docs(env): update cuda install inside yaml file.

Author: Kin-Zhang

README.md

@@ -62,6 +62,8 @@ There are two ways to install the codebase: directly on your [local machine](#en
 
 ### Environment Setup
 
+We use conda to manage the environment, you can install it follow [here](assets/README.md#system). Then create the base environment with the following command [5~15 minutes]:
+
 ```bash
 git clone --recursive https://github.com/KTH-RPL/OpenSceneFlow.git
 cd OpenSceneFlow && mamba env create -f environment.yaml
@@ -70,14 +72,6 @@ cd OpenSceneFlow && mamba env create -f environment.yaml
 # export LD_LIBRARY_PATH=$LD_LIBRARY_PATH:/home/kin/mambaforge/lib
 ```
 
-CUDA package (we already install nvcc compiler inside conda env), the compile time is around 1-5 minutes:
-```bash
-mamba activate opensf
-# CUDA already install in python environment. I also tested others version like 11.3, 11.4, 11.7, 11.8 all works
-cd assets/cuda/mmcv && python ./setup.py install && cd ../../..
-cd assets/cuda/chamfer3D && python ./setup.py install && cd ../../..
-```
-
 ### Docker (Recommended for Isolation)
 
 You always can choose [Docker](https://en.wikipedia.org/wiki/Docker_(software)) which isolated environment and free yourself from installation. Pull the pre-built Docker image or build manually.
@@ -115,8 +109,11 @@ Once extracted, you can directly use this dataset to run the [training script](#
 
 ## 2. Quick Start
 
-Don't forget to active Python environment before running the code. 
-If you want to use [wandb](wandb.ai), replace all `entity="kth-rpl",` to your own entity otherwise tensorboard will be used locally.
+Some tips before running the code:
+* Don't forget to active Python environment before running the code. 
+* If you want to use [wandb](wandb.ai), replace all `entity="kth-rpl",` to your own entity otherwise tensorboard will be used locally.
+* Set correct data path by passing the config, e.g. `train_data=/home/kin/data/av2/h5py/demo/train val_data=/home/kin/data/av2/h5py/demo/val`.
+
 And free yourself from trainning, you can download the pretrained weight from [HuggingFace](https://huggingface.co/kin-zhang/OpenSceneFlow) and we provided the detail `wget` command in each model section.
 
 ```bash

assets/README.md

@@ -65,22 +65,14 @@ bash Miniforge3-$(uname)-$(uname -m).sh
 
 ### Environment
 
-Create base env: [~5 mins]
+Create base env: [5~15 minutes based on your network speed and cpu]
 
 ```bash
 git clone https://github.com/KTH-RPL/OpenSceneFlow.git
 cd OpenSceneFlow
 mamba env create -f assets/environment.yml
 ```
 
-CUDA package (nvcc compiler already installed through conda), the compile time is around 1-5 minutes:
-```bash
-mamba activate opensf
-cd assets/cuda/mmcv && python ./setup.py install && cd ../../..
-cd assets/cuda/chamfer3D && python ./setup.py install && cd ../../..
-```
-
-
 Checking important packages in our environment now:
 ```bash
 mamba activate opensf

environment.yaml

@@ -30,6 +30,8 @@ dependencies:
   - pathtools
   - rerun-sdk
   - pip:
+    - assets/cuda/chamfer3D
+    - assets/cuda/mmcv
     - open3d==0.18.0
     - dztimer
     - av2==0.2.1
@@ -46,4 +48,4 @@ dependencies:
 # open3d==0.18.0: because 0.17.0 have bug on set the view json file
 # dufomap==1.0.0: in case later updating may not compatible with the code.
 # spconv-cu117==2.3.6: avoid error: KeyError: ((16, 8, 8), float, float)
-# torch-scatter==2.1.2: in case later updating may not compatible with the code.
+# torch-scatter==2.1.2: in case later updating may not compatible with the code.