Skip to content

Masked spectrogram and mask output #35

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
stoutta6 merged 2 commits into from
Feb 5, 2026
Merged

Masked spectrogram and mask output #35

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
6a5a95e
Added new mask and masked output image
bluemellophone Jan 29, 2026
a2ec490
Mask creation now conditional to support fast mode
Feb 4, 2026
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
29 changes: 29 additions & 0 deletions batbot/spectrogram/__init__.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1380,6 +1380,20 @@ def calculate_harmonic_and_echo_flags(
return harmonic_flag, harmonic_peak, echo_flag, echo_peak


def create_masked_image(stft_db, costs, kernel=11):
weights = costs.copy()
weights[weights < weights.mean()] = 0
weights[weights > 0] = weights.max()
weights = weights.astype(np.float32)
weights = cv2.GaussianBlur(
weights, (kernel, kernel), sigmaX=4, sigmaY=4, borderType=cv2.BORDER_DEFAULT
)
weights /= weights.max()
masked = stft_db * weights
masked = normalize_stft(masked, None, np.uint8)
return masked


# @lp
def compute_wrapper(
wav_filepath,
Expand Down Expand Up @@ -1823,6 +1837,8 @@ def compute_wrapper(

output_paths = []
compressed_paths = []
mask_paths = []
masked_paths = []
if not fast_mode:
datas = [
(output_paths, 'jpg', stft_db),
Expand All @@ -1834,6 +1850,14 @@ def compute_wrapper(
(compressed_paths, 'compressed.jpg', segments['stft_db']),
]

# Create masked image
if 'costs' in segments and 'stft_db' in segments:
masked = create_masked_image(segments['stft_db'], segments['costs'])
datas += [
(mask_paths, 'mask.jpg', segments['costs']),
(masked_paths, 'masked.jpg', masked),
]

for accumulator, tag, data in datas:
if data.dtype != np.uint8:
data_ = data.astype(np.float32)
Expand Down Expand Up @@ -1863,6 +1887,8 @@ def compute_wrapper(
'spectrogram': {
'uncompressed.path': output_paths,
'compressed.path': compressed_paths,
'mask.path': mask_paths,
'masked.path': masked_paths,
},
'global_threshold.amp': int(round(255.0 * (global_threshold / max_value))),
'sr.hz': int(sr),
Expand All @@ -1886,6 +1912,9 @@ def compute_wrapper(
'width.px': segments['stft_db'].shape[1],
'height.px': segments['stft_db'].shape[0],
}
if 'costs' in segments and 'stft_db' in segments:
metadata['size']['mask'] = metadata['size']['compressed']
metadata['size']['masked'] = metadata['size']['compressed']

metadata_path = f'{out_file_stem}.metadata.json'
with open(metadata_path, 'w') as metafile:
Expand Down
2 changes: 1 addition & 1 deletion setup.cfg
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,7 +38,7 @@ python_requires = >=3.7

[options.entry_points]
console_scripts =
batbot = batbot.batbot:cli
batbot = batbot.batbot_cli:cli

[tool:pytest]
minversion = 5.4
Expand Down