-
The `tf.lite.Interpreter` [documentation](https://www.tensorflow.org/api_docs/python/tf/lite/Interpreter) claims:
num_threads:
Sets the number of threads used by the interpreter and available to…
-
### 1. System information
Windows 11
### 2. Code
import tensorflow as tf
saved_model_dir = "C:/Users/s/Downloads/best (1)_saved_model"
converter = tf.lite.TFLiteConverter.from_saved_mod…
ssdv1 updated
22 hours ago
-
We tried to convert ESWT-12-12_LSR_x4.pth model from torch to tflight. We should use Flex tf ops as not all layers were converted initially but finally model was converted successfully without errors …
-
### 1. System information
- OS Platform and Distribution: Windows 11
- TensorFlow installation : pip
- TensorFlow library: 2.18.0
### 2. Code
import tensorflow as tf
input_shape = (224,…
-
### Issue type
Performance
### Have you reproduced the bug with TensorFlow Nightly?
No
### Source
binary
### TensorFlow version
v2.9.1
### Custom code
No
### OS platform and distribution
Li…
-
This has been experienced using TF 2.18.0 and has been seen in the current master branch.
I have compiled the TensorFlow Lite shared library for use on an embedded device. In order to compile my a…
-
### 1. System information
- OS Linux Ubuntu 22.04
- TensorFlow installation from sources
- TensorFlow library version 2.16
### 2. Code
I converted model from tensorflow to tflight. I should…
-
I use the following code to convert the internal state model into TFLite
```
converter.optimizations = [tf.lite.Optimize.DEFAULT]
converter.representative_dataset = representative_dataset_gen
conv…
-
On Apple M1 Pro with MacOs Sonoma 14.1.2 (23B92)
TensorFlow version 2.16.1 (still an issue with TF 2.17.0)
sources + assets:
[Gru_quantization_bug.zip](https://github.com/user-attachments/files/1…
-
### 1. System information
- Linux Ubuntu 24.04
- TF 2.17.0 (pip) and Keras 3.5.0
### 2. Code
A TF model is first exported using Keras 3.5.0:
```model.export(model_name)```
Then when th…