-
Hi, I'm pre-training xxlarge model using own language.
I trained on **TPU-v2-256** but loss is not decreasing.
Below is the learning information.
- vocab size: 33001
- training data size: 518G …
-
**System information**
- OS Platform and Distribution: Ubuntu 19.10
- TensorFlow installed from (source or binary): pip install tensorflow==2.3.0
**Command used to run the converter or code if yo…
-
**System information**
- Have I written custom code: No
- OS Platform and Distribution: Ubuntu 16.04.2 LTS
- TensorFlow installed from binary
- TensorFlow version v2.4.0-rc4-71-g582c8d236cb 2.4.0…
-
I am using tensorflow2.6 inside NGC docker nvcr.io/nvidia/tensorflow:21.10-tf2-py3. Running inference using pre-trained bert model from tensorflow hub https://tfhub.dev/tensorflow/small_bert/bert_en_u…
-
Let's compile open models. Through this we can:
- gather problems with compile real models
- gather information for better user command interface
Our CI http://npuci.mooo.com:8080/job/nnfw/job/ma…
-
Hi,
I am trying to train a custom object detector using this guide as a reference:
https://medium.com/@poulinakis.kon/object-detection-at-the-edge-with-tf-lite-model-maker-e635a17b0854
I was a…
-
I am using tensorflowjs_converter to convert a tflite model to tensorflowjs model.
The repository can be download with web browsers but failed when using tensorflowjs_converter.
```
tensorflowjs_…
-
Added model signature to model using below code:
import tensorflow as tf
import tensorflow_hub as hub
model_url = "https://tfhub.dev/tensorflow/mask_rcnn/inception_resnet_v2_1024x1024/1"
loade…
-
Added model signature to model using below code:
```python
import tensorflow as tf
import tensorflow_hub as hub
model_url = "https://tfhub.dev/tensorflow/mask_rcnn/inception_resnet_v2_1024x102…
-
Error - - 'range_iterator' object has no attribute 'throw'
- happening in lib.make_image_classifier at line 248
- noticed that if I let it download flower images it runs but if I set image_dir to m…