lars
93b19911f8
CI / Format (ruff format) (push) Successful in 36s
CI / Lint (ruff check) (push) Successful in 38s
CI / Sync project version with tag (push) Has been skipped
CI / Type check (ty) (push) Failing after 45s
CI / Lint (ruff check) (pull_request) Successful in 41s
CI / Tests (push) Has been skipped
CI / Format (ruff format) (pull_request) Successful in 35s
CI / Sync project version with tag (pull_request) Has been skipped
CI / Type check (ty) (pull_request) Failing after 37s
CI / Tests (pull_request) Has been skipped
- giant/sample.py: fix every sampler's call convention against
Stage1Model/Stage2OneShot's actual forward signatures (was still
calling model(x, t, cond_cont, cond_cat) positionally); add
sample_secondaries_ar (free-running AR loop, unsnapped history feature)
and sample_stage1/sample_stage2/resolve_n_sec dispatch helpers that read
each stage's generator_kind/decoder off the model instance itself.
- giant/particles.py: decode_topn_class (argmax + other_policy) and
decode_embedding_nearest (L1-snap + distance) turn a secondary's
"onehot"/"embedding" type prediction into a concrete PDG.
- giant/rollout.py: decode_secondary_identity routes all three
particle_type.target values to real mass/charge; per-stage generator
dispatch (drops the single shared `mode` string, adds ddpm support);
L1DistCollector accumulates the §11.3 embedding-distance diagnostic.
- giant/cli.py: drop the onehot/embedding-target rejection gate (narrowed
to the still-unimplemented conditioning.particle/material.type=onehot
axis); fix the dead model_cfg.get("mode") bug in predict/rollout.
- giant/analysis/: new type_embedding_l1_distance PlotSpec, wired through
the rollout YAML sidecar (no live-model call needed, unlike
router_gating -- the histogram is already pre-aggregated at rollout
time).
- Un-xfail every test that was blocked on this step (test_rollout.py,
test_flow.py, test_wgan.py, test_phase2.py, test_router.py,
test_validate.py); add test_sample.py, test_type_embedding_distance.py.
Known follow-up: giant/validate.py still unpacks the training val-batch
as a stale 6-tuple and doesn't use the new per-stage dispatch, so
marginal validation during training degrades gracefully with a warning
rather than working -- not in this step's scope.
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
74 lines
2.7 KiB
Python
74 lines
2.7 KiB
Python
import numpy as np
|
|
import torch
|
|
|
|
from giant.constants import COND_DIM, K_MAX, SEC_SLOT_DIM, X_DIM
|
|
from giant.model.network import Stage1Model, Stage2OneShot
|
|
from giant.validate import validate_marginals
|
|
|
|
_PARTICLE_CFG = {"type": "physical", "emb_dim": 8, "n_layers": 1}
|
|
_MATERIAL_CFG = {"type": "physical", "emb_dim": 8, "n_layers": 1}
|
|
|
|
|
|
def _tiny_models():
|
|
s1 = Stage1Model(
|
|
pdg_vocab=3,
|
|
mat_vocab=2,
|
|
particle_cfg=_PARTICLE_CFG,
|
|
material_cfg=_MATERIAL_CFG,
|
|
hidden_dim=16,
|
|
n_res_blocks=1,
|
|
n_sec_head_k_max=K_MAX,
|
|
)
|
|
s2 = Stage2OneShot(
|
|
pdg_vocab=3,
|
|
mat_vocab=2,
|
|
particle_cfg=_PARTICLE_CFG,
|
|
material_cfg=_MATERIAL_CFG,
|
|
hidden_dim=16,
|
|
n_res_blocks=1,
|
|
generator="flow",
|
|
time_dim=16,
|
|
)
|
|
return s1.eval(), s2.eval()
|
|
|
|
|
|
def _zero_secondaries_loader(B=4, n_batches=2):
|
|
"""A val_loader whose every batch has n_sec=0 (real side) — matches the
|
|
(cond_cont, cond_cat, target_s1, n_sec, sec_cont, proc_idx) tuple shape
|
|
StreamingStepsDataset yields."""
|
|
batches = []
|
|
for _ in range(n_batches):
|
|
cond_cont = torch.randn(B, COND_DIM)
|
|
cond_cat = torch.zeros(B, 2, dtype=torch.long)
|
|
x1 = torch.randn(B, X_DIM)
|
|
n_sec = torch.zeros(B, dtype=torch.long)
|
|
sec_cont = torch.zeros(B, K_MAX, SEC_SLOT_DIM)
|
|
proc_idx = torch.zeros(B, dtype=torch.long)
|
|
batches.append((cond_cont, cond_cat, x1, n_sec, sec_cont, proc_idx))
|
|
return batches
|
|
|
|
|
|
def test_validate_marginals_all_zero_secondaries_returns_nan_phys_kl(monkeypatch):
|
|
"""If n_sec_pred collapses to 0 across the whole validated set (realistic
|
|
during early/unstable training), phys_kl must degrade to NaN instead of
|
|
crashing on the empty-array .min()/.max() reduction inside
|
|
_histogram_kl -- a regression the old species/bincount code this
|
|
replaced explicitly guarded against."""
|
|
s1, s2 = _tiny_models()
|
|
loader = _zero_secondaries_loader()
|
|
|
|
# Force the Stage-1 n_sec head's prediction to 0 for every sample too, so
|
|
# the generated side's valid-slot mask is also empty (real side is
|
|
# already all n_sec=0 by construction of the fake loader above).
|
|
def _fake_sample_flow(model, cond_cont, cond_cat, **kw):
|
|
B = cond_cont.size(0)
|
|
return torch.randn(B, X_DIM), torch.zeros(B, dtype=torch.long)
|
|
|
|
monkeypatch.setattr("giant.validate.sample_flow", _fake_sample_flow)
|
|
|
|
result = validate_marginals(s1, loader, sec_decoder=s2, n_batches=2)
|
|
|
|
assert np.asarray(result["phys_real"]).shape == (0, 2)
|
|
assert np.asarray(result["phys_generated"]).shape == (0, 2)
|
|
assert np.isnan(np.asarray(result["phys_kl"])).all()
|