Comments (4)
Had same issue, switched to 2.15 temporarily. But can confirm the issue.
from tensorflow.
Hi @LaurentBerger,
I have reproduced the code with TF 2.15 and TF 2.16. With 2.15 it's working fine as expected. As you mentioned, it's getting crashed with TF2.16.1 at TFLite conversion . Right now, TF2.16 has an issue with Keras 3.0. As a workaround install Keras 2 as follows.
pip install -U tf_keras # Keras 2
import os
os.environ["TF_USE_LEGACY_KERAS"] = "1"
. Here is the gist with TF 2.16 and keras2 workaround. Please let us know if problem still persists.
Thank You
from tensorflow.
Had same issue, switched to 2.15 temporarily. But can confirm the issue.
It seems TFLite converter is not compatible with Keras 3. A workaround is to use ExportArchive to convert Keras model to saved model at first.
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.
Related Issues (20)
- `Check failed` in `tf.raw_ops.TensorScatterUpdate` and `tf.tensor_scatter_nd_update` when the rank of `indices` > 2. HOT 1
- `Check failed` in `tf.raw_ops.TensorScatterMax` and `tf.tensor_scatter_nd_max` when the rank of `indices` > 2.
- `Check failed` in `tf.raw_ops.TensorScatterMin` and `tf.tensor_scatter_nd_min` when the rank of `indices` > 2. HOT 2
- `Check failed` in `tf.raw_ops.TensorScatterSub` and `tf.tensor_scatter_nd_sub` when the rank of `indices` > 2.
- `Check failed` in `tf.raw_ops.TensorScatterAdd` and `tf.tensor_scatter_nd_add` when the rank of `indices` > 2. HOT 1
- `Segmentation Fault` in `tf.raw_ops.TensorListScatter` and `tf.raw_ops.TensorListScatterV2` when the value of `indices` is too large.
- Some `Check Failed` errors in `tf.raw_ops.MatrixSetDiagV3` HOT 1
- Some `Check Failed` errors in `tf.raw_ops.MatrixSetDiagV2`
- Memory leak in tf.data when iterating over Dataset.from_generator HOT 2
- Link error when building flex:tensorflowlite_flex in debug mode for Windows
- TensorFlow 2.16 is not found in Maven Central HOT 2
- How to build the tensorflow origin code fast when I modify the code HOT 1
- build TensorFlow in windows HOT 1
- `Check failed` in `f.raw_ops.CropAndResizeGradBoxes` when `boxes` and `box_indices` are empty.
- Some errors in `tf.raw_ops.SparseTensorDenseMatMul` when there are negative or too large values in `a_shape`. HOT 2
- `Overflow` in `tf.raw_ops.SerializeManySparse` when there are too large values in `sparse_shape`. HOT 2
- `Check Failed` in `tf.raw_ops.FakeQuantWithMinMaxVarsPerChannel` and `tf.quantization.fake_quant_with_min_max_vars_per_channel` when the input of `inputs` is scalar. HOT 2
- `Check failed` in `tf.raw_ops.Batch` when the value of `num_batch_threads` is too large.
- `Check failed` in `tf.raw_ops.LoadAndRemapMatrix` when the rank of `ckpt_path` is not equal to the rank of `old_tensor_name`. HOT 1
- `Segmentation fault` in `tf.raw_ops.LoadAndRemapMatrix` when the value of `num_cols` is too large while `col_remapping` is empty. HOT 3
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.