style(rename): rename tests folder to tools where includes visualization&conversion scripts etc.

docs(tools): update scripts under tools.

Author: Kin-Zhang

3_vis.py

@@ -8,7 +8,7 @@
 # listed on the above website.
 
 # Description: produce flow based on model predict and write into the dataset, 
-#              then use tests/scene_flow.py flow_mode="flow_est" to visualize the flow.
+#              then use tools/scene_flow.py flow_mode="flow_est" to visualize the flow.
 """
 
 import torch

README.md

@@ -33,7 +33,7 @@ You can try following methods in our code without any effort to make your own be
 - [x] [SeFlow](https://arxiv.org/abs/2407.01702) (Ours 🚀): ECCV 2024
 - [x] [DeFlow](https://arxiv.org/abs/2401.16122) (Ours 🚀): ICRA 2024
 - [x] [FastFlow3d](https://arxiv.org/abs/2103.01306): RA-L 2021
-- [x] [ZeroFlow](https://arxiv.org/abs/2305.10424): ICLR 2024, their pre-trained weight can covert into our format easily through [the script](tests/zerof2ours.py).
+- [x] [ZeroFlow](https://arxiv.org/abs/2305.10424): ICLR 2024, their pre-trained weight can covert into our format easily through [the script](tools/zerof2ours.py).
 - [ ] [NSFP](https://arxiv.org/abs/2111.01253): NeurIPS 2021, faster 3x than original version because of [our CUDA speed up](assets/cuda/README.md), same (slightly better) performance. Done coding, public after review.
 - [ ] [FastNSF](https://arxiv.org/abs/2304.09121): ICCV 2023. Done coding, public after review.
 <!-- - [ ] [Flow4D](https://arxiv.org/abs/2407.07995): 1st supervise network in the new leaderboard. Done coding, public after review. -->
@@ -160,11 +160,11 @@ python 3_vis.py checkpoint=/home/kin/seflow_best.ckpt dataset_path=/home/kin/dat
 # The output of above command will be like:
 Model: DeFlow, Checkpoint from: /home/kin/model_zoo/v2/seflow_best.ckpt
 We already write the flow_est into the dataset, please run following commend to visualize the flow. Copy and paste it to your terminal:
-python tests/scene_flow.py --flow_mode 'seflow_best' --data_dir /home/kin/data/av2/preprocess_v2/sensor/vis
+python tools/scene_flow.py --flow_mode 'seflow_best' --data_dir /home/kin/data/av2/preprocess_v2/sensor/vis
 Enjoy! ^v^ ------ 
 
 # Then run the command in the terminal:
-python tests/scene_flow.py --flow_mode 'seflow_best' --data_dir /home/kin/data/av2/preprocess_v2/sensor/vis
+python tools/scene_flow.py --flow_mode 'seflow_best' --data_dir /home/kin/data/av2/preprocess_v2/sensor/vis
 ```
 
 https://github.com/user-attachments/assets/f031d1a2-2d2f-4947-a01f-834ed1c146e6

dataprocess/README.md

@@ -140,7 +140,7 @@ Or you can run testing file to visualize the data.
 
 ```bash
 # view gt flow
-python3 tests/scene_flow.py --data_dir /home/kin/data/av2/preprocess/sensor/mini --flow_mode flow
+python3 tools/scene_flow.py --data_dir /home/kin/data/av2/preprocess/sensor/mini --flow_mode flow
 
-python3 tests/scene_flow.py --data_dir /home/kin/data/waymo/preprocess/val --flow_mode flow
+python3 tools/scene_flow.py --data_dir /home/kin/data/waymo/preprocess/val --flow_mode flow
 ```

scripts/pl_model.py

@@ -214,7 +214,7 @@ def on_validation_epoch_end(self):
 
         if self.save_res:
             print(f"We already write the flow_est into the dataset, please run following commend to visualize the flow. Copy and paste it to your terminal:")
-            print(f"python tests/scene_flow.py --flow_mode '{self.vis_name}' --data_dir {self.dataset_path}")
+            print(f"python tools/scene_flow.py --flow_mode '{self.vis_name}' --data_dir {self.dataset_path}")
             print(f"Enjoy! ^v^ ------ \n")
 
     def eval_only_step_(self, batch, res_dict):
@@ -310,5 +310,5 @@ def on_test_epoch_end(self):
         self.model.timer.print(random_colors=False, bold=False)
         print(f"\n\nModel: {self.model.__class__.__name__}, Checkpoint from: {self.load_checkpoint_path}")
         print(f"We already write the flow_est into the dataset, please run following commend to visualize the flow. Copy and paste it to your terminal:")
-        print(f"python tests/scene_flow.py --flow_mode '{self.vis_name}' --data_dir {self.dataset_path}")
+        print(f"python tools/scene_flow.py --flow_mode '{self.vis_name}' --data_dir {self.dataset_path}")
         print(f"Enjoy! ^v^ ------ \n")

tests/README.md

@@ -0,0 +1,36 @@
+Tools
+---
+
+Here we introduce some tools to help you:
+- visualize the data and results.
+- convert the pretrained model from others.
+- ... More to come.
+
+## Visualization
+
+run `tools/scene_flow.py` to view the scene flow dataset with ground truth flow. Note the color wheel in under world coordinate.
+
+```bash
+# view gt flow
+python3 tools/scene_flow.py --data_dir /home/kin/data/av2/preprocess/sensor/mini --flow_mode flow
+
+# view est flow
+python3 tools/scene_flow.py --data_dir /home/kin/data/av2/preprocess/sensor/mini --flow_mode deflow_best
+python3 tools/scene_flow.py --data_dir /home/kin/data/av2/preprocess/sensor/mini --flow_mode seflow_best
+```
+
+Demo Effect (press `SPACE` to stop and start in the visualization window):
+
+https://github.com/user-attachments/assets/f031d1a2-2d2f-4947-a01f-834ed1c146e6
+
+## Conversion
+
+run `tools/zero2ours.py` to convert the ZeroFlow pretrained model to our codebase. 
+
+```bash
+python tools/zero2ours.py --model_path /home/kin/nsfp_distilatation_3x_49_epochs.ckpt --reference_path /home/kin/fastflow3d.ckpt --output_path /home/kin/zeroflow3x.ckpt
+```
+
+- model_path, you can download from: [kylevedder/zeroflow_weights](https://github.com/kylevedder/zeroflow_weights/tree/master/argo)
+- reference_path,  you can download fastflow3d model from: [zendo](https://zenodo.org/records/12632962)
+- output_path, the converted model path. You can then run any evaluation script and visualization script with the converted model.