addons icon indicating copy to clipboard operation
addons copied to clipboard

Useful extra functionality for TensorFlow 2.x maintained by SIG-addons

Results 170 addons issues
Sort by recently updated
recently updated
newest added

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Ubuntu 18.04 - TensorFlow version and how it was installed (source or binary): 2.4.1 - TensorFlow-Addons version and how...

seq2seq
question

**code** tf.keras.layers.Bidirectional(tfa.layers.WeightNormalization(tf.keras.layers.GRU(units_gru, return_sequences=True)), merge_mode='concat') **problem** In Weight Normalization, there is no "go_backwards" argument, but Bidirectional needs such argument, so this line code met errors as following: ``` File "/usr/local/lib/python3.6/dist-packages/tensorflow/python/keras/layers/wrappers.py", line...

**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): **CentOS Linux release 8.3.2011** - TensorFlow version and how it was installed (source or binary): **binary** - TensorFlow-Addons version...

bug
image
custom-ops

# Description Brief Description of the PR: Updated the formula to include to complete the numerator Fixes # (issue) https://github.com/tensorflow/tensorflow/issues/50737 ## Type of change - [ x] Bug fix -...

cla: yes
activations

**System information** - Windows 10 - TensorFlow version and how it was installed (source or binary): TF 2.5.0 - TensorFlow-Addons version and how it was installed (source or binary): 0.13.0...

**1-)** I have a .pth image features' file with 4D tensor **[batch,dimension,height,width]**. I can see this class **(AdaptiveAveragePooling2D(AdaptivePooling2D):** Could you please tell me how can I Pass my .pth file...

tensorflow 2.2 keras 2.3.0-tf tfa 0.10.0 python 3.6 use code: metrics = [ tfa.metrics.RSquare(name='RSquare', dtype=tf.float32, y_shape=(1,)) ] run multiple epochs, it went well for the first epoch, but return error...

metrics

Hi, I am integrating the F1 score from tensorflow addons for a multi-label classification problem and there is a part of the documentation tat confuses me. Just to be completely...

documentation
metrics

I found that there are no RNN-Transducer loss in the new version. I have to use third party pkg like [wrap-transducer](https://github.com/HawkAaron/warp-transducer/tree/master/tensorflow_binding) So, official support in both tf1.x and tf2 is...

help wanted
losses
rnn
Feature Request

https://github.com/tensorflow/addons/blob/96136187b14d6508d42bacbf4c619e789ae04078/tensorflow_addons/metrics/f_scores.py#L212-L284 ``` from tensorflow.keras.metrics import Precision, Recall from tensorflow_addons.metrics import F1Score metric = F1Score(num_classes=3, threshold=0.5, average='weighted') y_true = np.array([[1, 1, 1], [1, 0, 0], [1, 1, 0]], np.int32) y_pred =...