feat: add vision transfer backbones and IMF variants
This commit is contained in:
73
experiment_suites/2026-04-05-lewm-vit-transfer/manifest.json
Normal file
73
experiment_suites/2026-04-05-lewm-vit-transfer/manifest.json
Normal file
@@ -0,0 +1,73 @@
|
||||
{
|
||||
"date": "2026-04-06",
|
||||
"branch": "feat-imf-attnres-policy",
|
||||
"worktree": "/home/droid/project/roboimi/.worktrees/feat-imf-attnres-policy",
|
||||
"model": "LEWM ViT frozen visual encoder + IMF AttnRes diffusion head",
|
||||
"checkpoint_path": "/home/droid/le-wm/lewm-sim-transfer/pa1w85md8jop6bvol8oxp/checkpoints/epoch=99-step=47800.ckpt",
|
||||
"visual_contract": {
|
||||
"input_camera_names": ["r_vis", "top", "front"],
|
||||
"fused_camera_names": ["front", "top", "r_vis"],
|
||||
"joint_output_dim": 192,
|
||||
"freeze_backbone": true,
|
||||
"dataset_image_resize_shape": null,
|
||||
"eval_image_resize_shape": [256, 256],
|
||||
"fused_short_side_resize": 224
|
||||
},
|
||||
"training_contract": {
|
||||
"pred_horizon": 16,
|
||||
"num_action_steps": 8,
|
||||
"max_steps": 50000,
|
||||
"rollout_val_freq_epochs": 5,
|
||||
"rollout_num_episodes": 10,
|
||||
"batch_size": 80,
|
||||
"lr": 0.00025,
|
||||
"num_workers": 12,
|
||||
"scheduler_type": "cosine",
|
||||
"warmup_steps": 2000,
|
||||
"min_lr": 1e-06,
|
||||
"weight_decay": 1e-05,
|
||||
"grad_clip": 1.0
|
||||
},
|
||||
"verification": {
|
||||
"local_tests": "38 passed",
|
||||
"remote_dataset_shape": [2, 3, 256, 256],
|
||||
"remote_eval_prepared_shape": [3, 256, 256],
|
||||
"remote_smoke_run": {
|
||||
"run_name": "smoke-lewm-imf-rawpath-emb384-20260406-002002",
|
||||
"result": "passed",
|
||||
"details": "2-step train + checkpoint-triggered 1-episode headless rollout succeeded with corrected raw256 path"
|
||||
}
|
||||
},
|
||||
"superseded_runs": [
|
||||
{
|
||||
"run_name": "lewm-vit-imf-sim-transfer-emb384-l12-ph16-ex08-step50k-roll10-5880g0-20260405-201914",
|
||||
"reason": "stopped due to incorrect early per-camera 224 resize"
|
||||
},
|
||||
{
|
||||
"run_name": "lewm-vit-imf-sim-transfer-emb256-l12-ph16-ex08-step50k-roll10-5880g1-20260405-201914",
|
||||
"reason": "stopped due to incorrect early per-camera 224 resize"
|
||||
}
|
||||
],
|
||||
"full_runs": [
|
||||
{
|
||||
"host": "100.73.14.65",
|
||||
"gpu": 0,
|
||||
"run_name": "lewm-vit-imf-raw256fix-sim-transfer-emb384-l12-ph16-ex08-step50k-roll10-5880g0-20260406-002124",
|
||||
"pid": 1058589,
|
||||
"log_path": "/home/droid/roboimi_suite_20260404/experiment_suite_launch_logs/lewm-vit-imf-raw256fix-sim-transfer-emb384-l12-ph16-ex08-step50k-roll10-5880g0-20260406-002124.launch.log",
|
||||
"swanlab_url": "https://swanlab.cn/@game-loader/roboimi-vla/runs/y5tzgqe0u966w9ak41i31",
|
||||
"head_n_emb": 384,
|
||||
"head_n_layer": 12
|
||||
},
|
||||
{
|
||||
"host": "100.73.14.65",
|
||||
"gpu": 1,
|
||||
"run_name": "lewm-vit-imf-raw256fix-sim-transfer-emb256-l12-ph16-ex08-step50k-roll10-5880g1-20260406-002124",
|
||||
"pid": 1058590,
|
||||
"log_path": "/home/droid/roboimi_suite_20260404/experiment_suite_launch_logs/lewm-vit-imf-raw256fix-sim-transfer-emb256-l12-ph16-ex08-step50k-roll10-5880g1-20260406-002124.launch.log",
|
||||
"swanlab_url": "https://swanlab.cn/@game-loader/roboimi-vla/runs/2esr9y7t2dgesstgrn5i6",
|
||||
"head_n_emb": 256,
|
||||
"head_n_layer": 12
|
||||
}
|
||||
]
|
||||
}
|
||||
25
experiment_suites/2026-04-05-lewm-vit-transfer/notes.md
Normal file
25
experiment_suites/2026-04-05-lewm-vit-transfer/notes.md
Normal file
@@ -0,0 +1,25 @@
|
||||
# 2026-04-06 LEWM ViT Transfer Notes
|
||||
|
||||
## Root-cause fix
|
||||
|
||||
The first LEWM runs were stopped because the data path still resized each camera view to `224x224` **before** multiview fusion. That preserved the final tensor shape but broke the original LEWM geometry.
|
||||
|
||||
Corrected path now is:
|
||||
|
||||
- **Training dataset**: keep stored per-view `256x256` images (`data.image_resize_shape=null` at launch; dataset instantiate override is `None` for LEWM)
|
||||
- **Eval rollout input**: resize live MuJoCo `480x640` camera images to `256x256` per view
|
||||
- **Backbone**: fuse `front, top, r_vis` on the LEWM axis, then resize fused short side to `224`
|
||||
|
||||
## Verification
|
||||
|
||||
- Local tests passed (`38 passed` across the focused suite)
|
||||
- Remote check:
|
||||
- dataset sample image shape: `(2, 3, 256, 256)`
|
||||
- eval-prepared live frame shape: `(3, 256, 256)`
|
||||
- Remote smoke passed with real checkpoint:
|
||||
- `smoke-lewm-imf-rawpath-emb384-20260406-002002`
|
||||
|
||||
## Current runs
|
||||
|
||||
- `lewm-vit-imf-raw256fix-sim-transfer-emb384-l12-ph16-ex08-step50k-roll10-5880g0-20260406-002124`
|
||||
- `lewm-vit-imf-raw256fix-sim-transfer-emb256-l12-ph16-ex08-step50k-roll10-5880g1-20260406-002124`
|
||||
19
experiment_suites/2026-04-05-lewm-vit-transfer/status.json
Normal file
19
experiment_suites/2026-04-05-lewm-vit-transfer/status.json
Normal file
@@ -0,0 +1,19 @@
|
||||
{
|
||||
"status": "running",
|
||||
"updated_at": "2026-04-06T00:22:10+08:00",
|
||||
"remote_host": "100.73.14.65",
|
||||
"runs": [
|
||||
{
|
||||
"run_name": "lewm-vit-imf-raw256fix-sim-transfer-emb384-l12-ph16-ex08-step50k-roll10-5880g0-20260406-002124",
|
||||
"pid": 1058589,
|
||||
"gpu": 0,
|
||||
"state": "running"
|
||||
},
|
||||
{
|
||||
"run_name": "lewm-vit-imf-raw256fix-sim-transfer-emb256-l12-ph16-ex08-step50k-roll10-5880g1-20260406-002124",
|
||||
"pid": 1058590,
|
||||
"gpu": 1,
|
||||
"state": "running"
|
||||
}
|
||||
]
|
||||
}
|
||||
Reference in New Issue
Block a user