-
Thank you for awesome repo.
I saw your accuracy model (tps_resnet_bilstm_attn) is 84.95. that is better than [this model](https://github.com/clovaai/deep-text-recognition-benchmark).
What did you c…
-
Hi @ku21fan, Thank you for your work.
I have tried to fine-tune the case sensitive model with my own characters (non-latin one). But when the character list has more than 64 char, i get the follow…
-
**Issue by [iftenney](https://github.com/iftenney)**
_Tuesday Jul 24, 2018 at 18:07 GMT_
_Originally opened as https://github.com/nyu-mll/jiant/pull/238_
----
Configs & scripts to run edge probing …
-
Hello!
First of all, many thanks for your incredible repo! I've decided to train None-ResNet-BiLSTM-Attn network on my own dataset. After training was finished I try to use a new network to check h…
-
Hi,
I am getting an error if I set
```
os.environ['DISABLE_V2_BEHAVIOR'] = '1'
```
Below error doesn't come If I do not set it. I worked fine for `BERT` and `DistilBERT`.
```
ValueError …
-
**System information**
- OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux Ubuntu 18.04
- TensorFlow installed from (source or binary): binary
- TensorFlow version (or github SHA if fr…
-
I faced this error!
```
(base) C:\DOPO\ArgMin\NCRFpp-master>python main.py --config demo.train.config
C:\Users\moha\anaconda3\lib\site-packages\torch\cuda\__init__.py:52: UserWarning: CUDA initi…
-
**System information**
- OS Platform and Distribution: Ubuntu 16.04
- TensorFlow installed from: binary
- TensorFlow version: tf-nightly 2.2.0
**Command used to run the converter or code if you’…
-
Hi @131250208 !
I was interested in evaluating other datasets (such as conll04 and scierc, as evaluated by [SpERT](https://github.com/markus-eberts/spert/)). I was wondering wich other settings I'd…
-
@DronistB posted an issue on #413 showing that the new TensorFlow V2 API for Keras does not work with the existing conversion code for Bidirectional RNN layers. This occurs because TensorFlow's new RN…