[apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

## Problem TensorFlow is one of the most popular machine learning libraries and most developers are used to train/inference models with TensorFlow/TensorFlow Serving. TVM is the flexible compiler to run computation efficiently in different devices. Although TensorFlow has implemented some effic

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

The implementation of this proposal has been submit to https://github.com/apache/incubator-tvm/pull/4459 . Anyone can try to test their TVM operators by re-compiling TVM with `set(USE_TFOP ON)`. -- You are receiving this because you are subscribed to this thread. Reply to this email directly o

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

Thanks @jwfromm and you're definitely right. This is the fastest way to integrate TVM functions into TensorFlow if we can not convert the whole model to TVM. This may be meaningful for TensorFlow developers if they can to try TVM and leverage the sub-graph optimizaition from TVM. Actually this

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

Hi @tqchen @jwfromm @jroesch @soiferj , do you have any other comment? We may add more docs about implementation and usage so that everyone can know it works. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.c

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

The PR has been merged and we will close this issue. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-621593883

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

Closed #4464. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/4464#event-3287390519

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

@652994331 You should not `tftvm` which is deprecated and please rebuild TVM with `USE_TF_TVMSOOP=ON`. -- You are receiving this because you are subscribed to this thread. Reply to this email directly or view it on GitHub: https://github.com/apache/incubator-tvm/issues/4464#issuecomment-67390860

Re: [apache/incubator-tvm] [RFC] Add TVMDSOOp to integrate any TVM operator with TensorFlow (#4464)

@652994331 You need to install `tensorflow` so that TVMDSOOp could link to TensorFlow libraries. Here is the error message from your cmake. ``` ModuleNotFoundError: No module named 'tensorflow' ``` -- You are receiving this because you are subscribed to this thread. Reply to this email directl

[TVM Discuss] [Development] Add the document for TVMDSOOp

# Integrate TVM optimization into TensorFlow with TVMDSOOp ## Introduction In the next release of TVM(maybe 0.7), we have released the new feature called TVMDSOOp to integrate TVM optimization with TensorFlow. TVMDSOOp is the general custom operator for TensorFlow which can run any TVM optim

[TVM Discuss] [Development] Add the document for TVMDSOOp

We have add the document in discuss first and please help to review if you have time @tqchen @FrozenGene @zhiics @gmagogsfm . Hope to add in the official document when the content is ready. --- [Visit Topic](https://discuss.tvm.ai/t/add-the-document-for-tvmdsoop/6622/2) to respond. You a

[TVM Discuss] [Development] Add the document for TVMDSOOp

Thanks @zhiics and @FrozenGene . We have the Keras example with TVMDSOOp as well and we will update the document in google docs later which may help to review. --- [Visit Topic](https://discuss.tvm.ai/t/add-the-document-for-tvmdsoop/6622/6) to respond. You are receiving this because you