Merge pull request #427 from rwightman/nfnet

Add NFNet-F models and tweak existing NF models.

Author: rwightman

README.md

@@ -2,6 +2,9 @@
 
 ## What's New
 
+### Feb 12, 2021
+* Update Normalization-Free nets to include new NFNet-F (https://arxiv.org/abs/2102.06171) model defs
+
 ### Feb 10, 2021
 * First Normalization-Free model training experiments done,
   * nf_resnet50 - 80.68 top-1 @ 288x288, 80.31 @ 256x256
@@ -164,6 +167,7 @@ A full version of the list below with source links can be found in the [document
 * Inception-ResNet-V2 and Inception-V4 - https://arxiv.org/abs/1602.07261
 * MobileNet-V3 (MBConvNet w/ Efficient Head) - https://arxiv.org/abs/1905.02244
 * NASNet-A - https://arxiv.org/abs/1707.07012
+* NFNet-F - https://arxiv.org/abs/2102.06171
 * NF-RegNet / NF-ResNet - https://arxiv.org/abs/2101.08692
 * PNasNet - https://arxiv.org/abs/1712.00559
 * RegNet - https://arxiv.org/abs/2003.13678

tests/test_models.py

@@ -19,7 +19,9 @@
 # exclude models that cause specific test failures
 if 'GITHUB_ACTIONS' in os.environ:  # and 'Linux' in platform.system():
     # GitHub Linux runner is slower and hits memory limits sooner than MacOS, exclude bigger models
-    EXCLUDE_FILTERS = ['*efficientnet_l2*', '*resnext101_32x48d', '*in21k', '*152x4_bitm'] + NON_STD_FILTERS
+    EXCLUDE_FILTERS = [
+        '*efficientnet_l2*', '*resnext101_32x48d', '*in21k', '*152x4_bitm',
+        'nfnet_f4*', 'nfnet_f5*', 'nfnet_f6*', 'nfnet_f7*'] + NON_STD_FILTERS
 else:
     EXCLUDE_FILTERS = NON_STD_FILTERS