mirror of
https://github.com/macaodha/batdetect2.git
synced 2025-06-29 14:41:58 +02:00
Remove test migration
This commit is contained in:
mbsantiago
parent
257e1e01bf
commit
8a463e3942
@ -1,156 +0,0 @@
|
||||
from pathlib import Path
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
from soundevent import data
|
||||
|
||||
from batdetect2 import preprocess
|
||||
from batdetect2.utils import audio_utils
|
||||
|
||||
ROOT_DIR = Path(__file__).parent.parent.parent
|
||||
EXAMPLE_AUDIO = ROOT_DIR / "example_data" / "audio"
|
||||
TEST_AUDIO = ROOT_DIR / "tests" / "data"
|
||||
|
||||
|
||||
TEST_FILES = [
|
||||
EXAMPLE_AUDIO / "20170701_213954-MYOMYS-LR_0_0.5.wav",
|
||||
EXAMPLE_AUDIO / "20180530_213516-EPTSER-LR_0_0.5.wav",
|
||||
EXAMPLE_AUDIO / "20180627_215323-RHIFER-LR_0_0.5.wav",
|
||||
TEST_AUDIO / "20230322_172000_selec2.wav",
|
||||
]
|
||||
|
||||
|
||||
@pytest.mark.parametrize("audio_file", TEST_FILES)
|
||||
@pytest.mark.parametrize("scale", [True, False])
|
||||
def test_audio_loading_hasnt_changed(
|
||||
audio_file,
|
||||
scale,
|
||||
):
|
||||
time_expansion = 1
|
||||
target_sampling_rate = 256_000
|
||||
recording = data.Recording.from_file(
|
||||
audio_file,
|
||||
time_expansion=time_expansion,
|
||||
)
|
||||
clip = data.Clip(
|
||||
recording=recording,
|
||||
start_time=0,
|
||||
end_time=recording.duration,
|
||||
)
|
||||
|
||||
_, audio_original = audio_utils.load_audio(
|
||||
audio_file,
|
||||
time_expansion,
|
||||
target_samp_rate=target_sampling_rate,
|
||||
scale=scale,
|
||||
)
|
||||
audio_new = preprocess.load_clip_audio(
|
||||
clip,
|
||||
config=preprocess.AudioConfig(
|
||||
resample=preprocess.ResampleConfig(
|
||||
samplerate=target_sampling_rate,
|
||||
),
|
||||
center=scale,
|
||||
scale=scale,
|
||||
duration=None,
|
||||
),
|
||||
dtype=np.float32,
|
||||
)
|
||||
|
||||
assert audio_original.shape == audio_new.shape
|
||||
assert audio_original.dtype == audio_new.dtype
|
||||
assert np.isclose(audio_original, audio_new.data).all()
|
||||
|
||||
|
||||
@pytest.mark.parametrize("audio_file", TEST_FILES)
|
||||
@pytest.mark.parametrize("spec_scale", ["log", "pcen", "amplitude"])
|
||||
@pytest.mark.parametrize("denoise_spec_avg", [True, False])
|
||||
@pytest.mark.parametrize("max_scale_spec", [True, False])
|
||||
@pytest.mark.parametrize("fft_win_length", [512 / 256_000, 1024 / 256_000])
|
||||
def test_spectrogram_generation_hasnt_changed(
|
||||
audio_file,
|
||||
spec_scale,
|
||||
denoise_spec_avg,
|
||||
max_scale_spec,
|
||||
fft_win_length,
|
||||
):
|
||||
time_expansion = 1
|
||||
target_sampling_rate = 256_000
|
||||
min_freq = 10_000
|
||||
max_freq = 120_000
|
||||
fft_overlap = 0.75
|
||||
|
||||
if spec_scale == "log":
|
||||
scale = preprocess.LogScaleConfig()
|
||||
elif spec_scale == "pcen":
|
||||
scale = preprocess.PcenConfig()
|
||||
else:
|
||||
scale = preprocess.AmplitudeScaleConfig()
|
||||
|
||||
config = preprocess.SpectrogramConfig(
|
||||
stft=preprocess.STFTConfig(
|
||||
window_overlap=fft_overlap,
|
||||
window_duration=fft_win_length,
|
||||
),
|
||||
frequencies=preprocess.FrequencyConfig(
|
||||
min_freq=min_freq,
|
||||
max_freq=max_freq,
|
||||
),
|
||||
scale=scale,
|
||||
spectral_mean_substraction=denoise_spec_avg,
|
||||
size=None,
|
||||
peak_normalize=max_scale_spec,
|
||||
)
|
||||
|
||||
recording = data.Recording.from_file(
|
||||
audio_file,
|
||||
time_expansion=time_expansion,
|
||||
)
|
||||
|
||||
clip = data.Clip(
|
||||
recording=recording,
|
||||
start_time=0,
|
||||
end_time=recording.duration,
|
||||
)
|
||||
|
||||
audio = preprocess.load_clip_audio(
|
||||
clip,
|
||||
config=preprocess.AudioConfig(
|
||||
resample=preprocess.ResampleConfig(
|
||||
samplerate=target_sampling_rate,
|
||||
)
|
||||
),
|
||||
)
|
||||
|
||||
spec_original, _ = audio_utils.generate_spectrogram(
|
||||
audio.data,
|
||||
sampling_rate=target_sampling_rate,
|
||||
params=dict(
|
||||
fft_win_length=fft_win_length,
|
||||
fft_overlap=fft_overlap,
|
||||
max_freq=max_freq,
|
||||
min_freq=min_freq,
|
||||
spec_scale=spec_scale,
|
||||
denoise_spec_avg=denoise_spec_avg,
|
||||
max_scale_spec=max_scale_spec,
|
||||
),
|
||||
)
|
||||
|
||||
new_spec = preprocess.compute_spectrogram(
|
||||
audio,
|
||||
config=config,
|
||||
dtype=np.float32,
|
||||
)
|
||||
|
||||
assert spec_original.shape == new_spec.shape
|
||||
assert spec_original.dtype == new_spec.dtype
|
||||
|
||||
# Check that the spectrogram content is the same within a tolerance of 1e-5
|
||||
# for each element of the spectrogram at least 99.5% of the time.
|
||||
# NOTE: The pcen function is not the same as the one in the original code
|
||||
# thus the need for a tolerance, but the values are still very similar.
|
||||
# NOTE: The original spectrogram is flipped vertically
|
||||
assert (
|
||||
np.isclose(spec_original, np.flipud(new_spec.data), atol=1e-5).mean()
|
||||
> 0.995
|
||||
)
|
||||
@ -1,85 +0,0 @@
|
||||
import json
|
||||
from pathlib import Path
|
||||
from typing import List
|
||||
|
||||
import numpy as np
|
||||
import pytest
|
||||
|
||||
from batdetect2.compat.params import get_training_preprocessing_config
|
||||
from batdetect2.data import BatDetect2FilesAnnotations, load_annotated_dataset
|
||||
from batdetect2.train.preprocess import generate_train_example
|
||||
|
||||
|
||||
@pytest.fixture
|
||||
def regression_dir(data_dir: Path) -> Path:
|
||||
dir = data_dir / "regression"
|
||||
assert dir.exists()
|
||||
return dir
|
||||
|
||||
|
||||
def test_can_generate_similar_training_inputs(
|
||||
example_audio_dir: Path,
|
||||
example_audio_files: List[Path],
|
||||
example_anns_dir: Path,
|
||||
regression_dir: Path,
|
||||
):
|
||||
old_parameters = json.loads((regression_dir / "params.json").read_text())
|
||||
config = get_training_preprocessing_config(old_parameters)
|
||||
|
||||
assert config is not None
|
||||
|
||||
for audio_file in example_audio_files:
|
||||
example_file = regression_dir / f"{audio_file.name}.npz"
|
||||
|
||||
dataset = np.load(example_file)
|
||||
|
||||
spec = dataset["spec"][0]
|
||||
detection_mask = dataset["detection_mask"][0]
|
||||
size_mask = dataset["size_mask"]
|
||||
class_mask = dataset["class_mask"]
|
||||
|
||||
project = load_annotated_dataset(
|
||||
BatDetect2FilesAnnotations(
|
||||
name="test",
|
||||
annotations_dir=example_anns_dir,
|
||||
audio_dir=example_audio_dir,
|
||||
)
|
||||
)
|
||||
|
||||
clip_annotation = next(
|
||||
ann
|
||||
for ann in project.clip_annotations
|
||||
if ann.clip.recording.path == audio_file
|
||||
)
|
||||
|
||||
new_dataset = generate_train_example(
|
||||
clip_annotation,
|
||||
preprocessing_config=config.preprocessing,
|
||||
target_config=config.target,
|
||||
label_config=config.labels,
|
||||
)
|
||||
new_spec = new_dataset["spectrogram"].values
|
||||
new_detection_mask = new_dataset["detection"].values
|
||||
new_size_mask = new_dataset["size"].values
|
||||
new_class_mask = new_dataset["class"].values
|
||||
|
||||
assert spec.shape == new_spec.shape
|
||||
assert detection_mask.shape == new_detection_mask.shape
|
||||
assert size_mask.shape == new_size_mask.shape
|
||||
assert class_mask.shape[1:] == new_class_mask.shape[1:]
|
||||
assert class_mask.shape[0] == new_class_mask.shape[0] + 1
|
||||
|
||||
x_new, y_new = np.nonzero(new_size_mask.max(axis=0))
|
||||
x_orig, y_orig = np.nonzero(np.flipud(size_mask.max(axis=0)))
|
||||
|
||||
assert (x_new == x_orig).all()
|
||||
|
||||
# NOTE: a difference of 1 pixel is due to discrepancies on how
|
||||
# frequency bins are interpreted. Shouldn't be an issue
|
||||
assert (y_new == y_orig + 1).all()
|
||||
|
||||
width_new, height_new = new_size_mask[:, x_new, y_new]
|
||||
width_orig, height_orig = np.flip(size_mask, axis=1)[:, x_orig, y_orig]
|
||||
|
||||
assert (np.floor(width_new) == width_orig).all()
|
||||
assert (np.ceil(height_new) == height_orig).all()
|
||||
Loading…
Reference in New Issue
Block a user