Merge pull request #76 from andreped/andreped-patch-2

README technique order update [no ci]

README.md

@@ -74,8 +74,8 @@ Our implementations enable theoretically **infinitely large batch size**, with *
 
 | Technique | Usage |
 | - | - |
-| `Adaptive Gradient Clipping` | `model = GradientAccumulateModel(accum_steps=4, agc=True, inputs=model.input, outputs=model.output)` |
 | `Batch Normalization` | `layer = AccumBatchNormalization(accum_steps=4)` |
+| `Adaptive Gradient Clipping` | `model = GradientAccumulateModel(accum_steps=4, agc=True, inputs=model.input, outputs=model.output)` |
 | `Mixed precision` | `model = GradientAccumulateModel(accum_steps=4, mixed_precision=True, inputs=model.input, outputs=model.output)` |
 
 * As batch normalization (BN) is not natively compatible with GA, we have implemented a custom BN layer which can be used as a drop-in replacement.