Update preprocess_input function for tf.data #132
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Hi, there. I found some bug of 'preprocess_input' function when i used the function with tf.data.
What is this PR? 🔍
This issue was occured when we use the function in the tf.data like below.
Let me reproduce the bug.
First, we usually the function like below. It works well.
![image](https://user-images.githubusercontent.com/19839987/100058828-5a865c80-2e6d-11eb-9b51-5d0449649be7.png)
But, when we use this function inside of tf.data flow. It didn't work like below.
![image](https://user-images.githubusercontent.com/19839987/100059167-f57f3680-2e6d-11eb-9a7c-954f8c542c27.png)
Changes 📝
There may be some change in the preprocess function in the tf.keras.
![image](https://user-images.githubusercontent.com/19839987/100059227-0fb91480-2e6e-11eb-81bd-5db9dd953ed4.png)
![image](https://user-images.githubusercontent.com/19839987/100060085-6a06a500-2e6f-11eb-9c76-ecc41827c7f0.png)
So, I just changed origin package 'keras_applications' to 'tensorflow.keras.applications'. And It worked well.
I think It's better to change 'keras_applications' to 'tensorflow.keras.applications' because now the keras backend support tensorflow only,
Thank you.