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_classical_models	[Feature] Add Zero-shot Knowledge Transfer via Adversarial Belief Matching (#241)	2022-08-24 14:57:35 +08:00
__init__.py	[Feature] Add slimmable algorithm	2022-07-15 23:05:07 +08:00
test_channel_mutator.py	[Feature] Add slimmable algorithm	2022-07-15 23:05:07 +08:00
test_diff_mutator.py	[Refactor] Move `build_arch_param` from `DiffMutableModule` to `DiffModuleMutator` (#221)	2022-08-10 10:05:32 +08:00
test_one_shot_mutator.py	Align SPOS and DetNAS to MMRazor2.0	2022-07-15 23:04:38 +08:00
utils.py	[Feature] Add dynamic bricks (#228)	2022-08-19 15:15:38 +08:00