-
Do anyone tried to convert trained .h5 model to Tensorflow Lite or Tensorflow Serving?
I got some difficulties due to some python functions such as 'yolo_loss' and 'yolo_head'.
-
Swift code keep crashing.I run swift app comes with repo on iPhone 8 and it crashes with following logs
```bash
TensorFlow: v2.2.0-24-g1c1b2b9dd9
DeepSpeech: v0.8.2-0-g02e4c762
2021-06-19 19:48:…
-
Please add support to jax2tf for nnx.Module.
```python3
from flax import nnx
import tensorflow as tf
import jax.numpy as jnp
from jax.experimental import jax2tf
import optax
from flax.training import…
-
Hi there,
I was following the build instructions in the README to create a tflite .dll file for my windows realtime image classification project.
The project works but very stuttery, so I tried to…
-
### Proposal Summary
Fiftyone currently only creates tfrecords with source_ids indexed to filenames. Tensorflow Lite does not support this, requiring source_id fields in tfrecord files to be numeri…
-
I learn tensorflow from: https://codelabs.developers.google.com/codelabs/tensorflow-for-poets-2-tflite/#0
In step 2, we install tensorflow version 1.7, but in step 3 we want to run "tflite_convert"…
-
Hi, many thanks for the article and the sample-code.
It works fine with the model mentioned in your project. However, I trained my own model (using the tensorflow-for-poets 1 and 2 tutorials) but I…
-
I'm trying to build tflite-micro as a submodule in PX4, what is the best way to do this? After two days of trying I'm still stuck at linker errors. Is there an easy way to utilize the Makefile with PX…
-
**I get this error message after succefully getting json files**
**I tried several tensorflow versions but I still get the same error**
Processing How001
Traceback (most recent call last):
File…
-
> EfficientNet-lite are a set of mobile/IoT friendly image classification models. Notably, while EfficientNet-EdgeTPU that is specialized for Coral EdgeTPU, these EfficientNet-lite models run well on …