Comments (7)
Hi @filip-halt ,
Can you please provide the tflite model file so that i can replicate the issue?
from tensorflow.
Hi @filip-halt ,
Can you please provide the tflite model file so that i can replicate the issue?
You can find a copy here: https://github.com/filip-halt/tflite_bug It was too large to upload directly into this chat.
from tensorflow.
Turns out that this is most likely due to a conv2dtranspose layer in the model. I was under the impression that conv2dtranpose was supported but I could be wrong.
Another interesting thing that happens is that when you convert the model with:
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.target_spec.supported_types = [tf.float16]
the resulting binary is 2x as large as float32 and 20% slower on mobile. When I inspected the graph with Netron, it looks like nothing was converted to float16, not even the conv2d's
from tensorflow.
Hi @filip-halt ,
I ran your model using GPU delegate on dimensity 9000 and it ran fine without giving any issues. Can you please try it out with a different device and let me know if it worked there. However the list of supported operators for tflite is here and TRANSPOSE_CONV is listed there.
from tensorflow.
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.
from tensorflow.
I believe that this is a grouped TRANSPOSE_CONV conversion problem. Tensorflow seems to barely support this and is what is breaking when converting onnx to tf. The default conversion creates a large amount of layers that ultimately cause an OOM on the phone when loading.
![image](https://private-user-images.githubusercontent.com/81822489/337407827-5c93b64a-b188-4fa3-9ea8-8c01abdf073a.png?jwt=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJnaXRodWIuY29tIiwiYXVkIjoicmF3LmdpdGh1YnVzZXJjb250ZW50LmNvbSIsImtleSI6ImtleTUiLCJleHAiOjE3MTk2MDUyNDEsIm5iZiI6MTcxOTYwNDk0MSwicGF0aCI6Ii84MTgyMjQ4OS8zMzc0MDc4MjctNWM5M2I2NGEtYjE4OC00ZmEzLTllYTgtOGMwMWFiZGYwNzNhLnBuZz9YLUFtei1BbGdvcml0aG09QVdTNC1ITUFDLVNIQTI1NiZYLUFtei1DcmVkZW50aWFsPUFLSUFWQ09EWUxTQTUzUFFLNFpBJTJGMjAyNDA2MjglMkZ1cy1lYXN0LTElMkZzMyUyRmF3czRfcmVxdWVzdCZYLUFtei1EYXRlPTIwMjQwNjI4VDIwMDIyMVomWC1BbXotRXhwaXJlcz0zMDAmWC1BbXotU2lnbmF0dXJlPWQyODdkOTk4ZTFjMmUyMTg5NTFhNmMzMWMzOGMwNTgzYzFhMTMwOWNhMTZmYmZlM2NiNjM5M2ZiNzkwZWJlM2EmWC1BbXotU2lnbmVkSGVhZGVycz1ob3N0JmFjdG9yX2lkPTAma2V5X2lkPTAmcmVwb19pZD0wIn0.ZcUyYNIg1b-FASQ_8QY1KmVahB6Qvd_H-akUppgW2u4)
from tensorflow.
Hi @filip-halt , 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.
Related Issues (20)
- model.fit ValueError: Cannot take the length of shape with unknown rank. HOT 1
- [TFLite] TfLiteInterpreterInvoke has memory leak and increasing duration time HOT 4
- Stable Gradient for BinaryFocalCrossEntropy HOT 2
- Strange issue File already exists in database HOT 2
- bucketize -function wrong results on GPU HOT 2
- Tensorflow build without boringssl on Power architecture HOT 2
- Model works in tensorflow 2.15 perfectly but unable to import the model in tensorflow 2.16! HOT 4
- TFLite: Stable Delegate: C++ Example HOT 3
- TensorFlow v2.12.0 Not Supporting GPU on Ubuntu 22.04 with CUDA 12.4 and cuDNN 9.0 HOT 2
- Unable to use tf and its modules including keras and etc, where the tensorflow==2.15.1 and keras==2.15.0 HOT 5
- Relu activation in TF Lite model return the negative values HOT 2
- LSTM model conversion failed from 'from_keras_model' HOT 3
- C-API support for .keras models HOT 4
- tfm.nlp.layers.RelativePositionEmbedding HOT 2
- Document tf.Dataset.zip/map triggers tf.Dataset.shuffle HOT 1
- Data Service Dynamic sharding policy seems extremely slow HOT 11
- ModuleNotFoundError: No module named 'tflite_support.task' HOT 3
- Notebook is not working anymore HOT 3
- Kubernetes cluster resolver fails when running from within a K8S cluster.
- Tried multiple builds, Bazel, pip, file. non of it is working HOT 5
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from tensorflow.