Add DeMemWM memory causality config
Browse files
.exp_artifact/dememwm_future_memory_selection_plan.md
ADDED
|
@@ -0,0 +1,489 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# DeMemWM Future Memory Selection Plan
|
| 2 |
+
|
| 3 |
+
Repo: `/share_1/users/bonan_ding/WorldMem`
|
| 4 |
+
|
| 5 |
+
Branch: `dememwm`
|
| 6 |
+
|
| 7 |
+
Purpose: allow the DeMemWM dataset-side memory selector to choose future frames
|
| 8 |
+
during training when explicitly configured, while keeping the packed DeMemWM
|
| 9 |
+
temporal-attention memory streams diagonal/self-only.
|
| 10 |
+
|
| 11 |
+
## Required Orchestration Flow
|
| 12 |
+
|
| 13 |
+
Use this plan with a new session prompt such as:
|
| 14 |
+
|
| 15 |
+
```text
|
| 16 |
+
/goal Complete /share_1/users/bonan_ding/WorldMem/.exp_artifact/dememwm_future_memory_selection_plan.md one substep at a time. For every substep, use a fresh implementation subagent, a fresh review subagent, and if needed fresh fix subagents until review is clean. Validate, inspect diff, commit the substep, and update this plan before moving to the next substep.
|
| 17 |
+
```
|
| 18 |
+
|
| 19 |
+
The main session is the orchestra leader. It owns sequencing, diff inspection,
|
| 20 |
+
validation, commits, and plan-status updates. Subagents do bounded implementation,
|
| 21 |
+
review, or fix work only for the current substep.
|
| 22 |
+
|
| 23 |
+
For every substep below:
|
| 24 |
+
|
| 25 |
+
1. Start a fresh implementation subagent.
|
| 26 |
+
2. The implementation subagent must read:
|
| 27 |
+
- `AGENTS.md`
|
| 28 |
+
- `.codex/AGENT.md`
|
| 29 |
+
- `.codex/memory.md`
|
| 30 |
+
- `/share_1/users/bonan_ding/.codex/skills/codex-ml-cv-clean-implementation/SKILL.md`
|
| 31 |
+
3. The implementation subagent must use:
|
| 32 |
+
- `[$codex-ml-cv-clean-implementation](/share_1/users/bonan_ding/.codex/skills/codex-ml-cv-clean-implementation/SKILL.md)`
|
| 33 |
+
4. The implementation subagent must implement only the current substep.
|
| 34 |
+
5. After implementation, the main session inspects the diff before review.
|
| 35 |
+
6. Start a fresh review subagent.
|
| 36 |
+
7. The review subagent must read the same files and use the same skill.
|
| 37 |
+
8. The review subagent must check:
|
| 38 |
+
- correctness
|
| 39 |
+
- bugs or regressions
|
| 40 |
+
- improper or unnecessary changes
|
| 41 |
+
- code cleanliness
|
| 42 |
+
- adherence to this plan
|
| 43 |
+
- adherence to repository conventions
|
| 44 |
+
- targeted test adequacy
|
| 45 |
+
9. If review finds issues, start a fresh fix subagent.
|
| 46 |
+
10. The fix subagent must read the same files, use the same skill, and fix only
|
| 47 |
+
the review findings.
|
| 48 |
+
11. Repeat review/fix/re-review until the review subagent reports no remaining
|
| 49 |
+
issues.
|
| 50 |
+
12. Run the validation commands listed for the substep.
|
| 51 |
+
13. Run `git diff --check`.
|
| 52 |
+
14. Inspect `git diff`.
|
| 53 |
+
15. Commit only the completed substep with a clear commit message.
|
| 54 |
+
16. Mark the substep complete in this plan file and include that plan-status
|
| 55 |
+
update in the same substep commit if possible.
|
| 56 |
+
17. Do not proceed to the next substep until the current one is reviewed clean,
|
| 57 |
+
validated, committed, and marked complete.
|
| 58 |
+
|
| 59 |
+
Global rules:
|
| 60 |
+
|
| 61 |
+
- Do not skip substeps.
|
| 62 |
+
- Do not combine unrelated substeps into one commit.
|
| 63 |
+
- Keep changes surgical.
|
| 64 |
+
- Preserve unrelated user changes.
|
| 65 |
+
- Do not train or submit Slurm jobs.
|
| 66 |
+
- Do not modify `algorithms/worldmem`; use it only as a reference.
|
| 67 |
+
- Do not couple `dataset.memory_selection.causal` to `algorithm.causal`.
|
| 68 |
+
- Do not change DeMemWM local target temporal-attention causality in this plan.
|
| 69 |
+
- Keep anchor selection semantics unchanged: same anchor candidate window and
|
| 70 |
+
same `_select_anchor` scoring/diversity logic.
|
| 71 |
+
- Allow cross-stream duplicate memory frames: `anchor`, `dynamic`, and `revisit`
|
| 72 |
+
may select the same raw frame, including frames in the target/local-context
|
| 73 |
+
window when training is configured non-causal.
|
| 74 |
+
- If validation fails, fix through the same fresh fix-subagent and
|
| 75 |
+
review-subagent loop, then rerun validation.
|
| 76 |
+
|
| 77 |
+
Status legend:
|
| 78 |
+
|
| 79 |
+
- `[ ]` not started
|
| 80 |
+
- `[~]` in progress
|
| 81 |
+
- `[x]` complete and committed
|
| 82 |
+
|
| 83 |
+
## Current Code Facts
|
| 84 |
+
|
| 85 |
+
- DeMemWM training samples are built by
|
| 86 |
+
`datasets/video/minecraft_video_dememwm_latent_dataset.py`, which calls
|
| 87 |
+
`select_memory_indices()` in `datasets/video/memory_selection.py`.
|
| 88 |
+
- `anchor` currently uses a clip-local context prefix through
|
| 89 |
+
`anchor_candidate_start` and `anchor_candidate_stop`. This must stay
|
| 90 |
+
unchanged.
|
| 91 |
+
- `_select_revisit()` currently builds a past-only pool using
|
| 92 |
+
`local_context_exclusion_frames`; this blocks future frames and local-window
|
| 93 |
+
frames.
|
| 94 |
+
- `select_memory_indices()` currently enforces some cross-stream uniqueness:
|
| 95 |
+
recent `dynamic` can be removed from anchor candidates, and `revisit` can be
|
| 96 |
+
told to exclude anchor/dynamic frames.
|
| 97 |
+
- DeMemWM validation/test rollout also calls `_select_revisit()` from
|
| 98 |
+
`algorithms/dememwm/df_video.py`; if duplicate stream semantics are changed
|
| 99 |
+
in the dataset selector, the online path should be checked for the same
|
| 100 |
+
cross-stream exclusion issue.
|
| 101 |
+
- In `algorithms/dememwm/models/attention.py`,
|
| 102 |
+
`_frame_memory_attn_bias()` currently makes `anchor` and `revisit`
|
| 103 |
+
diagonal/self-only, but gives `dynamic` full intra-stream attention.
|
| 104 |
+
- WorldMem memory frames do not need memory-stream self-attention: memory is
|
| 105 |
+
consumed as keys/values by target queries. In DeMemWM, this corresponds to
|
| 106 |
+
`FrameMemoryReferenceAttention`, not temporal mixing among memory frames.
|
| 107 |
+
|
| 108 |
+
## Non-Goals
|
| 109 |
+
|
| 110 |
+
- Do not change the frame-memory segment order:
|
| 111 |
+
|
| 112 |
+
```text
|
| 113 |
+
[target][anchor][dynamic][revisit]
|
| 114 |
+
```
|
| 115 |
+
|
| 116 |
+
- Do not change the DeMemWM reference-attention architecture.
|
| 117 |
+
- Do not change `algorithm.causal` behavior.
|
| 118 |
+
- Do not add a new selector framework or backend.
|
| 119 |
+
- Do not use `local_context_exclusion_frames` to block training memory
|
| 120 |
+
candidates in the new non-causal path.
|
| 121 |
+
- Do not add compatibility aliases such as `casual`; use `causal`.
|
| 122 |
+
- Do not run training or submit cluster jobs.
|
| 123 |
+
|
| 124 |
+
## Substep 1: Add Dataset-Side Memory Causal Config And Candidate Helper
|
| 125 |
+
|
| 126 |
+
Status: `[x]`
|
| 127 |
+
|
| 128 |
+
Goal:
|
| 129 |
+
|
| 130 |
+
Add the explicit dataset-side switch that controls whether training memory
|
| 131 |
+
selection may use future frames.
|
| 132 |
+
|
| 133 |
+
Primary files:
|
| 134 |
+
|
| 135 |
+
- `configurations/dataset/video_minecraft_dememwm_latent.yaml`
|
| 136 |
+
- `datasets/video/memory_selection.py`
|
| 137 |
+
- `tests/test_dememwm_latent_dataset.py`
|
| 138 |
+
|
| 139 |
+
Required behavior:
|
| 140 |
+
|
| 141 |
+
- Add:
|
| 142 |
+
|
| 143 |
+
```yaml
|
| 144 |
+
memory_selection:
|
| 145 |
+
causal: true
|
| 146 |
+
```
|
| 147 |
+
|
| 148 |
+
- The runtime override for future-memory training is:
|
| 149 |
+
|
| 150 |
+
```bash
|
| 151 |
+
dataset.memory_selection.causal=false
|
| 152 |
+
```
|
| 153 |
+
|
| 154 |
+
- Do not set `memory_selection.causal: ${algorithm.causal}`.
|
| 155 |
+
- Add a small helper in `memory_selection.py` for memory candidate frames:
|
| 156 |
+
|
| 157 |
+
```python
|
| 158 |
+
def _memory_candidate_frames(num_frames, target_positions, cfg, split, min_candidate_frame=0):
|
| 159 |
+
target_start = int(target_positions[0])
|
| 160 |
+
causal = split != "training" or bool(cfg_get(cfg, "causal", True))
|
| 161 |
+
stop = target_start if causal else num_frames
|
| 162 |
+
return np.arange(min_candidate_frame, stop, dtype=np.int64)
|
| 163 |
+
```
|
| 164 |
+
|
| 165 |
+
- This helper intentionally does not apply `local_context_exclusion_frames`.
|
| 166 |
+
For training with `causal=false`, the candidate pool may include future
|
| 167 |
+
frames, target frames, and local-window frames, matching the desired
|
| 168 |
+
WorldMem-style training behavior.
|
| 169 |
+
- For validation/test, the helper remains causal regardless of the config value
|
| 170 |
+
because `split != "training"` forces `causal=True`.
|
| 171 |
+
|
| 172 |
+
Implementation constraints:
|
| 173 |
+
|
| 174 |
+
- Keep the helper local to `memory_selection.py`; do not add a new module.
|
| 175 |
+
- Do not yet rewrite all selectors in this substep unless it stays cleaner to
|
| 176 |
+
include one direct use in `_select_revisit()`.
|
| 177 |
+
- Keep tests tiny and deterministic.
|
| 178 |
+
|
| 179 |
+
Validation for this substep:
|
| 180 |
+
|
| 181 |
+
```bash
|
| 182 |
+
python -m py_compile datasets/video/memory_selection.py tests/test_dememwm_latent_dataset.py
|
| 183 |
+
python -B -m unittest tests.test_dememwm_latent_dataset
|
| 184 |
+
git diff --check
|
| 185 |
+
```
|
| 186 |
+
|
| 187 |
+
Review must specifically confirm:
|
| 188 |
+
|
| 189 |
+
- The config key is dataset-side only.
|
| 190 |
+
- `algorithm.causal` remains unrelated.
|
| 191 |
+
- Training with `causal=false` can produce a candidate pool reaching the end of
|
| 192 |
+
the video.
|
| 193 |
+
- Validation/test remain no-future.
|
| 194 |
+
- No local-context exclusion was introduced in the new helper.
|
| 195 |
+
|
| 196 |
+
Suggested commit message:
|
| 197 |
+
|
| 198 |
+
```text
|
| 199 |
+
Add DeMemWM memory causality config
|
| 200 |
+
```
|
| 201 |
+
|
| 202 |
+
## Substep 2: Enable Future And Local-Window Revisit Selection
|
| 203 |
+
|
| 204 |
+
Status: `[ ]`
|
| 205 |
+
|
| 206 |
+
Goal:
|
| 207 |
+
|
| 208 |
+
Use the new candidate helper for `revisit` selection so training can choose
|
| 209 |
+
future frames when `dataset.memory_selection.causal=false`.
|
| 210 |
+
|
| 211 |
+
Primary files:
|
| 212 |
+
|
| 213 |
+
- `datasets/video/memory_selection.py`
|
| 214 |
+
- `algorithms/dememwm/df_video.py`
|
| 215 |
+
- `tests/test_dememwm_latent_dataset.py`
|
| 216 |
+
|
| 217 |
+
Required behavior:
|
| 218 |
+
|
| 219 |
+
- Replace `_select_revisit()` candidate construction with the helper from
|
| 220 |
+
Substep 1.
|
| 221 |
+
- Do not apply `local_context_exclusion_frames` in `_select_revisit()` candidate
|
| 222 |
+
construction for this path.
|
| 223 |
+
- Preserve the existing scoring:
|
| 224 |
+
- training uses pose-similarity selection;
|
| 225 |
+
- validation/test uses point-union/FOV selection.
|
| 226 |
+
- Preserve `_select_revisit()`'s `excluded` argument for any direct diagnostic
|
| 227 |
+
caller, but top-level DeMemWM selection should stop using cross-stream
|
| 228 |
+
exclusions to enforce uniqueness.
|
| 229 |
+
- In `select_memory_indices()`, pass an empty exclusion set to `_select_revisit()`
|
| 230 |
+
so `revisit` may reuse frames selected by `anchor` or `dynamic`.
|
| 231 |
+
- In `algorithms/dememwm/df_video.py`, check the online validation/test call to
|
| 232 |
+
`_select_revisit()`. Remove only the cross-stream exclusion that prevents
|
| 233 |
+
`revisit` from reusing online `anchor`/`dynamic` frames. Do not change online
|
| 234 |
+
causal history limits.
|
| 235 |
+
|
| 236 |
+
Implementation constraints:
|
| 237 |
+
|
| 238 |
+
- Keep anchor candidate window and `_select_anchor()` logic unchanged.
|
| 239 |
+
- Do not change dynamic selection in this substep except where needed to stop
|
| 240 |
+
blocking revisit duplicates.
|
| 241 |
+
- Do not modify WorldMem.
|
| 242 |
+
|
| 243 |
+
Required tests:
|
| 244 |
+
|
| 245 |
+
- Training with default `causal=true` does not select future revisit frames.
|
| 246 |
+
- Training with `causal=false` can select a future pose-matching revisit frame.
|
| 247 |
+
- Training with `causal=false` can select a target/local-window frame when it is
|
| 248 |
+
the best pose match.
|
| 249 |
+
- Validation/test with `causal=false` still does not select future revisit
|
| 250 |
+
frames.
|
| 251 |
+
- Revisit can duplicate an anchor or dynamic frame when scoring selects it.
|
| 252 |
+
|
| 253 |
+
Validation for this substep:
|
| 254 |
+
|
| 255 |
+
```bash
|
| 256 |
+
python -m py_compile datasets/video/memory_selection.py algorithms/dememwm/df_video.py tests/test_dememwm_latent_dataset.py
|
| 257 |
+
python -B -m unittest tests.test_dememwm_latent_dataset
|
| 258 |
+
git diff --check
|
| 259 |
+
```
|
| 260 |
+
|
| 261 |
+
Review must specifically confirm:
|
| 262 |
+
|
| 263 |
+
- Future memory is gated by `dataset.memory_selection.causal=false`.
|
| 264 |
+
- Validation/test are still no-future.
|
| 265 |
+
- Local-window candidates are not filtered out.
|
| 266 |
+
- Revisit duplicates across streams are allowed by the top-level DeMemWM path.
|
| 267 |
+
- Anchor selection itself was not changed.
|
| 268 |
+
|
| 269 |
+
Suggested commit message:
|
| 270 |
+
|
| 271 |
+
```text
|
| 272 |
+
Allow noncausal DeMemWM revisit selection
|
| 273 |
+
```
|
| 274 |
+
|
| 275 |
+
## Substep 3: Enable Future Event-Triggered Dynamic Selection
|
| 276 |
+
|
| 277 |
+
Status: `[ ]`
|
| 278 |
+
|
| 279 |
+
Goal:
|
| 280 |
+
|
| 281 |
+
Make event-triggered `dynamic` memory use the same training causal/non-causal
|
| 282 |
+
candidate pool as `revisit`, while still keeping `recent` dynamic semantics
|
| 283 |
+
unchanged.
|
| 284 |
+
|
| 285 |
+
Primary files:
|
| 286 |
+
|
| 287 |
+
- `datasets/video/memory_selection.py`
|
| 288 |
+
- `tests/test_dememwm_latent_dataset.py`
|
| 289 |
+
|
| 290 |
+
Required behavior:
|
| 291 |
+
|
| 292 |
+
- For `dynamic.selection_policy=event_triggered`, filter `dynamic_stream` using
|
| 293 |
+
`_memory_candidate_frames()`.
|
| 294 |
+
- For training with `causal=false`, eligible dynamic stream frames may include
|
| 295 |
+
future, target, and local-window frames.
|
| 296 |
+
- For validation/test, eligible dynamic stream frames remain no-future.
|
| 297 |
+
- Do not pass `anchor` or `revisit` as exclusions when selecting dynamic memory;
|
| 298 |
+
dynamic may reuse frames from either stream.
|
| 299 |
+
- Use `revisit` as reference frames when available; otherwise use
|
| 300 |
+
`target_positions` so non-causal selection stays query-local instead of
|
| 301 |
+
drifting to unrelated late-video events.
|
| 302 |
+
- Leave `dynamic.selection_policy=recent` past-only. "Recent" means immediate
|
| 303 |
+
history; future-frame memory should come from `revisit` and event-triggered
|
| 304 |
+
`dynamic`.
|
| 305 |
+
|
| 306 |
+
Implementation constraints:
|
| 307 |
+
|
| 308 |
+
- Do not change `_build_dynamic_stream()` event scoring.
|
| 309 |
+
- Do not change anchor selection.
|
| 310 |
+
- Do not add a new dynamic policy.
|
| 311 |
+
|
| 312 |
+
Required tests:
|
| 313 |
+
|
| 314 |
+
- Event-triggered dynamic with `causal=true` stays before the target.
|
| 315 |
+
- Event-triggered dynamic with `causal=false` can select future stream frames.
|
| 316 |
+
- Event-triggered dynamic can duplicate a revisit or anchor frame.
|
| 317 |
+
- Recent dynamic behavior remains unchanged by this substep.
|
| 318 |
+
|
| 319 |
+
Validation for this substep:
|
| 320 |
+
|
| 321 |
+
```bash
|
| 322 |
+
python -m py_compile datasets/video/memory_selection.py tests/test_dememwm_latent_dataset.py
|
| 323 |
+
python -B -m unittest tests.test_dememwm_latent_dataset
|
| 324 |
+
git diff --check
|
| 325 |
+
```
|
| 326 |
+
|
| 327 |
+
Review must specifically confirm:
|
| 328 |
+
|
| 329 |
+
- The change applies only to event-triggered dynamic selection.
|
| 330 |
+
- Recent dynamic remains past-only.
|
| 331 |
+
- Cross-stream duplicate frames are allowed.
|
| 332 |
+
- No local-context exclusion was reintroduced.
|
| 333 |
+
|
| 334 |
+
Suggested commit message:
|
| 335 |
+
|
| 336 |
+
```text
|
| 337 |
+
Allow noncausal DeMemWM dynamic events
|
| 338 |
+
```
|
| 339 |
+
|
| 340 |
+
## Substep 4: Make All Packed Memory Streams Diagonal/Self-Only
|
| 341 |
+
|
| 342 |
+
Status: `[ ]`
|
| 343 |
+
|
| 344 |
+
Goal:
|
| 345 |
+
|
| 346 |
+
Make `anchor`, `dynamic`, and `revisit` all use diagonal/self-only temporal
|
| 347 |
+
attention rows in the packed DeMemWM `TemporalAxialAttention` path.
|
| 348 |
+
|
| 349 |
+
Primary files:
|
| 350 |
+
|
| 351 |
+
- `algorithms/dememwm/models/attention.py`
|
| 352 |
+
- `tests/test_dememwm_temporal_attention.py`
|
| 353 |
+
|
| 354 |
+
Required behavior:
|
| 355 |
+
|
| 356 |
+
- In `_frame_memory_attn_bias()`, remove the special full intra-stream attention
|
| 357 |
+
for `dynamic`.
|
| 358 |
+
- Each memory stream should only allow each memory frame to attend itself in the
|
| 359 |
+
temporal self-attention block:
|
| 360 |
+
|
| 361 |
+
```python
|
| 362 |
+
idx = torch.arange(cursor, cursor + length, device=device)
|
| 363 |
+
allow[:, idx, idx] = True
|
| 364 |
+
```
|
| 365 |
+
|
| 366 |
+
- Keep target-target causal lower-triangular attention unchanged.
|
| 367 |
+
- Keep mask handling unchanged.
|
| 368 |
+
- Keep the final diagonal restore for padded/all-invalid rows unchanged.
|
| 369 |
+
- Do not change `FrameMemoryReferenceAttention`; target frames should still
|
| 370 |
+
consume stream memory as keys/values there.
|
| 371 |
+
|
| 372 |
+
Implementation constraints:
|
| 373 |
+
|
| 374 |
+
- This is an attention-mask cleanup only.
|
| 375 |
+
- Do not change model dimensions, segment order, or reference-attention logic.
|
| 376 |
+
- Do not modify WorldMem.
|
| 377 |
+
|
| 378 |
+
Required tests:
|
| 379 |
+
|
| 380 |
+
- Packed target segment remains causal.
|
| 381 |
+
- Anchor stream is diagonal/self-only.
|
| 382 |
+
- Dynamic stream is diagonal/self-only.
|
| 383 |
+
- Revisit stream is diagonal/self-only.
|
| 384 |
+
- Padded invalid memory rows remain finite through the diagonal restore.
|
| 385 |
+
|
| 386 |
+
Validation for this substep:
|
| 387 |
+
|
| 388 |
+
```bash
|
| 389 |
+
python -m py_compile algorithms/dememwm/models/attention.py tests/test_dememwm_temporal_attention.py
|
| 390 |
+
python -B -m unittest tests.test_dememwm_temporal_attention
|
| 391 |
+
git diff --check
|
| 392 |
+
```
|
| 393 |
+
|
| 394 |
+
Review must specifically confirm:
|
| 395 |
+
|
| 396 |
+
- `dynamic` no longer has full intra-stream temporal self-attention.
|
| 397 |
+
- Target local temporal causal masking was not changed.
|
| 398 |
+
- Memory consumption through reference attention remains untouched.
|
| 399 |
+
|
| 400 |
+
Suggested commit message:
|
| 401 |
+
|
| 402 |
+
```text
|
| 403 |
+
Make DeMemWM memory streams self-only
|
| 404 |
+
```
|
| 405 |
+
|
| 406 |
+
## Substep 5: Final Integration Validation
|
| 407 |
+
|
| 408 |
+
Status: `[ ]`
|
| 409 |
+
|
| 410 |
+
Goal:
|
| 411 |
+
|
| 412 |
+
Run the complete cheap validation set for this plan after all code substeps are
|
| 413 |
+
committed.
|
| 414 |
+
|
| 415 |
+
Primary files:
|
| 416 |
+
|
| 417 |
+
- No code changes expected unless validation or review finds a bug.
|
| 418 |
+
- This plan file should be updated to mark the final substep complete.
|
| 419 |
+
|
| 420 |
+
Validation:
|
| 421 |
+
|
| 422 |
+
```bash
|
| 423 |
+
python -m py_compile \
|
| 424 |
+
datasets/video/memory_selection.py \
|
| 425 |
+
algorithms/dememwm/df_video.py \
|
| 426 |
+
algorithms/dememwm/models/attention.py \
|
| 427 |
+
tests/test_dememwm_latent_dataset.py \
|
| 428 |
+
tests/test_dememwm_temporal_attention.py
|
| 429 |
+
|
| 430 |
+
python -B -m unittest \
|
| 431 |
+
tests.test_dememwm_latent_dataset \
|
| 432 |
+
tests.test_dememwm_temporal_attention
|
| 433 |
+
|
| 434 |
+
git diff --check
|
| 435 |
+
git status --short
|
| 436 |
+
```
|
| 437 |
+
|
| 438 |
+
Review must specifically confirm:
|
| 439 |
+
|
| 440 |
+
- The worktree contains only expected committed changes plus this plan status
|
| 441 |
+
update.
|
| 442 |
+
- There are no unrelated refactors.
|
| 443 |
+
- The final behavior can be enabled with:
|
| 444 |
+
|
| 445 |
+
```bash
|
| 446 |
+
dataset.memory_selection.causal=false
|
| 447 |
+
```
|
| 448 |
+
|
| 449 |
+
- No training or Slurm job was run.
|
| 450 |
+
|
| 451 |
+
Suggested commit message:
|
| 452 |
+
|
| 453 |
+
```text
|
| 454 |
+
Validate DeMemWM future memory selection
|
| 455 |
+
```
|
| 456 |
+
|
| 457 |
+
## New-Session Goal Prompt
|
| 458 |
+
|
| 459 |
+
Use this prompt to start the implementation session:
|
| 460 |
+
|
| 461 |
+
```text
|
| 462 |
+
Use $codex-ml-cv-clean-implementation.
|
| 463 |
+
Repo: /share_1/users/bonan_ding/WorldMem
|
| 464 |
+
Goal: Complete .exp_artifact/dememwm_future_memory_selection_plan.md step by step.
|
| 465 |
+
|
| 466 |
+
Act as the main orchestra leader. For each substep in the plan:
|
| 467 |
+
1. Use a fresh implementation subagent for only that substep.
|
| 468 |
+
2. Inspect the diff yourself.
|
| 469 |
+
3. Use a fresh review subagent to review correctness, bugs, design, cleanliness, and tests.
|
| 470 |
+
4. If review finds any issue, use a fresh fix subagent to fix only those findings.
|
| 471 |
+
5. Repeat review/fix with fresh subagents until review is clean.
|
| 472 |
+
6. Run the substep validation commands and git diff --check.
|
| 473 |
+
7. Inspect git diff.
|
| 474 |
+
8. Commit only that substep with the suggested or similarly clear commit message.
|
| 475 |
+
9. Mark the substep complete in the plan file and include the status update in the same commit if possible.
|
| 476 |
+
10. Move to the next substep only after the current substep is reviewed clean, validated, committed, and marked complete.
|
| 477 |
+
|
| 478 |
+
Hard constraints:
|
| 479 |
+
- Do not train or submit Slurm jobs.
|
| 480 |
+
- Do not modify algorithms/worldmem.
|
| 481 |
+
- Do not couple dataset.memory_selection.causal to algorithm.causal.
|
| 482 |
+
- Keep anchor selection semantics unchanged.
|
| 483 |
+
- Allow anchor, dynamic, and revisit to reuse the same raw frame.
|
| 484 |
+
- Do not filter training memory candidates with local_context_exclusion_frames.
|
| 485 |
+
- Make all packed DeMemWM memory streams diagonal/self-only in TemporalAxialAttention.
|
| 486 |
+
- Preserve unrelated user changes.
|
| 487 |
+
|
| 488 |
+
Final report must include changed files, commits made, validation commands and results, and remaining risks.
|
| 489 |
+
```
|
configurations/dataset/video_minecraft_dememwm_latent.yaml
CHANGED
|
@@ -19,6 +19,7 @@ shuffle_clips: true
|
|
| 19 |
|
| 20 |
memory_selection:
|
| 21 |
enabled: true
|
|
|
|
| 22 |
max_anchor_frames: 2
|
| 23 |
max_dynamic_frames: 4
|
| 24 |
max_revisit_frames: 2
|
|
|
|
| 19 |
|
| 20 |
memory_selection:
|
| 21 |
enabled: true
|
| 22 |
+
causal: true
|
| 23 |
max_anchor_frames: 2
|
| 24 |
max_dynamic_frames: 4
|
| 25 |
max_revisit_frames: 2
|
datasets/video/memory_selection.py
CHANGED
|
@@ -25,6 +25,13 @@ def cfg_get(cfg, key: str, default=None):
|
|
| 25 |
return getattr(cfg, key, default)
|
| 26 |
|
| 27 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 28 |
def _as_pose_array(poses) -> np.ndarray:
|
| 29 |
poses = np.asarray(poses, dtype=np.float32)
|
| 30 |
if poses.ndim != 2 or poses.shape[1] < 5:
|
|
|
|
| 25 |
return getattr(cfg, key, default)
|
| 26 |
|
| 27 |
|
| 28 |
+
def _memory_candidate_frames(num_frames, target_positions, cfg, split, min_candidate_frame=0):
|
| 29 |
+
target_start = int(target_positions[0])
|
| 30 |
+
causal = split != "training" or bool(cfg_get(cfg, "causal", True))
|
| 31 |
+
stop = target_start if causal else num_frames
|
| 32 |
+
return np.arange(min_candidate_frame, stop, dtype=np.int64)
|
| 33 |
+
|
| 34 |
+
|
| 35 |
def _as_pose_array(poses) -> np.ndarray:
|
| 36 |
poses = np.asarray(poses, dtype=np.float32)
|
| 37 |
if poses.ndim != 2 or poses.shape[1] < 5:
|
tests/test_dememwm_latent_dataset.py
CHANGED
|
@@ -9,7 +9,7 @@ import torch
|
|
| 9 |
from torch import nn
|
| 10 |
from omegaconf import OmegaConf
|
| 11 |
|
| 12 |
-
from datasets.video.memory_selection import select_memory_indices
|
| 13 |
from datasets.video.minecraft_video_dememwm_latent_dataset import MinecraftVideoDeMemWMLatentDataset
|
| 14 |
|
| 15 |
|
|
@@ -33,6 +33,7 @@ def _dynamic_cfg(selection_policy="recent", **overrides):
|
|
| 33 |
def _selection_cfg(**overrides):
|
| 34 |
cfg = {
|
| 35 |
"enabled": True,
|
|
|
|
| 36 |
"max_anchor_frames": 2,
|
| 37 |
"max_dynamic_frames": 2,
|
| 38 |
"max_revisit_frames": 2,
|
|
@@ -117,6 +118,36 @@ def _write_vae_feature_clip(root, feature_root, split="training", subdir="scene"
|
|
| 117 |
|
| 118 |
|
| 119 |
class MemorySelectionTests(unittest.TestCase):
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 120 |
def test_revisit_uses_sampled_fov_selection(self):
|
| 121 |
poses = np.array(
|
| 122 |
[
|
|
@@ -433,8 +464,9 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 433 |
_write_vae_feature_clip(root, root / "vae_features", stem="sample", poses=poses)
|
| 434 |
dataset = MinecraftVideoDeMemWMLatentDataset(_dataset_cfg(root), split="training")
|
| 435 |
|
| 436 |
-
with self.assertRaisesRegex(
|
| 437 |
dataset[0]
|
|
|
|
| 438 |
|
| 439 |
def test_dataset_converts_raw_actions_to_original_25d_contract(self):
|
| 440 |
with tempfile.TemporaryDirectory() as tmp:
|
|
@@ -857,6 +889,7 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 857 |
self.metric_updates = []
|
| 858 |
self.logger = type("Logger", (), {"experiment": object()})()
|
| 859 |
self.log_video = True
|
|
|
|
| 860 |
self.save_local = False
|
| 861 |
self.local_save_dir = None
|
| 862 |
|
|
@@ -877,6 +910,12 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 877 |
def _update_metric_accumulators(self, xs_pred, xs_gt):
|
| 878 |
self.metric_updates.append((xs_pred.detach().clone(), xs_gt.detach().clone()))
|
| 879 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 880 |
def log(self, name, value):
|
| 881 |
self.logged.append((name, value))
|
| 882 |
|
|
@@ -980,6 +1019,7 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 980 |
self.logged = []
|
| 981 |
self.logger = None
|
| 982 |
self.log_video = False
|
|
|
|
| 983 |
self.save_local = False
|
| 984 |
self.local_save_dir = None
|
| 985 |
|
|
@@ -995,6 +1035,12 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 995 |
def _update_metric_accumulators(self, xs_pred, xs_gt):
|
| 996 |
pass
|
| 997 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 998 |
def log(self, name, value):
|
| 999 |
self.logged.append((name, value))
|
| 1000 |
|
|
@@ -1025,9 +1071,9 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 1025 |
|
| 1026 |
self.assertEqual(len(harness.diffusion_model.calls), 1)
|
| 1027 |
call = harness.diffusion_model.calls[0]
|
| 1028 |
-
self.assertEqual(call["kwargs"]["frame_idx"][:, 0].tolist(), [13, 14,
|
| 1029 |
-
self.assertEqual(call["kwargs"]["frame_memory_masks"]["dynamic"].tolist(), [[
|
| 1030 |
-
self.assertEqual(call["x"][:, 0, 0, 0, 0].tolist(), [0.0, 0.0,
|
| 1031 |
|
| 1032 |
def test_interactive_generation_fails_until_packed_memory_path_exists(self):
|
| 1033 |
from algorithms.dememwm.df_video import DeMemWMMinecraft
|
|
@@ -1096,7 +1142,7 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 1096 |
|
| 1097 |
self.assertEqual(dataset.context_length, 4)
|
| 1098 |
self.assertEqual(len(dataset), 112 - (100 + 4 + 3) + 1)
|
| 1099 |
-
self.assertEqual(sample["frame_indices"].tolist(), [106, 107, 108,
|
| 1100 |
self.assertTrue(sample["memory_masks"]["anchor"].all().item())
|
| 1101 |
self.assertTrue(sample["memory_masks"]["dynamic"].all().item())
|
| 1102 |
self.assertEqual(tuple(sample["memory_masks"]["revisit"].shape), (0,))
|
|
@@ -1131,7 +1177,7 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 1131 |
stem="sample",
|
| 1132 |
num_frames=num_frames,
|
| 1133 |
actions=np.zeros((num_frames, 25), dtype=np.float32),
|
| 1134 |
-
latents=_event_latents(num_frames, event_frame=
|
| 1135 |
)
|
| 1136 |
dataset = MinecraftVideoDeMemWMLatentDataset(
|
| 1137 |
_dataset_cfg(
|
|
@@ -1148,8 +1194,8 @@ class DeMemWMLatentDatasetTests(unittest.TestCase):
|
|
| 1148 |
)
|
| 1149 |
sample = dataset[0]
|
| 1150 |
|
| 1151 |
-
self.assertEqual(sample["frame_indices"].tolist(), [106, 107, 108,
|
| 1152 |
-
self.assertEqual(sample["memory_masks"]["dynamic"].tolist(), [True,
|
| 1153 |
|
| 1154 |
def test_dataset_returns_target_anchor_dynamic_revisit_contract(self):
|
| 1155 |
with tempfile.TemporaryDirectory() as tmp:
|
|
|
|
| 9 |
from torch import nn
|
| 10 |
from omegaconf import OmegaConf
|
| 11 |
|
| 12 |
+
from datasets.video.memory_selection import _memory_candidate_frames, select_memory_indices
|
| 13 |
from datasets.video.minecraft_video_dememwm_latent_dataset import MinecraftVideoDeMemWMLatentDataset
|
| 14 |
|
| 15 |
|
|
|
|
| 33 |
def _selection_cfg(**overrides):
|
| 34 |
cfg = {
|
| 35 |
"enabled": True,
|
| 36 |
+
"causal": True,
|
| 37 |
"max_anchor_frames": 2,
|
| 38 |
"max_dynamic_frames": 2,
|
| 39 |
"max_revisit_frames": 2,
|
|
|
|
| 118 |
|
| 119 |
|
| 120 |
class MemorySelectionTests(unittest.TestCase):
|
| 121 |
+
def test_memory_candidate_frames_default_training_is_causal_without_local_exclusion(self):
|
| 122 |
+
cfg = _selection_cfg(local_context_exclusion_frames=99)
|
| 123 |
+
|
| 124 |
+
candidates = _memory_candidate_frames(10, np.array([5]), cfg, "training", min_candidate_frame=1)
|
| 125 |
+
|
| 126 |
+
self.assertEqual(candidates.tolist(), [1, 2, 3, 4])
|
| 127 |
+
|
| 128 |
+
def test_memory_candidate_frames_training_can_be_noncausal(self):
|
| 129 |
+
cfg = _selection_cfg(causal=False, local_context_exclusion_frames=99)
|
| 130 |
+
|
| 131 |
+
candidates = _memory_candidate_frames(8, np.array([3]), cfg, "training", min_candidate_frame=1)
|
| 132 |
+
|
| 133 |
+
self.assertEqual(candidates.tolist(), [1, 2, 3, 4, 5, 6, 7])
|
| 134 |
+
|
| 135 |
+
def test_memory_candidate_frames_validation_and_test_stay_causal(self):
|
| 136 |
+
cfg = _selection_cfg(causal=False)
|
| 137 |
+
|
| 138 |
+
for split in ("validation", "test"):
|
| 139 |
+
with self.subTest(split=split):
|
| 140 |
+
candidates = _memory_candidate_frames(8, np.array([3]), cfg, split, min_candidate_frame=1)
|
| 141 |
+
|
| 142 |
+
self.assertEqual(candidates.tolist(), [1, 2])
|
| 143 |
+
|
| 144 |
+
def test_dememwm_latent_config_has_dataset_side_memory_causal_default(self):
|
| 145 |
+
config_path = Path(__file__).resolve().parents[1] / "configurations" / "dataset" / "video_minecraft_dememwm_latent.yaml"
|
| 146 |
+
|
| 147 |
+
cfg = OmegaConf.load(config_path)
|
| 148 |
+
|
| 149 |
+
self.assertIs(cfg.memory_selection.causal, True)
|
| 150 |
+
|
| 151 |
def test_revisit_uses_sampled_fov_selection(self):
|
| 152 |
poses = np.array(
|
| 153 |
[
|
|
|
|
| 464 |
_write_vae_feature_clip(root, root / "vae_features", stem="sample", poses=poses)
|
| 465 |
dataset = MinecraftVideoDeMemWMLatentDataset(_dataset_cfg(root), split="training")
|
| 466 |
|
| 467 |
+
with self.assertRaisesRegex(RuntimeError, "Pose height variation") as captured:
|
| 468 |
dataset[0]
|
| 469 |
+
self.assertIsInstance(captured.exception.__cause__, ValueError)
|
| 470 |
|
| 471 |
def test_dataset_converts_raw_actions_to_original_25d_contract(self):
|
| 472 |
with tempfile.TemporaryDirectory() as tmp:
|
|
|
|
| 889 |
self.metric_updates = []
|
| 890 |
self.logger = type("Logger", (), {"experiment": object()})()
|
| 891 |
self.log_video = True
|
| 892 |
+
self.log_memory_selection_sheet = False
|
| 893 |
self.save_local = False
|
| 894 |
self.local_save_dir = None
|
| 895 |
|
|
|
|
| 910 |
def _update_metric_accumulators(self, xs_pred, xs_gt):
|
| 911 |
self.metric_updates.append((xs_pred.detach().clone(), xs_gt.detach().clone()))
|
| 912 |
|
| 913 |
+
def _update_per_frame_metric_accumulators(self, xs_pred, xs_gt, mask, eval_start):
|
| 914 |
+
pass
|
| 915 |
+
|
| 916 |
+
def _update_revisit_metric_accumulators(self, xs_pred, xs_gt, poses, frame_indices, mask, eval_start, batch_idx, namespace):
|
| 917 |
+
pass
|
| 918 |
+
|
| 919 |
def log(self, name, value):
|
| 920 |
self.logged.append((name, value))
|
| 921 |
|
|
|
|
| 1019 |
self.logged = []
|
| 1020 |
self.logger = None
|
| 1021 |
self.log_video = False
|
| 1022 |
+
self.log_memory_selection_sheet = False
|
| 1023 |
self.save_local = False
|
| 1024 |
self.local_save_dir = None
|
| 1025 |
|
|
|
|
| 1035 |
def _update_metric_accumulators(self, xs_pred, xs_gt):
|
| 1036 |
pass
|
| 1037 |
|
| 1038 |
+
def _update_per_frame_metric_accumulators(self, xs_pred, xs_gt, mask, eval_start):
|
| 1039 |
+
pass
|
| 1040 |
+
|
| 1041 |
+
def _update_revisit_metric_accumulators(self, xs_pred, xs_gt, poses, frame_indices, mask, eval_start, batch_idx, namespace):
|
| 1042 |
+
pass
|
| 1043 |
+
|
| 1044 |
def log(self, name, value):
|
| 1045 |
self.logged.append((name, value))
|
| 1046 |
|
|
|
|
| 1071 |
|
| 1072 |
self.assertEqual(len(harness.diffusion_model.calls), 1)
|
| 1073 |
call = harness.diffusion_model.calls[0]
|
| 1074 |
+
self.assertEqual(call["kwargs"]["frame_idx"][:, 0].tolist(), [13, 14, 10])
|
| 1075 |
+
self.assertEqual(call["kwargs"]["frame_memory_masks"]["dynamic"].tolist(), [[True]])
|
| 1076 |
+
self.assertEqual(call["x"][:, 0, 0, 0, 0].tolist(), [0.0, 0.0, 1.0])
|
| 1077 |
|
| 1078 |
def test_interactive_generation_fails_until_packed_memory_path_exists(self):
|
| 1079 |
from algorithms.dememwm.df_video import DeMemWMMinecraft
|
|
|
|
| 1142 |
|
| 1143 |
self.assertEqual(dataset.context_length, 4)
|
| 1144 |
self.assertEqual(len(dataset), 112 - (100 + 4 + 3) + 1)
|
| 1145 |
+
self.assertEqual(sample["frame_indices"].tolist(), [106, 107, 108, 102, 103, 104, 105])
|
| 1146 |
self.assertTrue(sample["memory_masks"]["anchor"].all().item())
|
| 1147 |
self.assertTrue(sample["memory_masks"]["dynamic"].all().item())
|
| 1148 |
self.assertEqual(tuple(sample["memory_masks"]["revisit"].shape), (0,))
|
|
|
|
| 1177 |
stem="sample",
|
| 1178 |
num_frames=num_frames,
|
| 1179 |
actions=np.zeros((num_frames, 25), dtype=np.float32),
|
| 1180 |
+
latents=_event_latents(num_frames, event_frame=102),
|
| 1181 |
)
|
| 1182 |
dataset = MinecraftVideoDeMemWMLatentDataset(
|
| 1183 |
_dataset_cfg(
|
|
|
|
| 1194 |
)
|
| 1195 |
sample = dataset[0]
|
| 1196 |
|
| 1197 |
+
self.assertEqual(sample["frame_indices"].tolist(), [106, 107, 108, 100, 103])
|
| 1198 |
+
self.assertEqual(sample["memory_masks"]["dynamic"].tolist(), [True, True])
|
| 1199 |
|
| 1200 |
def test_dataset_returns_target_anchor_dynamic_revisit_contract(self):
|
| 1201 |
with tempfile.TemporaryDirectory() as tmp:
|