lars
72bd65ff9f
step_length already encodes |post_pos - pre_pos| by definition, so a raw post_pos target would duplicate that magnitude and could drift inconsistent with step_length during sampling. Instead add travel_dir, a unit vector (local frame) giving only the direction of pre_pos->post_pos; post_pos is reconstructed at inference as pre_pos + step_length * travel_dir, keeping the two self-consistent. Target grows from 6D to 9D. Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
43 lines
1.2 KiB
Python
43 lines
1.2 KiB
Python
import torch
|
|
import pytest
|
|
from giant.model.network import DenoisingMLP, SinusoidalEmbedding
|
|
|
|
|
|
def test_sinusoidal_embedding_shape():
|
|
emb = SinusoidalEmbedding(64)
|
|
t = torch.rand(16)
|
|
assert emb(t).shape == (16, 64)
|
|
|
|
|
|
def test_sinusoidal_embedding_batch_1():
|
|
emb = SinusoidalEmbedding(32)
|
|
t = torch.tensor([0.5])
|
|
assert emb(t).shape == (1, 32)
|
|
|
|
|
|
def test_denoising_mlp_output_shape():
|
|
B = 8
|
|
model = DenoisingMLP(pdg_vocab=5, mat_vocab=3)
|
|
x_t = torch.randn(B, 9)
|
|
t = torch.rand(B)
|
|
cond_cont = torch.randn(B, 9)
|
|
cond_cat = torch.stack([
|
|
torch.randint(0, 5, (B,)),
|
|
torch.randint(0, 3, (B,)),
|
|
], dim=1)
|
|
out = model(x_t, t, cond_cont, cond_cat)
|
|
assert out.shape == (B, 9)
|
|
|
|
|
|
def test_denoising_mlp_gradients_flow():
|
|
B = 4
|
|
model = DenoisingMLP(pdg_vocab=3, mat_vocab=2, hidden_dim=32, n_blocks=2)
|
|
x_t = torch.randn(B, 9)
|
|
t = torch.rand(B)
|
|
cond_cont = torch.randn(B, 9)
|
|
cond_cat = torch.zeros(B, 2, dtype=torch.long)
|
|
loss = model(x_t, t, cond_cont, cond_cat).sum()
|
|
loss.backward()
|
|
for name, p in model.named_parameters():
|
|
assert p.grad is not None, f"no grad for {name}"
|