### Author:  [@agibsonccc](https://community.konduit.ai/u/agibsonccc)
#### Post date: [October 4, 2021, 12:47am UTC](https://community.konduit.ai/t/onnx-import-fails/1626/3 "2021-10-04T00:47:04Z")
@craig88 I added Unsqueeze can be found here:
>
if you’d like you can pull my branch and test it if you’d like. I am adding quite a few ops in this pull request but unsqueeze should be there for you.
That or I can try to convert your model for you if you can DM me your model.
---
### Author:  [@craig88](https://community.konduit.ai/u/craig88)
#### Post date: [October 4, 2021, 6:59pm UTC](https://community.konduit.ai/t/onnx-import-fails/1626/4 "2021-10-04T18:59:27Z")
> [@craig88](#):
>
> onnxFrameworkImporter
Is this via the pom? doesn’t seem to be working:
```auto
org.nd4j
samediff-import-onnx
d5ee31d8c8
```
Here is the [onnx model](https://wildwebwidget.com/temp/shapen_hf_bigbird.zip), it’s just a smoketest.
---
### Author:  [@agibsonccc](https://community.konduit.ai/u/agibsonccc)
#### Post date: [October 5, 2021, 12:01am UTC](https://community.konduit.ai/t/onnx-import-fails/1626/5 "2021-10-05T00:01:10Z")
@craig88 No…where did you get that so I can fix it? It should just be 1.0.0-SNAPSHOT or the latest version 1.0.0-M1.1
---
### Author:  [@craig88](https://community.konduit.ai/u/craig88)
#### Post date: [October 5, 2021, 2:54pm UTC](https://community.konduit.ai/t/onnx-import-fails/1626/6 "2021-10-05T14:54:55Z")
Sorry new to Maven; had the naive notion I could use your github branches/tags in the POM dependency. Anyway I’ll wait till the updates are officially released; can use the onnxruntime until then.
---
### Author:  [@agibsonccc](https://community.konduit.ai/u/agibsonccc)
#### Post date: [October 6, 2021, 2:03am UTC](https://community.konduit.ai/t/onnx-import-fails/1626/7 "2021-10-06T02:03:35Z")
@craig88 could you clarify? We have the nd4j-onnxruntime bindings that will allow an easy transition. I’m not sure if you saw those:
> **[deeplearning4j/nd4j/nd4j-onnxruntime at master · eclipse/deeplearning4j](https://github.com/eclipse/deeplearning4j/tree/master/nd4j/nd4j-onnxruntime)**
>
> master/nd4j/nd4j-onnxruntime
For your maven setup, I would seriously consider reading a quickstart to make sure you understand the basics. It won’t take long and will save you lots of headaches and unnecessary detours in the future.
[https://maven.apache.org/guides/getting-started/maven-in-five-minutes.html](https://maven.apache.org/guides/getting-started/maven-in-five-minutes.html)
You can only pull maven dependencies from a maven repository (maven central by default) You can’t just pull random git commits. Those commits and versions have to be manually set and deployed by the library to maven central or a maven repository.
Beyond that, yes you can once this is merged to master.
In order to embed the unsqueeze implementation I wrote, all you have to do is declare the annotations as listed in the docs there and put it in your project.
That won’t be necessary after this is merged to master since it will be available by default.
There are other ops (sometimes custom to pytorch or other frameworks or even one off ops implemented in research papers) where you need to do the same thing and declare the dependencies in your project in order for it to work. That would allow you to just add a shiv to the import without the need to change the dependencies.
That or again if you want, you can just DM me your model and I’ll convert it for you.
After that you don’t even need the model import framework. It will be converted to our flatbuffers format which you can then load with Samediff.load(…)
If you want to use the new changes after it’s merged tp master then that’s called snapshots. You just specify 1.0.0-SNAPSHOT with the snapshots repository. You can find that here:
> **[Snapshots](https://deeplearning4j.konduit.ai/multi-project/explanation/snapshots)**
>
> Using daily builds for access to latest Eclipse Deeplearning4j features.
---
### Author:  [@craig88](https://community.konduit.ai/u/craig88)
#### Post date: [October 6, 2021, 5:10pm UTC](https://community.konduit.ai/t/onnx-import-fails/1626/8 "2021-10-06T17:10:20Z")
I put in the [Unsqueeze](https://github.com/eclipse/deeplearning4j/blob/d5ee31d8c86136c657d562152fcb152727f39395/nd4j/samediff-import/samediff-import-onnx/src/main/kotlin/org/nd4j/samediff/frameworkimport/onnx/definitions/implementations/Unsqueeze.kt) Op and the [op defs](https://github.com/eclipse/deeplearning4j/blob/master/nd4j/samediff-import/samediff-import-onnx/src/main/kotlin/org/nd4j/samediff/frameworkimport/onnx/definitions/OnnxOpDeclarations.kt) but it is not liking the function signature:
```auto
override fun preProcess(
op: SameDiffOp,
sd: SameDiff,
attributes: Map,
descriptor: OpNamespace.OpDescriptor,
outputNames: List,
isFinalOutput: Boolean
): HookResult {
```
it likes this signature:
```auto
override fun preProcess(
op: SameDiffOp,
sd: SameDiff,
attributes: Map,
descriptor: OpNamespace.OpDescriptor): HookResult {
```
I’m using: 1.0-SNAPSHOT
---
### Author:  [@agibsonccc](https://community.konduit.ai/u/agibsonccc)
#### Post date: [October 6, 2021, 10:19pm UTC](https://community.konduit.ai/t/onnx-import-fails/1626/9 "2021-10-06T22:19:38Z")
@craig88 We just merged some changes to master that updates the signature. That is the old one. For Unsqueeze it should work fine.
---
### Author:  [@agibsonccc](https://community.konduit.ai/u/agibsonccc)
#### Post date: [October 13, 2021, 1:07pm UTC](https://community.konduit.ai/t/onnx-import-fails/1626/10 "2021-10-13T13:07:48Z")
@craig88 JFYI snapshots should have this now if you want to try it.