Reshape inputs size should be compatible

[wincle]

Hi , I have facing one problem , I'm running the "Compile Tensorflow Models" tutorial demo code, it's okay with the given model which is InceptionV1 from "https://github.com/dmlc/web-data/tree/master/tensorflow/models/InceptionV1" , But when I test my model which is InceptionV4, it brings Error as follow:
nnvm._base.NNVMError: Error in operator prefix/InceptionV4/Logits/PreLogitsFlatten/flatten/Reshape: [09:00:52] /tvm/nnvm/src/top/tensor/transform.cc:649: Check failed: in_attrs->at(0).Size() == in_attrs->at(1).Size() (1536 vs. 2) Reshape inputs size should be compatible
The inputs of reshape op with shapes (1,1,1,1536) and 2
output shape is (?,?)
Could you please tell why did the error happened?

[tqchen]

Thanks for bringing up this problem, please open a thread at the community disucss forum https://discuss.tvm.ai

[srkreddy1238]

@wincle #1923 should fix this issue.

[srkreddy1238]

@wincle you may follow the below discussion
https://discuss.tvm.ai/t/tvm-tf-converter-bug-with-inception-v4-network/894/2

[wincle]

@tqchen Thx! I have post my question up there, it seems need time to show up for me.

[wincle]

Hi, @srkreddy1238 , Thanks for your reply , I have checked the links which you posted, your work is indeed valuable, but it still confused me because I didn't find the same problems as I met which happened in nnvm.frontend.from_tensorflow at the Reshape Op.
Could you please explain clearly why did this error happened? Thx!

[srkreddy1238]

@wincle replied on discussion forum.