addons
addons copied to clipboard
Useful extra functionality for TensorFlow 2.x maintained by SIG-addons
**System information** - macOS 11.5.1 (Big Sur) Macbook Air M1 2020 Hi! Would you help with a tutorial for installing Tensorflow and tensorflow_addons in this system?
Hi, I have use the tfa.layers.CRF in my BiLSTM_CRF, it could be compiled but I got an Error which says: "TypeError Expected int32 got 0.0 of type 'float' instead "...
**Describe the feature and the current behavior/state.** Currently, [tfa.text.crf_decode_forward](https://github.com/tensorflow/addons/blob/master/tensorflow_addons/text/crf.py#L467-L492) is designed as 1. Create an RNN cell and pass a loop in variant `transition_params` into constructor. 2. Create an RNN...
Hello, I found a performance issue in the definition of `test_crf_log_likelihood`, tensorflow_addons/text/tests/crf_test.py, [tf.expand_dims](https://github.com/tensorflow/addons/blob/a69c12a26e129d9fb388114fa65fc3ddac16a977/tensorflow_addons/text/tests/crf_test.py#L313) will be called repeatedly during program execution, resulting in reduced efficiency. I think it should be created...
**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Windows 10 - TensorFlow version and how it was installed (source or binary): 2.3 binary - TensorFlow-Addons version and...
Environment : Google Colab Hardware Accelerator: TPU TensorFlow version: 2.2.0-rc3 TensorFlow Addons: 0.9.1 **Describe the bug** Weight Normalization layer (tfa.layers.WeightNormalization) throws error when running in TPU **Code to reproduce the...
Can I use normalized "trellis" as probability distribution over classes for each sequence element?
Hi, I use your [piece of code](https://github.com/tensorflow/addons/blob/v0.12.0/tensorflow_addons/text/crf.py#L374) in my model, but instead of hard labels, I need to know the probability of each class for each timestamp. So can I...
Hello, I want to ask if you there is an alternative crf_losses.py as in keras_contrib in tensorflow_addons?
In layers/crf CRF Layer, the output is [decoded_sequence, potentials, sequence_length, self.chain_kernel], however, when I want to get the first element of the output like the code below : ``` from...
**System information** - OS Platform and Distribution (e.g., Linux Ubuntu 16.04): Linux centOS - TensorFlow version and how it was installed (source or binary): 2.4.1 pip install binary - TensorFlow-Addons...