hide with inference optim API (#17355)

paddle/fluid/API.spec

@@ -50,7 +50,6 @@ paddle.fluid.DataFeedDesc.set_use_slots (ArgSpec(args=['self', 'use_slots_name']
 paddle.fluid.CompiledProgram ('paddle.fluid.compiler.CompiledProgram', ('document', '598d294107d44d7620bce76527a92c37'))
 paddle.fluid.CompiledProgram.__init__ (ArgSpec(args=['self', 'program_or_graph', 'build_strategy'], varargs=None, keywords=None, defaults=(None,)), ('document', '6adf97f83acf6453d4a6a4b1070f3754'))
 paddle.fluid.CompiledProgram.with_data_parallel (ArgSpec(args=['self', 'loss_name', 'build_strategy', 'exec_strategy', 'share_vars_from', 'places'], varargs=None, keywords=None, defaults=(None, None, None, None, None)), ('document', '1c7c6171bbf6d77f2fce0166aa0ec43b'))
-paddle.fluid.CompiledProgram.with_inference_optimize (ArgSpec(args=['self', 'config'], varargs=None, keywords=None, defaults=None), ('document', '9e5b009d850191a010e859189c127fd8'))
 paddle.fluid.ExecutionStrategy ('paddle.fluid.core_avx.ExecutionStrategy', ('document', '535ce28c4671176386e3cd283a764084'))
 paddle.fluid.ExecutionStrategy.__init__ __init__(self: paddle.fluid.core_avx.ParallelExecutor.ExecutionStrategy) -> None
 paddle.fluid.BuildStrategy ('paddle.fluid.core_avx.BuildStrategy', ('document', 'eec64b9b7cba58b0a63687b4c34ffe56'))

python/paddle/fluid/compiler.py

@@ -237,7 +237,7 @@ class CompiledProgram(object):
 
         return self
 
-    def with_inference_optimize(self, config):
+    def _with_inference_optimize(self, config):
         """ Add inference optimize
 
         Args:

python/paddle/fluid/sampcd_processor.py

@@ -740,7 +740,7 @@ wlist_inneed = [
     "DistributeTranspilerConfig.min_block_size",
     "ExecutionStrategy.allow_op_delay", "load", "Accuracy.update",
     "ChunkEvaluator.update", "ExecutionStrategy.num_iteration_per_drop_scope",
-    "ExecutionStrategy.num_threads", "CompiledProgram.with_inference_optimize",
+    "ExecutionStrategy.num_threads", "CompiledProgram._with_inference_optimize",
     "CompositeMetric.add_metric", "CompositeMetric.update",
     "CompositeMetric.eval", "DetectionMAP.get_map_var", "MetricBase",
     "MetricBase.reset", "MetricBase.get_config", "MetricBase.update",

python/paddle/fluid/tests/book/test_word2vec.py

@@ -214,7 +214,7 @@ def infer(use_cuda, save_dirname=None):
             infer_config.device = 0
             infer_config.fraction_of_gpu_memory = 0.15
         compiled_program = fluid.compiler.CompiledProgram(inference_program)
-        compiled_program.with_inference_optimize(infer_config)
+        compiled_program._with_inference_optimize(infer_config)
         assert compiled_program._is_inference is True
         infer_outputs = exe.run(compiled_program, feed=infer_inputs)
         np_data = np.array(results[0])