From 252499c6334592f56d84b71c86a1cee254eb9b24 Mon Sep 17 00:00:00 2001
From: Qasim Khan <straightouttadetroit.qk@gmail.com>
Date: Thu, 1 Jun 2023 13:32:02 +0500
Subject: [PATCH] Copy float_model using load_model

---
 prototype_source/fx_graph_mode_ptq_static.rst | 8 ++++----
 1 file changed, 4 insertions(+), 4 deletions(-)

diff --git a/prototype_source/fx_graph_mode_ptq_static.rst b/prototype_source/fx_graph_mode_ptq_static.rst
index f97b1f0a5f2..091673ed2e4 100644
--- a/prototype_source/fx_graph_mode_ptq_static.rst
+++ b/prototype_source/fx_graph_mode_ptq_static.rst
@@ -214,9 +214,9 @@ Download the `torchvision resnet18 model <https://download.pytorch.org/models/re
     float_model = load_model(saved_model_dir + float_model_file).to("cpu")
     float_model.eval()
 
-    # deepcopy the model since we need to keep the original model around
-    import copy
-    model_to_quantize = copy.deepcopy(float_model)
+    # create another instance of the model since
+    # we need to keep the original model around
+    model_to_quantize = load_model(saved_model_dir + float_model_file).to("cpu")
 
 3. Set model to eval mode
 -------------------------
@@ -408,4 +408,4 @@ Running the model in AIBench (with single threading) gives the following result:
 
 As we can see for resnet18 both FX graph mode and eager mode quantized model get similar speedup over the floating point model,
 which is around 2-4x faster than the floating point model. But the actual speedup over floating point model may vary
-depending on model, device, build, input batch sizes, threading etc.
\ No newline at end of file
+depending on model, device, build, input batch sizes, threading etc.