complete v2.0 test

JiahangXu · JiahangXu · commit cd9bcb3ce254 · 2022-06-27T05:17:20.000-04:00
diff --git a/docs/builder/build_kernel_latency_predictor.md b/docs/builder/build_kernel_latency_predictor.md
@@ -244,7 +244,7 @@ predictor, data = build_predictor_for_kernel(
 )
 ```
 
-In the experiment of nn-Meter, we set `init_sample_num` as 1000, `finegrained_sample_num` as 10, `iteration` as 5, and `error_threshold` as 0.1.
+In the experiment of nn-Meter, we set default `init_sample_num` as 1000, `finegrained_sample_num` as 10, `iteration` as 5, and `error_threshold` as 0.1.
 
 nn-Meter also provided a end-to-end method for users to build a series of general latency predictors, named `nn_meter.builder.build_latency_predictor`. This method will build predictors for all kernels in `<workspace-path>/configs/predictorbuild_config.yaml` according to their corresponding parameters. The parameters includes `INIT_SAMPLE_NUM`, `FINEGRAINED_SAMPLE_NUM`, `ITERATION`, and `ERROR_THRESHOLD`. Here is an example:
 
diff --git a/setup.py b/setup.py
@@ -5,7 +5,7 @@
 
 setup(
     name='nn-meter',
-    version='2.0a1',
+    version='2.0',
     description='nn-Meter is a novel and efficient system to accurately predict the inference latency of DNN models on diverse edge devices.',
     long_description = open('README.md', encoding='utf-8').read(),
     long_description_content_type = 'text/markdown',

Original file line number	Diff line number	Diff line change
`@@ -244,7 +244,7 @@ predictor, data = build_predictor_for_kernel(`
`244`	`244`	`)`
`245`	`245`	```
`246`	`246`
`247`		-In the experiment of nn-Meter, we set `init_sample_num` as 1000, `finegrained_sample_num` as 10, `iteration` as 5, and `error_threshold` as 0.1.
	`247`	+In the experiment of nn-Meter, we set default `init_sample_num` as 1000, `finegrained_sample_num` as 10, `iteration` as 5, and `error_threshold` as 0.1.
`248`	`248`
`249`	`249`	nn-Meter also provided a end-to-end method for users to build a series of general latency predictors, named `nn_meter.builder.build_latency_predictor`. This method will build predictors for all kernels in `<workspace-path>/configs/predictorbuild_config.yaml` according to their corresponding parameters. The parameters includes `INIT_SAMPLE_NUM`, `FINEGRAINED_SAMPLE_NUM`, `ITERATION`, and `ERROR_THRESHOLD`. Here is an example:
`250`	`250`