add readme

Signed-off-by: ramlabserver <[email protected]>

readme.md

@@ -11,13 +11,22 @@ You could checkout the ROS1 version of each inference package:
 
 In this repo, we fully re-structure the code and messages formats for ROS2 (humble), and integrate multi-thread inferencing for three vision tasks.
 
-- Currently all pretrained models are trained using the [visionfactory](https://github.com/Owen-Liuyuxuan/visionfactory) repo. Thus focusing on out-door autonomous driving scenarios. But it is ok to plugin ONNX models that satisfiy the [interface](#onnx-model-interface).
+- Currently all pretrained models are trained using the [visionfactory](https://github.com/Owen-Liuyuxuan/visionfactory) repo. Thus focusing on out-door autonomous driving scenarios. But it is ok to plugin ONNX models that satisfiy the [interface](#onnx-model-interface). Published models description:
+
+| Model | Type | Link | Description |
+| ------------------------------ | ---------------- | --------------------------------------------------------------------------------------------------------------------- | ------------------------------------------------------------------------------------------------------- |
+| monodepth_res101_384_1280.onnx | MonoDepth | [link](https://github.com/Owen-Liuyuxuan/ros2_vision_inference/releases/download/v1.0/monodepth_res101_384_1280.onnx) | FSNet, res101 backbone, model input shape (384x1280) trained on KITTI/KITTI360/nuscenes |
+| bisenetv1.onnx | Segmentation | [link](https://github.com/Owen-Liuyuxuan/ros2_vision_inference/releases/download/v1.0/bisenetv1.onnx) | BiSeNetV1, model input shape (512x768) trained on remapped KITTI360/ApolloScene/CityScapes/BDD100k/a2d2 |
+| mono3d_yolox_576_768.onnx | Mono3D Detection | [link](https://github.com/Owen-Liuyuxuan/ros2_vision_inference/releases/download/v1.0/mono3d_yolox_576_768.onnx) | YoloX-m MonoFlex, model input (576x768) trained on KITTI/nuscenes/ONCE/bdd100k/cityscapes|
+| dla34_deform_576_768.onnx | Mono3D Detection | [link](https://github.com/Owen-Liuyuxuan/ros2_vision_inference/releases/download/v1.0.1/dla34_deform_576_768.onnx) | DLA34 Deformable Upsample MonoFlex, model input (576x768) trained on KITTI/nuscenes/ONCE/bdd100k/cityscapes|
 
 
 ## Getting Started
 
 This repo relies on [ROS2](https://docs.ros.org/en/humble/Installation.html) and onnxruntime:
 
+> If you want to use ROS1, checkout to ROS1 branch with `git checkout ros1`. We tested the ROS1 code in ROS noetic Ubuntu 20.04 (we need python3 so we suggest we at least run at Ubuntu 20.04). The branch `ros1` is a standard ROS1 package built with `catkin_make` and run with `roslaunch`
+
 ```bash
 pip3 install onnxruntime-gpu
 ```
@@ -66,3 +75,13 @@ Segmentation ONNX `def forward(self, normalized_images[1, 3, H, W]):->long[1, H,
 Mono3D ONNX: `def forward(self, normalized_images[1, 3, H, W], P[1, 3, 4]):->scores[N], bboxes[N,12], cls_indexes[N]`
 
 Classes definitions are from the [visionfactory](https://github.com/Owen-Liuyuxuan/visionfactory) repo.
+
+## Data, Domain
+
+### Reshape Scheme
+
+ We resize the input image to the length/width, and pad zero on the others. We also modify the camera intrinsic accordingly before feeding into the onnx model. The output will be de-resized to the original shape. Currently published models are all trained with various input images, so the node should work naturally with different image sources.
+
+### Expected Data Domain
+
+This is related to the training data of the onnx models. The published models now mainly work on autonomous driving/road scenes. Most of the data for the published segmentation models only use the front-facing camera (Detection / MonoDepth are trained with various camera views).