Skip to content

download data... and fix training SNR #123

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
oliverchampion merged 1 commit into from
Oct 17, 2025
Merged

download data... and fix training SNR #123

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
4 changes: 2 additions & 2 deletions .github/workflows/website.yml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -40,7 +40,7 @@ jobs:
# Download Figures artifact
- name: Download Figures artifact

if: ${{ github.event.workflow_run.conclusion == 'success' }}
#if: ${{ github.event.workflow_run.conclusion == 'success' }}
uses: actions/download-artifact@v4
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
Expand All @@ -50,7 +50,7 @@ jobs:

# Download Data artifact
- name: Download Data artifact
if: ${{ github.event.workflow_run.conclusion == 'success' }}
#if: ${{ github.event.workflow_run.conclusion == 'success' }}
uses: actions/download-artifact@v4
with:
github-token: ${{ secrets.GITHUB_TOKEN }}
Expand Down
10 changes: 4 additions & 6 deletions utilities/data_simulation/GenerateData.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -185,29 +185,27 @@ def simulate_training_data(self, bvalues, SNR = (5,100), n = 1000000, Drange = (
- Noise is applied after generating noise-free IVIM signals, using either Gaussian or Rician noise.
- Simulated signals are normalized by the mean S0 (b = 0) signal.
"""
test = self._rng.uniform(0, 1, (n, 3))
test = self._rng.uniform(0, 1, (n, 4))
D = Drange[0] + test[:, [0]] * (Drange[1] - Drange[0])
f = frange[0] + test[:, [1]] * (frange[1] - frange[0])
Dp = Dprange[0] + test[:, [2]] * (Dprange[1] - Dprange[0])
#data_sim = np.zeros([len(D), len(bvalues)])
bvalues = np.array(bvalues)
if type(SNR) == tuple:
test = self._rng.uniform(0, 1, (n, 1))
SNR = np.exp(np.log(SNR[1]) + (test * (np.log(SNR[0]) - np.log(SNR[1]))))
noise_std = 1/SNR[1] + test[:,4] * (1/SNR[0] - 1/SNR[1])
addnoise = True
elif SNR == 0:
addnoise = False
SNR = np.ones((n, 1))
noise_std = np.ones((n, 1))
else:
SNR = np.full((n, 1), SNR)
noise_std = np.full((n, 1), 1/SNR)
addnoise = True
# loop over array to fill with simulated IVIM data
bvalues = np.array(bvalues).reshape(1, -1)
data_sim = 1 * (f * np.exp(-bvalues * Dp) + (1 - f) * np.exp(-bvalues * D))

# if SNR is set to zero, don't add noise
if addnoise:
noise_std = 1 / SNR # shape (n, 1)
noise_real = self._rng.normal(0, noise_std, data_sim.shape)
noise_imag = self._rng.normal(0, noise_std, data_sim.shape)

Expand Down
Loading