cfalas/dissertation
1
0
Fork 0
Code Issues 5 Pull Requests Actions Packages Projects 2 Releases Wiki Activity

Improve logging

Browse Source
This commit is contained in:
Christos Falas 2025-01-30 11:27:07 +00:00
parent 15557bc671
commit 7ffad6ffac
No known key found for this signature in database
2 changed files with 20 additions and 15 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
where_fi/cli/__init__.py
View File

@ -50,8 +50,8 @@ def heatmap() -> None:
def callback(antenna_data: npt.NDArray[np.complex64]) -> None: def callback(antenna_data: npt.NDArray[np.complex64]) -> None:
logger.info(f"Got final CSI data with shape {antenna_data.shape}") logger.info(f"Got final CSI data with shape {antenna_data.shape}")
processed = preprocessor.preprocess(antenna_data) processed = preprocessor.preprocess(antenna_data)
logger.info(f"Processed CSI data with shape {processed.shape}")
processed_tensor = torch.tensor(processed, device=device) processed_tensor = torch.tensor(processed, device=device)
# visualise.add_data(all_data, processed)
aoa.update(processed_tensor) aoa.update(processed_tensor)
if not webapp_queue.full(): if not webapp_queue.full():

33
where_fi/processing/aoa.py
View File

@ -52,6 +52,7 @@ class AoA:
def update(self, data: torch.Tensor) -> None: def update(self, data: torch.Tensor) -> None:
self.timestamp = datetime.now() self.timestamp = datetime.now()
H_sm = self.smooth(data) H_sm = self.smooth(data)
logger.debug(f"Calculated smoothed CSI matrix: {H_sm.shape}")
auto_corr = H_sm @ torch.conj(H_sm).T auto_corr = H_sm @ torch.conj(H_sm).T
# This matrix is by definition Hermitian. # This matrix is by definition Hermitian.
@ -68,6 +69,8 @@ class AoA:
if self.historical_autocorr.shape[0] > WINDOW_SIZE: if self.historical_autocorr.shape[0] > WINDOW_SIZE:
self.historical_autocorr = self.historical_autocorr[-WINDOW_SIZE:] self.historical_autocorr = self.historical_autocorr[-WINDOW_SIZE:]
logger.debug("Finished updating autocorrelation matrix")
def steering_vector(self, theta: torch.Tensor, tof: torch.Tensor) -> torch.Tensor: def steering_vector(self, theta: torch.Tensor, tof: torch.Tensor) -> torch.Tensor:
assert theta.shape == tof.shape assert theta.shape == tof.shape
assert len(theta.shape) == 1 assert len(theta.shape) == 1
@ -83,7 +86,6 @@ class AoA:
/ 299_792_458 / 299_792_458
) )
assert omega_t.shape == phi_theta.shape == (N,) assert omega_t.shape == phi_theta.shape == (N,)
print(omega_t, phi_theta)
omega_t = torch.unsqueeze(omega_t, dim=-1) omega_t = torch.unsqueeze(omega_t, dim=-1)
phi_theta = torch.unsqueeze(phi_theta, dim=-1) phi_theta = torch.unsqueeze(phi_theta, dim=-1)
@ -114,20 +116,22 @@ class AoA:
# The smallest eigenvectors span the noise subspace, # The smallest eigenvectors span the noise subspace,
# and the largest span the signal subspace. # and the largest span the signal subspace.
logger.debug(f"Calculating eigenvectors of R: {R.shape}")
eigvals, eigvecs = torch.linalg.eig(R) eigvals, eigvecs = torch.linalg.eig(R)
assert isinstance(eigvals, torch.Tensor) assert isinstance(eigvals, torch.Tensor)
assert isinstance(eigvecs, torch.Tensor) assert isinstance(eigvecs, torch.Tensor)
logger.info(f"Eigenvalues: {eigvals}") logger.info(f"Eigenvalues: {eigvals}")
E_n = eigvecs[:, torch.abs(eigvals) < config.music.eigval_threshold] E_n = eigvecs[:, torch.abs(eigvals) < config.music.eigval_threshold]
logger.info(f"Signal subspace: {E_n.shape}") logger.debug(f"Signal subspace: {E_n.shape}")
steering = torch.unsqueeze(self.steering_vector(theta, tof), dim=-1) steering = torch.unsqueeze(self.steering_vector(theta, tof), dim=-1)
steering_h = torch.conj(steering).permute(0, 2, 1) steering_h = torch.conj(steering).permute(0, 2, 1)
E_n = E_n.unsqueeze(0) E_n = E_n.unsqueeze(0)
E_n_H = torch.conj(E_n).permute(0, 2, 1) E_n_H = torch.conj(E_n).permute(0, 2, 1)
logger.info( logger.debug(
f"Heatmap multiplication: {steering_h.shape}, {E_n.shape}, {E_n_H.shape}, {steering.shape}" f"Heatmap multiplication: {steering_h.shape}, {E_n.shape}, "
f"{E_n_H.shape}, {steering.shape}"
) )
c: torch.Tensor = 1 / (0.001 + (steering_h @ E_n @ E_n_H @ steering)) c: torch.Tensor = 1 / (0.001 + (steering_h @ E_n @ E_n_H @ steering))
return torch.abs(c.real) return torch.abs(c.real)
@ -143,17 +147,18 @@ class AoA:
dtype=np.float32, dtype=np.float32,
) )
thetas_mesh, tofs_mesh = np.meshgrid(thetas, tofs) thetas_mesh, tofs_mesh = np.meshgrid(thetas, tofs)
heatmap: npt.NDArray[np.float32] = ( logger.debug(
self.evaluate( f"Calculating heatmap with {thetas_mesh.shape} and {tofs_mesh.shape}"
torch.tensor(thetas_mesh.reshape(-1)),
torch.tensor(tofs_mesh.reshape(-1)),
)
.reshape(
config.music.heatmap.theta_resolution,
config.music.heatmap.tof_resolution,
)
.numpy(force=True)
) )
evaluated = self.evaluate(
torch.tensor(thetas_mesh.reshape(-1)),
torch.tensor(tofs_mesh.reshape(-1)),
)
logger.debug(f"Evaluated heatmap: {evaluated.shape}")
heatmap: npt.NDArray[np.float32] = evaluated.reshape(
config.music.heatmap.theta_resolution,
config.music.heatmap.tof_resolution,
).numpy(force=True)
return heatmap return heatmap