# Flutter pytorch model to Tflite **URL:** \ **Category:** General Discussion\ **Tags:** tflite, models, help\_request\ **Created:** [September 15, 2021, 10:17am UTC](https://discuss.ai.google.dev/t/flutter-pytorch-model-to-tflite/32462 "2021-09-15T10:17:17Z")\ **Posts on this page:** 3\ **Page:** 1
**Author:** ![An\_Nguy\_n](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/an_nguy_n/32/8984_2.png) [@An\_Nguy\_n](https://discuss.ai.google.dev/u/An_Nguy_n)\ **Post date:** [September 15, 2021, 10:17am UTC](https://discuss.ai.google.dev/t/flutter-pytorch-model-to-tflite/32462/1 "2021-09-15T10:17:17Z")
I use ONNX to convert Pytorch to tflite and use flutter with package ‘tflite\_flutter: ^0.9.0’ to deploy model. But the tflite model run on Colab output differently from flutter (Colab is the correct one). On Colab, image must be transpose to [1,3,256,256] to be feed on the model. But I don’t know how to transpose Image shape on Flutter and feed the image with model shape [1,3,256,256]. After I run ‘interpreter.run(tensorImage.buffer, probabilityBuffer.buffer)’, The output is different from the output from Colab. Output shape from flutter is 1D array which length is [196608]. How to feed image to model shape [1,3,256,256] on flutter. ---
**Author:** ![Bhack](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/bhack/32/6388_2.png) [@Bhack](https://discuss.ai.google.dev/u/Bhack)\ **Post date:** [September 15, 2021, 11:20am UTC](https://discuss.ai.google.dev/t/flutter-pytorch-model-to-tflite/32462/3 "2021-09-15T11:20:07Z")
Have you tried with > > > \*\*Problem\*\* > > In my usecase, I need to port a model (only containing conv, relu… and maxpool layers) from PyTorch to TensorFlow Lite micro, using the following conversions: PyTorch-\>ONNX-\>TensorFLow-\>Tensorflow Lite micro. The microcontroller kernels of TFLite however only support NHWC format and there is no support for a transpose layer (see supported layers \[here\](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/micro/all\_ops\_resolver.cc)). In CPU mode, onnx-tf inserts transpose operations before and after every conv layer so the conv layers can work with NHWC format. However, the rest of the network is kept in NCHW format. What I need is a network with only NHWC tensors for all layers without any transpose operations (also input/output layers should have NHWC format). > > It would be nice if onnx-tf had a mode where you can completely convert a model that is only using NCHW format to a model that is only using NHWC format instead of creating hybrids as is done by the current implementation. > I know this is currently not supported and there is probably not an easy solution for this. But is want to indicate that a conversion from ONNX-\>TFLite micro is currently fundamentally broken for any given model because of the transpose ops. > > We could also fix the problem at the TFLite micro side, by implementing a transpose op, but that is a more wasteful solution given the unnecessary overhead of transpose operations on an already very constrained platform. Fixing the issue in TensorFlow by rewriting the graph seems a bit too complex to do and error prone to future changes. > > I therefore kindly ask to consider implementing an additional mode in the converter if possible. I'm willing to contribute if necessary. > > \*\*Python, ONNX, ONNX-TF, Tensorflow version\*\* > > - Python version: 3.6.5 > - ONNX version: 1.8.0 > - ONNX-TF version: 1.7.0 (master branch, commit: db092105ceebe076610a1b27c1fc1553978c17cd) > - Tensorflow version: 2.3.1 ---
**Author:** ![lgusm](https://d1dlmcr85iqnpo.cloudfront.net/user_avatar/discuss.ai.google.dev/lgusm/32/6230_2.png) [@lgusm](https://discuss.ai.google.dev/u/lgusm)\ **Post date:** [September 15, 2021, 3:47pm UTC](https://discuss.ai.google.dev/t/flutter-pytorch-model-to-tflite/32462/4 "2021-09-15T15:47:38Z")
I don’t have a good answer for the question but out of curiosity, what does this model do?