use ema weights when exporting models

Summary:
Use EMA weights when exporting the model. Many previous FBNetV3_B* + EMA training runs didn't have this config flag set, so setting it here during export when the model is built.

If a model uses EMA (MODEL_EMA.ENABLED = True), then this flag will take effect and use EMA weights. Otherwise, this flag has no effect on the export.

Yanghan may be adding `torchscript_mobile` export type, deprecating this script, soon.

Reviewed By: vivekn, sanjeevk42

Differential Revision: D26412081

fbshipit-source-id: 98f5402279ab02157e5e3dbefd41840a5e230d94

d2go/modeling/backbone/fbnet_v2.py

@@ -49,7 +49,7 @@ def _get_builder_norm_args(cfg):
 
 def _merge_fbnetv2_arch_def(cfg):
     arch_def = {}
-    assert all(isinstance(x, dict) for x in cfg.MODEL.FBNET_V2.ARCH_DEF)
+    assert all(isinstance(x, dict) for x in cfg.MODEL.FBNET_V2.ARCH_DEF), cfg.MODEL.FBNET_V2.ARCH_DEF
     for dic in cfg.MODEL.FBNET_V2.ARCH_DEF:
         arch_def.update(dic)
     return arch_def