RuntimeError when invoking TFLite INT8 model with tile operation about tensorflow HOT 9 OPEN

Hi @ShabbirMarfatiya ,

I will replicate your issue and will get back to you.

from tensorflow.

Hey @sawantkumar,

Thanks for looking into this issue. If you need any more details, feel free to let me know.

from tensorflow.

Hi @sawantkumar,

Have you happened to find anything related to my issue that might be helpful?

from tensorflow.

Hi @ShabbirMarfatiya ,

I am in the process of replicating your issue. Meanwhile did you try out with the latest tensorflow version , 2.16.1 ?

from tensorflow.

Hi @sawantkumar,

No, I didn't try that, but I'll try and let you know the outcome.

from tensorflow.

Hi @ShabbirMarfatiya ,

I see that you have already filed a bug report for this, right? Anyway , just in case can you also also provide all the other assets like model file and dataset.

from tensorflow.

Hi @sawantkumar,

I have uploaded all necessary folders and files to GDrive. Here's the link for you: https://drive.google.com/drive/folders/1Ov1qVyreDWq0q3VQbAq0BIvrxRSB4dRs?usp=sharing

If you need any more details, feel free to let me know.

from tensorflow.

Hi @ShabbirMarfatiya ,

I am getting a lot of protobuf library issues. It will take me some time to resolve and replicate your issue. I will let you know once i am done. Thank you

from tensorflow.

Hi @ShabbirMarfatiya , we're wondering if you may be able to resolve your issue by using AI-Edge-Torch, you can find more information here: googleblog.

I have actually created a simple script for converting a mobilenet model here:

import torch
import torchvision
import ai_edge_torch

mobilenet_model = torchvision.models.mobilenet_v3_small()
sample_inputs = (torch.randn(1, 3, 224, 224),)

edge_model = ai_edge_torch.convert(mobilenet_model.eval(), sample_inputs)
edge_model.export("mobilenet_v3_small.tflite")

If you want to, you can actually try visualizing the result in model-explorer as well.

Please try them out and let us know if this resolves your issue. If you still need further help, feel free to open a new issue at the respective repo.

from tensorflow.