I know, the only backend implemented so far is Gorgonia (via gorgonnx), and it has been patched.
from onnx-go.
Related Issues (20)
- IR used by onnx-go is several version behind onnx HOT 2
- Implement operator PRelu for backend Gorgonia
- Implement operator pRelu for backend Gorgonia
- Failed to infer shape. Op: A ร Bแต: Inner dimensions do not match up HOT 2
- Implement operator `Gather` for backend `Gorgonia` HOT 3
- Cannot model.UnmarshalBinary - says 'No data found' HOT 1
- Can't import onnx model, converted from BigGAN-PyTorch HOT 2
- Implement operator LSTM,Clip for backend Gorgonia HOT 1
- Will this project be maintained further and are contributions still welcomed?
- Implement operator `LinearRegressor` for backend `gorgonia`
- "Asymmetric padding" error
- panic: negative dimension size does not make sense
- ../../go/src/gorgonia.org/tensor/dense_compat.go:442:23: undefined: array.Interface HOT 2
- Updated depens
- poor performance (run model)
- run() function calls newMachine() everytime HOT 1
- Question: unsqueeze: axes in not an []int64 HOT 3
- Support for empty tensors
- Tape machine does not reset properly for some models HOT 2
- Implement operator `PReLU` for backend `Gorgonia`
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
๐ 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. ๐๐๐
-
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 โค๏ธ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from onnx-go.