Update README.md

README.md

@@ -6,6 +6,14 @@ tags:
 language:
 - en
 ---
+---
+tags:
+- computer-vision
+- robotics
+- articulated-objects
+language:
+- en
+---
 
 # L-CAMP: Language-Conditioned Axis and Motion Prediction for Articulated Object Manipulation
 
@@ -13,18 +21,17 @@ language:
 
 The University of Texas at Austin
 
-## Download Model
+Code: [UTNuclearRobotics/l_camp](https://github.com/UTNuclearRobotics/l_camp)
+
+## About this checkpoint
 
-A pretrained checkpoint is available on HuggingFace:
-[danieladebi/lcamp-model](https://huggingface.co/danieladebi/lcamp-model).
-Download it into `checkpoints/` to skip training and go straight to
-evaluation.
+This repository hosts a pretrained L-CAMP checkpoint, `lcamp_model.pt`, available from the Files tab above. It predicts the screw axis and motion of an articulated object part from an RGB(-D) image conditioned on a language instruction.
 
-You can access our model by downloading the `lcamp_model.pt` checkpoint from the Files tab
+To use it, download `lcamp_model.pt` from the Files tab and place it in a `checkpoints/` directory inside a clone of the [GitHub repo](https://github.com/UTNuclearRobotics/l_camp), then follow the setup and evaluation steps below.
 
 ## Setup
 
-1. Create the conda/micromamba environment from `environment_lcamp.yml`:
+1. Clone the [GitHub repo](https://github.com/UTNuclearRobotics/l_camp) and create the conda/micromamba environment from `environment_lcamp.yml`:
    ```bash
    micromamba create -f environment_lcamp.yml   # or: conda env create -f environment_lcamp.yml
    micromamba activate lcamp
@@ -37,13 +44,9 @@ You can access our model by downloading the `lcamp_model.pt` checkpoint from the
 All commands below (`train.py`, `eval.py`) assume the `lcamp` environment is
 active.
 
-
 ## Training
 
-Training is done with `train.py` via `torchrun` (DDP). The dataset must already
-be built (see `process_lcamp_dataset.py` / `process_lcamp_dataset.slurm`) as a
-directory containing `train_dataset.json`, `test_dataset.json`, and
-`intrinsics.npy`.
+If you'd rather train your own checkpoint instead of using this one, training is done with `train.py` via `torchrun` (DDP). The dataset must already be built (see `process_lcamp_dataset.py` / `process_lcamp_dataset.slurm`) as a directory containing `train_dataset.json`, `test_dataset.json`, and `intrinsics.npy`.
 
 Single-GPU / local run:
 ```bash
@@ -87,9 +90,7 @@ torchrun --nproc_per_node=8 train.py \
     --log_dir "$SCRATCH/train_logs" \
     --cluster_loc "stampede3"
 ```
-See `train.slurm` / `train_h100.slurm` for full Slurm submission scripts (note:
-those scripts currently hold older `--lr`/`--lambda_anchor`/`--lambda_joint`
-values, update them if you want the Slurm jobs to match the above).
+See `train.slurm` / `train_h100.slurm` in the GitHub repo for full Slurm submission scripts (note: those scripts currently hold older `--lr`/`--lambda_anchor`/`--lambda_joint` values, update them if you want the Slurm jobs to match the above).
 
 Notable flags (`train.py --help` for the complete list):
 - `--model_type`: `resnet` (default LCAMP backbone) or `dino`.
@@ -110,10 +111,10 @@ Checkpoints are written to `--save_path` as `checkpoint_best.pt`,
 
 ## Evaluation
 
-Evaluation is done with `eval.py` (single process, no DDP):
+Evaluation is done with `eval.py` (single process, no DDP). To evaluate this checkpoint:
 ```bash
 python eval.py \
-    --model_path checkpoints/my_lcamp_model/checkpoint_best.pt \
+    --model_path checkpoints/lcamp_model.pt \
     --data_dir ./lcamp_dataset_limited_dataset \
     --split test \
     --model_type resnet \
@@ -142,12 +143,13 @@ Results (per-object/per-category success rates, axis/location error, joint
 type accuracy) are written to `results/<model_name>/`, where `<model_name>`
 is derived from `--model_path`.
 
-Once you have a checkpoint you're happy with, drop it into `checkpoints/`
-and point the `model_name` launch argument in `launch/lcamp.launch.py` at it
-(see the launch file for details on `use_bbox_loc` and other runtime flags).
+Once you're happy with a checkpoint (this one or your own), point the
+`model_name` launch argument in `launch/lcamp.launch.py` at it (see the
+launch file for details on `use_bbox_loc` and other runtime flags).
 
 ## Deploying on a Robot
 
 Running predictions on a real Boston Dynamics Spot (via the ROS2 service node
-in `scripts/lcamp_service_node.py`) is outside the scope of this README, see
-[ros2_setup/ROS2_SETUP.md](ros2_setup/ROS2_SETUP.md) for that setup.
+in `scripts/lcamp_service_node.py`) is outside the scope of this model card,
+see [ros2_setup/ROS2_SETUP.md](https://github.com/UTNuclearRobotics/l_camp/blob/main/ros2_setup/ROS2_SETUP.md) in the GitHub repo for that setup.
+