ammended the example (#12)

Author: tanayvarshney

Quick_Deploy/PyTorch/README.md

@@ -33,7 +33,7 @@ This README showcases how to deploy a simple ResNet model on Triton Inference Se
 
 ## Step 1: Export the model
 
-Save the PyTorch model.
+Save the PyTorch model. This model needs to be traced/scripted to obtain a torchscript model.
 
 ```
 # <xx.xx> is the yy:mm for the publishing tag for NVIDIA's PyTorch 

Quick_Deploy/PyTorch/export.py

@@ -25,8 +25,8 @@
 # OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 import torch
-import torch_tensorrt
 torch.hub._validate_not_a_forked_repo=lambda a,b,c: True
 
 model = torch.hub.load('pytorch/vision:v0.10.0', 'resnet50', pretrained=True).eval().to("cuda")
-torch.save(model, "model.pt")
+traced_model = torch.jit.trace(model, torch.randn(1,3,224,224).to("cuda"))
+torch.jit.save(traced_model, "model.pt")