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>
73 lines
2.1 KiB
Python
73 lines
2.1 KiB
Python
import torch
|
|
from giant.constants import COND_DIM
|
|
from giant.model.network import Stage1Model
|
|
from giant.model.schedule import CosineSchedule, flow_matching_loss
|
|
from giant.sample import sample_flow, sample_ddim
|
|
|
|
PARTICLE_CFG = {"type": "physical", "emb_dim": 8, "n_layers": 1}
|
|
MATERIAL_CFG = {"type": "physical", "emb_dim": 8, "n_layers": 1}
|
|
|
|
|
|
def _small_model():
|
|
return Stage1Model(
|
|
pdg_vocab=3,
|
|
mat_vocab=2,
|
|
particle_cfg=PARTICLE_CFG,
|
|
material_cfg=MATERIAL_CFG,
|
|
hidden_dim=32,
|
|
n_res_blocks=2,
|
|
n_sec_head_k_max=15,
|
|
)
|
|
|
|
|
|
def _batch(B=8):
|
|
x1 = torch.randn(B, 9)
|
|
cond_cont = torch.randn(B, COND_DIM)
|
|
cond_cat = torch.zeros(B, 2, dtype=torch.long)
|
|
return x1, cond_cont, cond_cat
|
|
|
|
|
|
def test_flow_matching_loss_nonneg():
|
|
x1, cond_cont, cond_cat = _batch()
|
|
loss = flow_matching_loss(_small_model(), x1, cond_cont, cond_cat)
|
|
assert loss.item() >= 0.0
|
|
|
|
|
|
def test_flow_matching_loss_is_scalar():
|
|
x1, cond_cont, cond_cat = _batch()
|
|
loss = flow_matching_loss(_small_model(), x1, cond_cont, cond_cat)
|
|
assert loss.shape == ()
|
|
|
|
|
|
def test_flow_matching_loss_has_grad():
|
|
model = _small_model()
|
|
x1, cond_cont, cond_cat = _batch()
|
|
flow_matching_loss(model, x1, cond_cont, cond_cat).backward()
|
|
assert any(p.grad is not None for p in model.parameters())
|
|
|
|
|
|
def test_sample_flow_shape():
|
|
B = 6
|
|
cond_cont = torch.randn(B, COND_DIM)
|
|
cond_cat = torch.zeros(B, 2, dtype=torch.long)
|
|
sample, n_sec = sample_flow(_small_model(), cond_cont, cond_cat, steps=5)
|
|
assert sample.shape == (B, 9)
|
|
assert n_sec.shape == (B,)
|
|
|
|
|
|
def test_ddpm_loss_nonneg():
|
|
schedule = CosineSchedule(T=50)
|
|
x1, cond_cont, cond_cat = _batch()
|
|
loss = schedule.loss(_small_model(), x1, cond_cont, cond_cat)
|
|
assert loss.item() >= 0.0
|
|
|
|
|
|
def test_sample_ddim_shape():
|
|
B = 4
|
|
schedule = CosineSchedule(T=50)
|
|
cond_cont = torch.randn(B, COND_DIM)
|
|
cond_cat = torch.zeros(B, 2, dtype=torch.long)
|
|
sample, n_sec = sample_ddim(_small_model(), cond_cont, cond_cat, schedule, steps=5)
|
|
assert sample.shape == (B, 9)
|
|
assert n_sec.shape == (B,)
|