Fixing the wrong predictions in transfer_learning.ipynb

[tilakrayal]

In the Transfer_learning https://www.tensorflow.org/tutorials/images/transfer_learning,
After running the last cell for prediction on test data with fine-tuned model, the output at the end of the code cell predicts all 1, which is wrong prediction

Document:
#Apply a sigmoid since our model returns logits
predictions = tf.nn.sigmoid(predictions)
predictions = tf.where(predictions < 0.5, 0, 1)

This can be fixed by commenting/removing the part in the last cell where we apply the sigmoid function on the predictions,
#Apply a sigmoid since our model returns logits
predictions = tf.nn.sigmoid(predictions) ======> removed this line
predictions = tf.where(predictions < 0.5, 0, 1)

The original behavior is happening because we already applied a sigmoid activation in the classification head's prediction layer while we were making the model for feature extraction.

Kindly find the gist for the reference which was providing the correct output after removing/commenting the above mentioned(TF.nn.sigmoid) line. Thank you!

[github-actions]

Preview

Preview and run these notebook edits with Google Colab:

• site/en/tutorials/images/transfer_learning.ipynb

Rendered notebook diffs available on ReviewNB.com.

Format and style

Use the TensorFlow docs notebook tools to format for consistent source diffs and lint for style:

$ python3 -m pip install -U --user git+https://github.com/tensorflow/docs

$ python3 -m tensorflow_docs.tools.nbfmt notebook.ipynb

$ python3 -m tensorflow_docs.tools.nblint --arg=repo:tensorflow/docs notebook.ipynb

If commits are added to the pull request, synchronize your local branch: git pull origin patch-16

[lbo462]

Maybe you should remove this comment since we're not applying a sigmoid anymore ...

[MarkDaoust]

Yes, thanks!