Use current class __next__ implementation in __init__, to avoid special handling of first batch in child classes #2363
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
…d special handling of first batch when writing iterator wrapper classes Signed-off-by: Joaquin Anton <janton@nvidia.com>
|
!build |
JanuszL
approved these changes
Oct 15, 2020
|
CI MESSAGE: [1703801]: BUILD STARTED |
mzient
approved these changes
Oct 15, 2020
JanuszL
reviewed
Oct 15, 2020
| @@ -230,7 +230,7 @@ def __init__(self, | |||
| with p._check_api_type_scope(types.PipelineAPIType.ITERATOR): | |||
| p.schedule_run() | |||
| self._first_batch = None | |||
| self._first_batch = self.next() | |||
| self._first_batch = DALIGenericIterator.next(self) | |||
There was a problem hiding this comment.
Suggested change
| self._first_batch = DALIGenericIterator.next(self) | |
| self._first_batch = DALIGenericIterator.__next__(self) |
Because:
def next(self):
"""
Returns the next batch of data.
"""
return self.__next__()
JanuszL
reviewed
Oct 15, 2020
|
CI MESSAGE: [1703801]: BUILD FAILED |
Signed-off-by: Joaquin Anton <janton@nvidia.com>
mzient
approved these changes
Oct 15, 2020
JanuszL
reviewed
Oct 16, 2020
|
|
||
| pipe = Pipeline(batch_size = 16, num_threads = 1, device_id = 0) | ||
| with pipe: | ||
| data = fn.uniform(range=(-1, 1), shape=(20, 30, 3), seed=1234) |
There was a problem hiding this comment.
Suggested change
| data = fn.uniform(range=(-1, 1), shape=(20, 30, 3), seed=1234) | |
| data = fn.uniform(range=(-1, 1), shape=(2, 2, 2), seed=1234) |
I think we can make it as simple as possible
JanuszL
reviewed
Oct 16, 2020
| super(IteratorWrapper, self).__init__(*args, **kwargs) | ||
|
|
||
| def __next__(self): | ||
| assert(self._allow_next) |
There was a problem hiding this comment.
I would add a comment why this works.
JanuszL
approved these changes
Oct 16, 2020
Signed-off-by: Joaquin Anton <janton@nvidia.com>
|
!build |
|
CI MESSAGE: [1707353]: BUILD STARTED |
|
CI MESSAGE: [1707353]: BUILD PASSED |
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.
Signed-off-by: Joaquin Anton janton@nvidia.com
Why we need this PR?
Currently, custom iterators that override next() function need to be aware that the first batch was produced during init, which invokes the child class next, therefore the first iteration produces a "wrapped" batch while the following don't.
What happened in this PR?
Fill relevant points, put NA otherwise. Replace anything inside []
Use current class next function in DALIGenericIterator
FW iterators
N/A
N/A
N/A
JIRA TASK: [DALI-1635]