Model Loading issue in iOS

Mobile
1

I get the following error when trying to initialize a traced model with the iOS framework:
PyTorchDemo[25132:6735005] false CHECK FAILED at /Users/distiller/project/c10/core/Backend.h (tensorTypeIdToBackend at /Users/distiller/project/c10/core/Backend.h:106)
(no backtrace available)

The error appears similar to these Android issues:

The second linked issue states that there’s an Android update with a fix --is there a fix for the iOS framework?

The model I’m using was traced with PyTorch 1.3.1, and I’m using LibTorch 1.3.1

2

Looks like the fix was landed to master as mentioned on #29806 so it will be part of 1.4 release. You can test the nightly build of iOS. @IvanKobzarev could you please confirm?

3

Yeah, I’m pretty sure this is resolved. If you want to verify, the steps for testing with the nightly build are in the first half of this comment: Incomprehensible behaviour

4

Hi @kennywalker, are you using cocoapods on iOS? if so, the correct version should be 1.3.1. If the error still exist, try the iOS nightly build - https://ossci-ios-build.s3.amazonaws.com/libtorch_ios_nightly_build.zip. Let me know if you have any questions.

1 Like
5

The model loads with the nightly build.

Thank you for the help @ljk53, @David_Reiss, @xta0

1 Like
6

Hi @xta0

I was using cocoapods 1.3.1. Can the 1.4 podspec be published?.

7

Hi @kennywalker, we’re going to publish 1.4 in Jan (Hopefully). Could you give a solution mark on this? If there is any questions, feel free to leave a comment.

8

Hi @xta0, is there an update about the release date of 1.4 for iOS?

9

I think it’ll be in the middle of Jan. @jspisak do you know the exact date?

10

Yes, we are targeting mid next week to release 1.4. Look for the blog post on pytorch.org. :slight_smile:

11

Dear @xta0, I tried to use the current iOS nightly build, but it doesn’t work. I’ve noticed that the file libtorch.a has only 944 bytes.

12

Dear @kennywalker, could you share with us the version you downloaded on December 19th, please?

13

@fabricionarcizo the nightly build is from master branch. We’ve recently split the libtorch.a into multiple libraries. If you unzip the nightly build, you should see this - libtorch_cpu.a which is the old libtorch.a.

14

@xta0 I just tried to compile the libtorch.a using the branch v1.4.0 with the following command:

SELECTED_OP_LIST=predictor.yaml BUILD_PYTORCH_MOBILE=1 IOS_ARCH=arm64 ./scripts/build_ios.sh

It compiles correctly, but I got some additional error when I try to link the libtorch.a on Xcode.

Undefined symbol: c10::NonVariableTypeMode::is_enabled()
Undefined symbol: torch::jit::script::Module::module_object() const
Undefined symbol: c10::NonVariableTypeMode::set_enabled(bool)
Undefined symbol: caffe2::detail::_typeMetaDataInstance_preallocated_6
Undefined symbol: at::TypeDefault::to(at::Tensor const&, c10::TensorOptions const&, bool, bool)
15

@fabricionarcizo SELECTED_OP_LIST is used for the custom build. Also, the build is in arm64, were you running in simulator?

Since I don’t have your code, my recommendation is to follow the tutorials