Update README.md

deployment/README.md

@@ -1,14 +1,14 @@
 # LibTorch Inference
 
-A LibTorch inference implementation of yolov5. Both GPU and CPU are supported.
+The LibTorch inference of yolort. Both GPU and CPU are supported.
 
 ## Dependencies
 
 - Ubuntu 18.04
-- CUDA 10.2
-- LibTorch 1.7.0+
-- TorchVision 0.8.1+
+- LibTorch 1.8.0 / 1.9.0
+- TorchVision 0.9.0 / 0.10.0
 - OpenCV 3.4+
+- CUDA 10.2 [Optional]
 
 ## Usage
 
@@ -24,16 +24,16 @@ A LibTorch inference implementation of yolov5. Both GPU and CPU are supported.
     ```bash
     git clone https://github.com/pytorch/vision.git
     cd vision
-    git checkout release/0.8.0 # replace to `nightly` branch instead if you are using the nightly version
+    git checkout release/0.9  # replace to `nightly` branch instead if you are using the nightly version
     mkdir build && cd build
-    cmake .. -DTorch_DIR=$TORCH_PATH/share/cmake/Torch
+    cmake .. -DTorch_DIR=$TORCH_PATH/share/cmake/Torch  # Set `-DWITH_CUDA=ON` if you're using GPU
     make -j4
     sudo make install
     ```
 
 1. Generate `TorchScript` model
 
-    Unlike [ultralytics's](https://github.com/ultralytics/yolov5/blob/master/models/export.py) trace (`torch.jit.trace`) mechanism, I'm using `torch.jit.script` to jit trace the YOLO models which containing the whole pre-processing (especially using the `GeneralizedRCNNTransform` ops) and post-processing (especially with the `nms` ops) procedures, so you don't need to rewrite manually the cpp codes of pre-processing and post-processing.
+    Unlike [ultralytics's](https://github.com/ultralytics/yolov5/blob/master/models/export.py) trace (`torch.jit.trace`) mechanism, We're using `torch.jit.script` to trace the YOLOv5 models which containing the whole pre-processing (especially using the `letterbox` ops) and post-processing (especially with the `nms` ops) procedures, so you don't need to rewrite manually the C++ codes of pre-processing and post-processing.
 
     ```bash
     git clone https://github.com/zhiqwang/yolov5-rt-stack.git