Tan Pengshi Alvin comments

Results 7 comments of


                                            Tan Pengshi Alvin

pretrained model

I can no longer evaluate the PFE_sphere64_msarcface_am pretrained model for lfw accuracy! Came across the error here: ``` 157 print('Metagraph file: %s' % meta_file) 158 print('Checkpoint file: %s' % ckpt_file)...

ValueError: Dimension 0 in both shapes must be equal, but are 0 and 512

Same issue for me! Can the creator make the code compatible with Tensorflow 2?

Potential Tensorrt Bug on WSL2 (8.4 GA)

Same issue for me. TensorRT 8.4 on WSL2 gives rubbish results on model inference. See my post: https://forums.developer.nvidia.com/t/onnx-tensorrt-inference-gives-wrong-result/230625 Can I run TensorRT 8.4 on VM Ubuntu?

Potential Tensorrt Bug on WSL2 (8.4 GA)

> Would it be possible for someone to help me out here? I cant seem to figure why tkdnn wont work with tensorrt 8.4 on wsl2 while there are no...

Potential Tensorrt Bug on WSL2 (8.4 GA)

TensorRT 8.5 is released. I wonder if it would work with WSL2.

Link error when using both TensorFlowLiteSelectTfOps.framework and TensorFlowLiteC.framework on iOS

> @w3sip While there's no direct way to build a subset of TensorFlowLiteSelectTfOps_framework, here are effective approaches to reduce its size for iOS apps: such as follows; > > 1....

Tensorflow lite selective build results _ZN6google8protobuf8internal26fixed_address_empty_stringE" error, build fails with tne --config=monolithic setup, returning the Check failed: existing == nullptr (Tensor already registered) errror

I am encountering a similar error with 2.13 Anyone knows if 2.15 solves the error? Do you need `echo -n "build --config=monolithic" >> .bazelrc` command for 2.15?