Merge branch 'master' into zixuan/new_config

Conflicts:
	neural_compressor/config.py

Author: violetch24

neural_compressor/config.py

@@ -149,6 +149,22 @@ def tensorboard(self, tensorboard):
 class BenchmarkConfig:
     """Config Class for Benchmark.
 
+    Args:
+        inputs (list, optional): A list of strings containing the inputs of model. Default is an empty list.
+        outputs (list, optional): A list of strings containing the outputs of model. Default is an empty list.
+        backend (str, optional): Backend name for model execution. Supported values include: 'default', 'itex',
+                                'ipex', 'onnxrt_trt_ep', 'onnxrt_cuda_ep'. Default value is 'default'.
+        warmup (int, optional): The number of iterations to perform warmup before running performance tests.
+                                Default value is 5.
+        iteration (int, optional): The number of iterations to run performance tests. Default is -1.
+        cores_per_instance (int, optional): The number of CPU cores to use per instance. Default value is None.
+        num_of_instance (int, optional): The number of instances to use for performance testing.
+                                         Default value is None.
+        inter_num_of_threads (int, optional): The number of threads to use for inter-thread operations.
+                                              Default value is None.
+        intra_num_of_threads (int, optional): The number of threads to use for intra-thread operations.
+                                              Default value is None.
+
     Example::
 
         # Run benchmark according to config
@@ -1156,6 +1172,21 @@ def teacher_model(self, teacher_model):
 
 class MixedPrecisionConfig(_BaseQuantizationConfig):
     """Config Class for MixedPrecision.
+    
+    Args:
+        device (str, optional): device for execution. Support 'cpu' and 'gpu', default is 'cpu'
+        backend (str, optional): backend for model execution. Support 'default', 'itex', 'ipex',
+                                    'onnxrt_trt_ep', 'onnxrt_cuda_ep', default is 'default'
+        precision (str, optional): target precision for mix precision conversion.
+                                      Support 'bf16' and 'fp16', default is 'bf16'
+        inputs (list, optional): inputs of model, default is []
+        outputs (list, optional): outputs of model, default is []
+        tuning_criterion (TuningCriterion object, optional): accuracy tuning settings, it won't work
+                                                             if there is no accuracy tuning process
+        accuracy_criterion (AccuracyCriterion object, optional): accuracy constraint settings, it won't
+                                                                 work if there is no accuracy tuning process
+        excluded_precisions (list, optional): precisions to be excluded during mix precision conversion, 
+                                              default is []
 
     Example::
 
@@ -1330,7 +1361,28 @@ def __init__(
 
 
 class TF2ONNXConfig(ExportConfig):
-    """Config Class for TF2ONNX."""
+    """Config Class for TF2ONNX.
+
+    Args:
+        dtype (str, optional): The data type of export target model. Supports 'fp32' and 'int8'.
+                               Defaults to 'int8'.
+        opset_version (int, optional): The version of the ONNX operator set to use. Defaults to 14.
+        quant_format (str, optional): The quantization format for the export target model.
+                                      Supports 'default', 'QDQ' and 'QOperator'. Defaults to 'QDQ'.
+        example_inputs (list, optional): A list example inputs to use for tracing the model.
+                                        Defaults to None.
+        input_names (list, optional): A list of model input names. Defaults to None.
+        output_names (list, optional): A list of model output names. Defaults to None.
+        dynamic_axes (dict, optional): A dictionary of dynamic axis information. Defaults to None.
+        **kwargs: Additional keyword arguments.
+
+    Examples::
+
+        # tensorflow QDQ int8 model 'q_model' export to ONNX int8 model
+        from neural_compressor.config import TF2ONNXConfig
+        config = TF2ONNXConfig()
+        q_model.export(output_graph, config)
+    """
     def __init__(
        self,
        dtype="int8",