Fewshot learning predict proba #3267
Conversation
…fewshot_learning
…fewshot_learning
…fewshot_learning_proba
yongxinw
added
the
model list checked
|
Job PR-3267-0137e8a is done. |
|
Job PR-3267-28660cf is done. |
|
Job PR-3267-869c0e8 is done. |
There was a problem hiding this comment.
We may need to align with test_predictor (https://github.com/autogluon/autogluon/blob/master/multimodal/tests/unittests/predictor/test_predictor.py#L252-L283) to facilitate future learner refactor. After the refactor, few shot predictor will reuse the MultiModalPredictor APIs, so the tests should also be compatible.
| from autogluon.multimodal.utils.few_shot_learning import FewShotSVMPredictor | ||
| from autogluon.multimodal.utils.misc import shopee_dataset | ||
|
|
||
|
|
||
| def verify_evaluate(test_data, predictor): | ||
| results = predictor.evaluate(test_data) | ||
|
|
There was a problem hiding this comment.
Can we reuse verify_predictor_save_load (https://github.com/autogluon/autogluon/blob/master/multimodal/tests/unittests/predictor/test_predictor.py#L46)? We may need to merge the tests after the learner refactor.
| assert (preds == preds2).all() | ||
| return preds | ||
|
|
||
|
|
||
| def test_fewshot_fit_predict(): |
There was a problem hiding this comment.
Can we also test realtime inference (https://github.com/autogluon/autogluon/blob/master/multimodal/tests/unittests/predictor/test_predictor.py#LL263C5-L263C30)?
|
|
||
| results = predictor.evaluate(test_data) | ||
| verify_predict_as_pandas_multiclass(test_data, predictor) |
There was a problem hiding this comment.
Continuous training seems also missing (https://github.com/autogluon/autogluon/blob/master/multimodal/tests/unittests/predictor/test_predictor.py#L275-L283).
…fewshot_learning_proba
…fewshot_learning_proba
|
Job PR-3267-f8b9ba4 is done. |
|
Job PR-3267-792191a is done. |
* 'master' of https://github.com/awslabs/autogluon: (24 commits) [WIP] 0.8.0 release notes (autogluon#3303) Add model keys doc (autogluon#3321) Fix NaN warning in np.array(X) (autogluon#3315) [Draft] Upgrade networkx to 3.x (autogluon#3317) Add calibrate_decision_threshold tutorial (autogluon#3316) [Doc] AutoMM FAQ Updates (autogluon#3314) Update to v0.8.0 (autogluon#3313) Add Experimental Zeroshot HPO (autogluon#3312) Update GPU installation guide to use CUDA 11.7 (autogluon#3306) [Tutorial]Update tutorials for object detection (autogluon#3305) [timeseries] Update documentation (autogluon#3297) Update mac cpu install instructions (autogluon#3280) Add docstring for hyperparameter_tune_kwargs (autogluon#3307) [Doc] Add Search Space Page (autogluon#3311) Fewshot learning predict proba (autogluon#3267) Fix log to file Windows tests (autogluon#3302) Add missing doc pages (autogluon#3304) Add calibrate_decision_threshold (autogluon#3298) continuous training tutorial update (autogluon#3300) Add TabPFN (autogluon#3270) ...
Issue #, if available:
Description of changes:
Adding predict proba for fewshot svm learner
By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.