9c3d741a08
Move 17 library crates into crates/, CLI binary into bin/fxt, consolidate 10 test crates into testing/, split config crate from deployment config files. Root directory reduced from 38+ to ~17 directories. All Cargo.toml paths and build.rs proto refs updated. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
53 lines
1.8 KiB
Rust
53 lines
1.8 KiB
Rust
// Quick verification that DbnSequenceLoader produces 256-dimensional features
|
|
|
|
use ml::data_loaders::DbnSequenceLoader;
|
|
|
|
#[tokio::main]
|
|
async fn main() -> anyhow::Result<()> {
|
|
println!("🔍 Verifying DbnSequenceLoader feature dimensions...\n");
|
|
|
|
// Create loader with 256 feature dimensions
|
|
let mut loader = DbnSequenceLoader::new(60, 256).await?;
|
|
println!("✅ Loader created: seq_len=60, d_model=256\n");
|
|
|
|
// Load sequences from test data
|
|
let data_dir = "test_data/real/databento/ml_training_small";
|
|
println!("📂 Loading sequences from: {}", data_dir);
|
|
|
|
let (train_data, val_data) = loader.load_sequences(data_dir, 0.9).await?;
|
|
|
|
println!("\n📊 Results:");
|
|
println!(" Training sequences: {}", train_data.len());
|
|
println!(" Validation sequences: {}", val_data.len());
|
|
|
|
// Check first sequence dimensions
|
|
if let Some((input, target)) = train_data.first() {
|
|
let input_shape = input.shape();
|
|
let target_shape = target.shape();
|
|
|
|
println!("\n🔢 Tensor Shapes:");
|
|
println!(
|
|
" Input: {:?} (expected: [1, 60, 256])",
|
|
input_shape.dims()
|
|
);
|
|
println!(
|
|
" Target: {:?} (expected: [1, 1, 256])",
|
|
target_shape.dims()
|
|
);
|
|
|
|
// Verify dimensions
|
|
assert_eq!(input_shape.dims(), &[1, 60, 256], "Input shape mismatch!");
|
|
assert_eq!(target_shape.dims(), &[1, 1, 256], "Target shape mismatch!");
|
|
|
|
println!("\n✅ SUCCESS: All feature dimensions are correct!");
|
|
println!(" - Extract features produces exactly 256 dimensions");
|
|
println!(" - No zero-padding needed");
|
|
println!(" - Ready for MAMBA-2 training");
|
|
} else {
|
|
println!("\n❌ ERROR: No training sequences found!");
|
|
return Err(anyhow::anyhow!("No training data"));
|
|
}
|
|
|
|
Ok(())
|
|
}
|