dump actual_subset_size #2769
dump actual_subset_size #2769
Conversation
github-actions
bot
added
the
NNCF OpenVINO
|
@l-bat HI, could you please help me review the PR? |
| dataset_length = dataset.get_length() | ||
| if dataset_length: | ||
| return min(dataset_length, subset_size) | ||
| return subset_size |
There was a problem hiding this comment.
if __len()__ is not implemented, the actual subset size should be obtained as:
actual_subset_size = 0
for data in islice(calibration_dataset.get_inference_data(), subset_size):
actual_subset_size = 1There was a problem hiding this comment.
Sorry for the late reply. I found that the suggested changes do not work because the calibration_dataset.get_inference_data() iterator is consumed before dump_parameters. As a result, actual_subset_size ends up being zero. Could you please provide some suggestions on how to handle this issue?
Thank you very much! @l-bat
There was a problem hiding this comment.
@awayzjj after discussing within the team, we decided not to add actual_subset_size to rt_info because rt_info is intended to contain quantization parameters provided to algorithms. If the provided dataset is shorter than subset_size, we should display a warning during the statistics collection process:
|
|
||
|
|
||
| @pytest.mark.parametrize("subset_size, expected_actual_subset_size", [[1, 1], [2, 1]]) | ||
| def test_dump(subset_size, expected_actual_subset_size, tmp_path): |
There was a problem hiding this comment.
Please add 2 tests:
__len()__implemented__len()__not implemented
|
hey @awayzjj will you continue work on this? |
|
@mlukasze Yes, sorry for the delay, I will finish it this weekend :) |
Changes
Dump actual_subset_size to ov.Model
Reason for changes
Inconsistencies arise when the dataset size is less than the provided or default 'subset_size'.
Related tickets
Closes: #2562
Tests
WIP