-
Hi,
I am trying to convert a '_ssd_mobilenet_v2_320x320_coco17_tpu-8_' TF2 model to .tflite.
i use export_tflite_ssd_graph.py for create tflite_graph.pb
But this either fails to create. I am …
-
Could you add native support for Focal Loss? There are implementations for LGBM and XGB. They show better performance on imbalanced data, but they are slow and clunky. Also allow to use MSE for classi…
glevv updated
3 years ago
-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [x] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [x] I am reporting…
-
I'm training on custom dataset using DeepMAC. The config is as follows:
```
# DeepMAC meta architecture from the "The surprising impact of mask-head
# architecture on novel class segmentation" [1] …
-
@tensorflow/micro
**System information**
- Host OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Amazon Linux AMI
- TensorFlow installed from (source or binary): source
- Tensorflow ve…
-
Hello,
We have our datasets with a unique class. For that, we pass our COCO format datasets to `create_coco_tf_record.py`.
Changing `num_classes=2` in `hparams_config.py` and after launching th…
-
System information：
Have I written custom code (as opposed to using a stock example script provided in TensorFlow):no
OS Platform and Distribution (e.g., Linux Ubuntu 16.04):ubuntu 18.04
Mobile d…
-
# Prerequisites
Please answer the following questions for yourself before submitting an issue.
- [x] I am using the latest TensorFlow Model Garden release and TensorFlow 2.
- [x] I am reporting…
-
System information
Have I written custom code (as opposed to using example directory): https://github.com/tensorflow/models/tree/master/official/vision/detection changed strategy to "mirrored" to…
-
Hi all,
I retrained the ssd_mobilNet_v1 model with own data (4 classes) (following the google tutorial for the coral chip: https://coral.ai/docs/edgetpu/retrain-detection/#using-the-coral-usb-acceler…