round up the number of batches per epoch #30
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Instead of np.floor, I think np.ceil is the right form of rounding to use. this is with reference to the tensorflow/keras documentation (https://www.tensorflow.org/api_docs/python/tf/keras/utils/Sequence) Example explanation: given a sample size (or the length of list_enzymes in this context) of 35 and a batch_size of 10, using np.floor will result in 3 batches. This leaves out the remaining 5 samples in the list_enzymes. meanwhile, using the ceil will result in 4 batches which covers the last 5 samples. You may be wondering about indexing in __getitem__ but since the self.indexes is a numpy array, indexing beyond the length of that array will just truncate at the end of the arra.
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
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Outdated suggestions cannot be applied.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.
Instead of np.floor, I think np.ceil is the right form of rounding to use. this is with reference to the tensorflow/keras documentation (https://www.tensorflow.org/api_docs/python/tf/keras/utils/Sequence)
Example explanation:
given a sample size (or the length of list_enzymes in this context) of 35 and a batch_size of 10, using np.floor will result in 3 batches. This leaves out the remaining 5 samples in the list_enzymes. meanwhile, using the ceil will result in 4 batches which covers the last 5 samples. You may be wondering about indexing in getitem but since the self.indexes is a numpy array, indexing beyond the length of that array will just truncate at the end of the arra.