addons

addons copied to clipboard

Gradient accumulate optimizer

43

**Describe the feature and the current behavior/state.** Hi, I think it's good if someone can support Gradient Accumulate optimizer for this repo, this feature is really helpful for those who...

dathudeptrai

Cite your project

2

Hi, first of all, thanks for that great work! I just wanted to clarify what is the correct way to reference your repository when writing an article? Do you have...

RoyalStorm

Training fails when using Yogi extended with weight decay as optimizer

1

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 20.04 - TensorFlow version and how it was installed (source or binary): TF 2.5.3 from pip - TensorFlow-Addons...

YannPourcenoux

I was trying to implement seq2seq translation model at **character level** along with beam search by referring the tensorflow documentation. [https://www.tensorflow.org/addons/tutorials/networks_seq2seq_nmt](url) For this, I tried to change parameter, 'char_level =...

VallabhMahajan1

Can ROCm be supported?

11

**System information** - TensorFlow version (you are using): tensorflow-rocm 2.0.0b3, 15/07/19 - TensorFlow Addons version: 0.4.0 - Is it in the tf.contrib (if so, where): Not applicable - Are you...

iszotic

your ciou customer op according to the ciou paper seems to have the same mistake the paper have.

3

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): - TensorFlow version and how it was installed (source or binary): - TensorFlow-Addons version and how it was installed...

fjzhangcr

TypeError: Unable to serialize 1.0000000656873453e-05 to JSON. Unrecognized type . https://stackoverflow.com/questions/69882263/tf-keras-callbacks-modelcheckpoint-type-error-unable-to-serialize-1-0000000656 `wd` is directly copy-&-pasted from: https://www.tensorflow.org/addons/api_docs/python/tfa/optimizers/AdamW ``` step = tf.Variable(0, trainable=False) schedule = tf.optimizers.schedules.PiecewiseConstantDecay( [10000, 15000], [1e-0, 1e-1, 1e-2])...

mw66

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04.5 LTS - TensorFlow version and how it was installed (source or binary): tf-nightly 2.10.0.dev20220427, binary - TensorFlow-Addons...

adhadse

EDT performance in real app: gpu-version is ~24 slower then cpu one

5

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Google Colab - TensorFlow version and how it was installed (source or binary): default colab version - TensorFlow-Addons version...

intervolga-school

very strange result with lamb optimizers

2

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): linux 20.04 - TensorFlow version and how it was installed (source or binary): 2.8 pip install - TensorFlow-Addons version...

exx8