docs

docs copied to clipboard

Update imbalanced_data.ipynb

2

remove unneeded symbol

artem110101

nbfmt: Support using nbfmt as a component of shell pipeline

2

nbfmt now can read source of a notebook from stdin and can output formatted contents to stdout.

CourierKyn

Wrote a parallel introductory brief of Narrative documentation and Community translations on the page Snapshot of diff is attached as an image file 

deepwrites

Customizable reduction strategy in model docs

1

Fills in the docs related to newly introduced `distribute_reduction_method` in the model for distributed training with custom train_step. Valid together with https://github.com/keras-team/keras/pull/16664

kretes

Update transfer learning tutorial

3

@MarkDaoust

8bitmp3

Update text_classification.ipynb

5

This line was a mistake and probably comes from this page: https://www.tensorflow.org/text/guide/word_embeddings (the model is almost the same except for the Dense(16, activation='relu') layer).

AnasNeumann

update to checkpoint callback options (save_frequency)

1

introduced the number of batches ('n_batches') option for the save frequency instead of 'batch_size'. Using 'batch_size' works in this tutorial because the length of the training data is 1000 which...

gdarkwah

Add a complete code example for loading a model

1

I added a complete code example that can be used to confirm if the TensorFlow C++ API (built from source code with bazel) works.

rangsimanketkaew

Fix load_data/text.ipynb

1

1. Use Softmax activation for export_model that have num_labels > 1: - For models that have num_labels > 1, I think it would be more accurate when using Softmax activation...

18520339

Added Random Normal Init and fixed optimizer hyperparameters

3

In response to the discussions in this [pull request](https://github.com/tensorflow/docs/pull/1643), this pull request adds Random normal initializer with mean 0 and std-dev 1, and fixes the optimizer hyper-parameters as per DC-GAN...

arshagarwal