refine nn-Meter API and add nn-meter in README.md (#4001)

* refactor nn-Meter multi-trial to adapt new structure of nn-Meter

* add github repo link of nn-Meter

* refine nn-Meter API and add nn-meter in README.md

README.md

@@ -356,6 +356,7 @@ Targeting at openness and advancing state-of-art technology, [Microsoft Research
 * [FrameworkController](https://github.com/Microsoft/frameworkcontroller) : an open source general-purpose Kubernetes Pod Controller that orchestrate all kinds of applications on Kubernetes by a single controller.
 * [MMdnn](https://github.com/Microsoft/MMdnn) : A comprehensive, cross-framework solution to convert, visualize and diagnose deep neural network models. The "MM" in MMdnn stands for model management and "dnn" is an acronym for deep neural network.
 * [SPTAG](https://github.com/Microsoft/SPTAG) : Space Partition Tree And Graph (SPTAG) is an open source library for large scale vector approximate nearest neighbor search scenario.
+* [nn-Meter](https://github.com/microsoft/nn-Meter) : An accurate inference latency predictor for DNN models on diverse edge devices.
 
 We encourage researchers and students leverage these projects to accelerate the AI development and research.
 

examples/nas/oneshot/spos/multi_trial.py

@@ -13,7 +13,7 @@ from torchvision.datasets import CIFAR10
 
 from blocks import ShuffleNetBlock, ShuffleXceptionBlock
 
-from nn_meter import get_default_config, load_latency_predictors
+from nn_meter import load_latency_predictors
 
 
 class ShuffleNetV2(nn.Module):
@@ -146,7 +146,7 @@ class LatencyFilter:
         self.threshold = threshold
 
     def __call__(self, ir_model):
-        latency = self.predictors.predict(ir_model, 'nni')
+        latency = self.predictors.predict(ir_model, 'nni-ir')
         return latency < self.threshold