ranking
ranking copied to clipboard
Learning to Rank in TensorFlow
First of all, thank you for a nice library for rankers 😺 I found out you cannot import as you would expect from the documentation. This is not specific to...
Updated Quickstart tutorial with new apis. Attached [gist](https://colab.research.google.com/gist/mohantym/7fd3fe3c01007d968b36a1cbf44e5487/quickstart.ipynb#scrollTo=6yzAaM85Z12D) for reference. Replaced tf.keras.layers.experimental.preprocessing.StringLookup with tf.keras.layers.StringLookup at line 165, 169
Hello. in function is_label_valid (line 76 of utils.py), the following code is given: ```` def is_label_valid(labels): """Returns a boolean `Tensor` for label validity.""" labels = tf.convert_to_tensor(value=labels) return tf.greater_equal(labels, 0.) ````...
How do I pack Bert into my textual data? I have query and document pairs, should I package only documents? I ask because of this definition: ``` SEQ_LENGTH = 64...
As the example is given in https://www.tensorflow.org/ranking/tutorials/ranking_dnn_distributed , it directly uses the TF Records and doesnt show how the data got converted into them. Even though as per format there...
Fix for ranking example, Fixes issue [#57921](https://github.com/tensorflow/tensorflow/issues/57921) Attached working [gist](https://colab.research.google.com/gist/tiruk007/97a4b30099f91b43ce9535f4c930ca50/landingpage_example.ipynb) for reference.
https://github.com/tensorflow/ranking/blob/de7d7c2a8b8663a9d813a68ef036ef0c7585ab37/tensorflow_ranking/python/keras/pipeline.py#L1026 With the example in the documentation I get an error: dictionary update sequence element #0 has length 1; 2 is required I guess it is deprecated and should now...
Hi, I am trying to build a model based on tensorflow ranking. The project will try to learn the ranking rule of some online service. My features are 0-1 scaled...
It appears the newest version of tensorflow no longer supports the estimator function, which is used in tensorflow-ranking. You probably already know this an have a fix for the next...
In lines 70 and 76 of tensorflow_ranking/python/keras/layers.py, the code snippet should have `**kwargs` as input to `tf.keras.layers.Dense` ``` model = tf.keras.Sequential(name=name) # Input batch normalization. if input_batch_norm: model.add(tf.keras.layers.BatchNormalization(momentum=batch_norm_moment)) for layer_width...