swap-animal: README + config; drop the block config

README.md

@@ -4,28 +4,35 @@ tags: [diffusion-policy, robotics, franka]
 ---
 # oopsie-debug
 
-Diffusion Policy (image, UNet) checkpoints trained on the Franka teleop block dataset
-`teleop_dataset_20260920_205906` (20 episodes, 1206 steps @ 10 Hz, all demos used for training,
-no held-out validation). Trained 2001 epochs (~34k steps, batch 64); loss values in the table are
-in-sample train loss.
+Diffusion Policy (image, UNet) checkpoints trained with `train.py` of
+https://github.com/KuanchengWang/oopsie (branch `dp-teleop-block`) on Franka teleop data.
 
-| file | epoch | train loss |
+## swap-animal/
+
+Dataset `teleop_dataset_20260922_211038` (40 episodes, 15840 steps @ 10 Hz, all demos in
+training, no held-out validation). 3000-epoch run started 2026-09-23 (batch 64, ~244
+steps/epoch); the run keeps only `latest.ckpt`, so snapshots are taken when it passes the
+listed epochs. Loss values are in-sample train loss.
+
+| file | epoch | mean train loss |
 |---|---|---|
-| epoch_0500.ckpt | 500 | 0.0072 |
-| epoch_1000.ckpt | 1000 | 0.0031 |
-| epoch_1500.ckpt | 1500 | 0.0011 |
-| epoch_2000.ckpt | 2000 | 0.0004 |
+| swap-animal/epoch_1600.ckpt | 1600 | 0.0005 |
+
+(epochs 500 / 1000 / 1500 were overwritten before a copy could be taken; epochs 2000 / 2500 /
+3000 will be added as the run passes them.) `swap-animal/config.yaml` is the resolved training
+config. The checkpoint's `task.dataset.quat_order` is `wxyz` (the corrected quaternion
+handling; see the repo README).
 
 Each `.ckpt` is a full training checkpoint (`state_dicts`: model, ema_model, optimizer;
 `pickles`: epoch, global_step, rng_state; `cfg`), loadable with
 `torch.load(path, pickle_module=dill, map_location='cpu', weights_only=False)`.
-Use `state_dicts['ema_model']` for inference.
+Use `state_dicts['ema_model']` for inference, or roll it out with
+`eval_real_robot_panda_realsense_teleop_block.py -i <ckpt>`.
 
 ## Observation / action contract
-- obs: `img_third`, `img_wrist` (3x120x160 RGB, resized from 480x640 BGR source), `robot_eef_pose`
-  (9-D: xyz + rotation_6d), `gripper_state` (1-D width in m). n_obs_steps = 2.
-- action (10-D): `[x, y, z, rot6d(6), gripper]` = pose/gripper of frame t+1. horizon 16, 8 executed.
-- Normalization: position min/max -> [-1,1]; rotation_6d identity (no min/max);
-  gripper fixed [0, 0.08] m -> [-1,1]. The source quaternion is scalar-last (xyzw).
-- Code: `memory_diffusion_policy/dataset/teleop_block_image_dataset.py`
-  (`action10_to_pose7_gripper` is the inverse for rollout). Full config in `config.yaml`.
+- obs: `img_third`, `img_wrist` (3x120x160 RGB, INTER_AREA from 480x640 BGR), `robot_eef_pose`
+  (9-D: xyz + rotation_6d from the stored (w,x,y,z) quaternion), `gripper_state` (width m); n_obs_steps 2.
+- action (10-D): `[x, y, z, rot6d(6), gripper width]` = pose/gripper of frame t+1; horizon 16, 8 executed.
+- Normalization: position min/max -> [-1,1]; rotation_6d identity; gripper fixed [0, 0.08] m -> [-1,1].
+
+The teleop-block checkpoints previously stored at the repo root were removed on 2026-09-23.

config.yaml → swap-animal/config.yaml

@@ -1,4 +1,4 @@
-name: train_diffusion_unet_teleop_block
+name: train_diffusion_unet_teleop_swap_animal
 _target_: memory_diffusion_policy.workspace.train_diffusion_unet_teleop_block_workspace.TrainDiffusionUnetTeleopBlockWorkspace
 task_name: ${task.name}
 shape_meta: ${task.shape_meta}
@@ -86,7 +86,7 @@ training:
   resume: true
   lr_scheduler: cosine
   lr_warmup_steps: 500
-  num_epochs: 2001
+  num_epochs: 3000
   gradient_accumulate_every: 1
   use_ema: true
   freeze_encoder: false
@@ -112,7 +112,7 @@ checkpoint:
   topk:
     monitor_key: train_loss
     mode: min
-    k: 21
+    k: 0
     format_str: epoch={epoch:04d}-train_loss={train_loss:.4f}.ckpt
   save_last_ckpt: true
   save_last_snapshot: false
@@ -120,16 +120,17 @@ multi_run:
   run_dir: data/outputs/teleop_block_dp/${name}_${task_name}_${exp_name}
   wandb_name_base: ${name}_${task_name}_${exp_name}
 task:
-  name: teleop_block_image
+  name: teleop_swap_animal_image
   image_shape:
   - 3
   - 120
   - 160
-  dataset_path: data/teleop_block_new/teleop_dataset_20260920_205906/replay_buffer.zarr
+  dataset_path: data/teleop_swap_animal/teleop_dataset_20260922_211038/replay_buffer.zarr
   action_shift: 1
   gripper_range:
   - 0.0
   - 0.08
+  quat_order: wxyz
   shape_meta:
     obs:
       img_third:
@@ -186,3 +187,5 @@ task:
     gripper_range: ${task.gripper_range}
     image_cache: true
     image_cache_path: null
+    quat_order: ${task.quat_order}
+    repair_dropouts: true