@sronen71 For LSTM conversion, this is an article and colab describing the process, and you can follow the colab gist to do it. For 4 kinds of quantizations, maybe you can also try other ways like dynamic range. Hope it could help? Please let us know. Thank you!

@sushreebarsa
I checked that information and colab example previously, and based my colab gist on that.
I find the original colab example is broken right now, because of tf-nightly error.
I was able to run it yesterday successfully, however, it only uses the vanilla convert.
When I try to use the optimize option with float16 target, as in the colab gist I attached, the reported defect is observed.

@pkgoogle I was able to reproduce this issue. Please find this gist.

Could you please look into this?

Thanks.

I was able to replicate with @pjpratik's exact same gist, @abattery, can you please take a look? Thanks.

Hi, can i work on this issue ?

Hi @devadigapratham, we always welcome any contribution from the community. Please let us know if you have any questions.

Also running into this issue for float16 tflite conversions

Hi @sronen71 ,

You can now move to AI-Edge-Torch to resolve your issue. you can find more information here: googleblog.

Here is a simple script for converting an LSTM model here:

import torch
import torchvision
import ai_edge_torch

rnn = torch.nn.LSTM(10, 20, 2)
sample_inputs = (torch.randn(5, 3, 10),)

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

try:
  edge_model = ai_edge_torch.convert(rnn.eval(), sample_inputs)
  edge_model.export('rnn.tflite')
  print("Conversion successful!")
except Exception as e:
  print("Error during conversion:", e)

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 repos.

This issue is stale because it has been open for 7 days with no activity. It will be closed if no further activity occurs. Thank you.