zhongyu zhang 876b2ac033

[Feature] Add Zero-shot Knowledge Transfer via Adversarial Belief Matching (#241) ...

* 1.Add ZSKT algorithm with zskt_generator, at_loss. 2.Add teacher_detach in kl_divergence.

* 1.Amend readme. 2.Revise UT bugs of test_graph and test_distill.

* 1.Amend docstring of zskt_generator

* 1.Add torch version judgment in test_distillation_loss.

* 1.Revise defaults of batch_size to 1 in generators. 2.Revise mmcls.data to mmcls.structures

* 1.Rename function "at" to "calc_attention_matrix".

2022-08-24 14:57:35 +08:00

..

test_autoslim.py

[Feature] Add Zero-shot Knowledge Transfer via Adversarial Belief Matching (#241)

2022-08-24 14:57:35 +08:00

test_base_algorithm.py

…

test_darts.py

Refactor darts (#204)

2022-07-25 09:52:39 +08:00

test_datafree_distill.py

[fix] fix mmcv mmengine (#242)

2022-08-24 09:58:11 +08:00

test_self_distill.py

[fix] fix mmcv mmengine (#242)

2022-08-24 09:58:11 +08:00

test_single_teacher_distill.py

[fix] fix mmcv mmengine (#242)

2022-08-24 09:58:11 +08:00

test_slimmable_network.py

[Feature] Add Zero-shot Knowledge Transfer via Adversarial Belief Matching (#241)

2022-08-24 14:57:35 +08:00

test_spos.py

[Feature] Add slimmable algorithm

2022-07-15 23:05:07 +08:00

toy_models.py

[Feature] Add DAFL Distillation (#235)

2022-08-23 10:47:34 +08:00