11 Commits (6c7932fe75e541112c065d5ef603525bb0572a9a)

Author	SHA1	Message	Date
Ross Wightman	eb7653614f	Monster commit, activation refactor, VoVNet, norm_act improvements, more ... * refactor activations into basic PyTorch, jit scripted, and memory efficient custom auto * implement hard-mish, better grad for hard-swish * add initial VovNet V1/V2 impl, fix #151 * VovNet and DenseNet first models to use NormAct layers (support BatchNormAct2d, EvoNorm, InplaceIABN) * Wrap IABN for any models that use it * make more models torchscript compatible (DPN, PNasNet, Res2Net, SelecSLS) and add tests	2020-06-01 17:16:52 -07:00
Ross Wightman	4d13db538f	Add x48d ResNext101s to test exclude for ubuntu	2020-05-21 19:13:41 -07:00
Ross Wightman	4212cd3b9f	Another attempt at getting Ubuntu test runner to work	2020-05-21 18:55:10 -07:00
Ross Wightman	20329f2630	Bring down test resolutions to see if we can at least do a fwd on the L2 models	2020-05-21 16:49:46 -07:00
Ross Wightman	3873ea710e	Minor test change	2020-05-21 15:51:47 -07:00
Ross Wightman	afb6bd0669	Add backward and default_cfg tests and fix a few issues found. Fix #153	2020-05-21 15:30:58 -07:00
Ross Wightman	5bd1ad13e7	Refactor test indent	2020-05-12 13:07:46 -07:00
Ross Wightman	9cc289f18c	Exclude EfficientNet-L2 models from test	2020-05-12 13:07:03 -07:00
Ross Wightman	e545bb9401	Update test_inference.py ... Not six min	2020-05-07 10:15:49 -07:00
Ross Wightman	305a2db705	Update test_inference.py ... Make the timeout 5-min for now, see if we can get a pass...	2020-05-07 10:14:24 -07:00
michal	69d725c9fe	Basic forward pass test for all registered models	2020-05-07 00:20:58 -04:00