opensoundscape
OpenSoundscape
Introduction
Quick Start Guide
Resources
Orientation for PyTorch users
Installation
Mac and Linux
Windows
Create a conda environment from the included yml file
Jupyter
Google Colab
Contributors
Tutorials
Audio
Spectrograms
Audio annotations
Use a CNN to recognize sounds
Train a CNN
Transfer learning: training shallow classifiers on embedding models outputs
train on variants of the embeddings generated with audio-space augmentations
Train classifiers on BirdNET or Perch embeddings
Training with Opensoundscape & Pytorch Lightning
Customize CNN training
Preprocess audio samples
Save and load preprocessors
Acoustic localization
Signal processing
Classifiers 101
Introduction to training classifiers
Uses of automated sound classification
Organization
Creating a training dataset
CNN training
Testing a CNN
Further steps
Additional resources
API Documentation
Subpackages
Submodules
opensoundscape.annotations module
opensoundscape.audio module
opensoundscape.data_selection module
opensoundscape.logging module
opensoundscape.metrics module
opensoundscape.ribbit module
opensoundscape.sample module
opensoundscape.signal_processing module
opensoundscape.spectrogram module
opensoundscape.utils module
Module contents
Index
General Index
opensoundscape
Index
Index
_
|
A
|
B
|
C
|
D
|
E
|
F
|
G
|
H
|
I
|
J
|
L
|
M
|
N
|
O
|
P
|
Q
|
R
|
S
|
T
|
U
|
V
|
W
_
__getitem__() (opensoundscape.ml.safe_dataset.SafeDataset method)
__iter__() (opensoundscape.ml.safe_dataset.SafeDataset method)
_safe_get_item() (opensoundscape.ml.safe_dataset.SafeDataset method)
A
Action (class in opensoundscape.preprocess.actions)
action_from_dict() (in module opensoundscape.preprocess.actions)
alexnet() (in module opensoundscape.ml.cnn_architectures)
always_true() (in module opensoundscape.preprocess.overlay)
amplitude() (opensoundscape.spectrogram.Spectrogram method)
annotation_files (opensoundscape.annotations.BoxedAnnotations attribute)
apply_activation_layer() (in module opensoundscape.ml.utils)
apply_channel_gain() (opensoundscape.audio.MultiChannelAudio method)
apply_gain() (opensoundscape.audio.Audio method)
associate_pps_samples_timestamps() (in module opensoundscape.localization.audiomoth_sync)
Audio (class in opensoundscape.audio)
audio_add_noise() (in module opensoundscape.preprocess.action_functions)
audio_files (opensoundscape.annotations.BoxedAnnotations attribute)
audio_random_gain() (in module opensoundscape.preprocess.action_functions)
audio_sample_rate (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
audio_time_mask() (in module opensoundscape.preprocess.action_functions)
AudioAugmentationPreprocessor (class in opensoundscape.preprocess.preprocessors)
AudioClipLoader (class in opensoundscape.preprocess.actions)
AudioFileDataset (class in opensoundscape.ml.datasets)
AudioOutOfBoundsError
AudioPreprocessor (class in opensoundscape.preprocess.preprocessors)
AudioSample (class in opensoundscape.sample)
AudioSplittingDataset (class in opensoundscape.ml.datasets)
AudioTrim (class in opensoundscape.preprocess.actions)
augmented_embed() (in module opensoundscape.ml.shallow_classifier)
B
bandpass() (opensoundscape.annotations.BoxedAnnotations method)
(opensoundscape.audio.Audio method)
(opensoundscape.spectrogram.Spectrogram method)
bandpass_filter() (in module opensoundscape.audio)
BaseAction (class in opensoundscape.preprocess.actions)
BaseClassifier (class in opensoundscape.ml.cnn)
BaseModule (class in opensoundscape.ml.cnn)
BasePreprocessor (class in opensoundscape.preprocess.preprocessors)
BCEWithLogitsLoss_hot (class in opensoundscape.ml.loss)
binarize() (in module opensoundscape.utils)
binary_cross_entropy() (in module opensoundscape.ml.loss)
BoxedAnnotations (class in opensoundscape.annotations)
build_name() (in module opensoundscape.preprocess.io)
C
calc_speed_of_sound() (in module opensoundscape.localization.localization_algorithms)
calculate_pulse_score() (in module opensoundscape.ribbit)
calculate_tdoa_residuals() (in module opensoundscape.localization.spatial_event)
CAM (class in opensoundscape.ml.cam)
cas_dataloader() (in module opensoundscape.ml.utils)
cast_np_to_native() (in module opensoundscape.utils)
categorical_labels (opensoundscape.sample.AudioSample property)
categorical_to_integer_labels() (in module opensoundscape.annotations)
categorical_to_multi_hot() (in module opensoundscape.annotations)
CategoricalLabels (class in opensoundscape.annotations)
change_classes() (opensoundscape.ml.cnn.SpectrogramModule method)
change_conv2d_channels() (in module opensoundscape.ml.cnn_architectures)
change_fc_output_size() (in module opensoundscape.ml.cnn_architectures)
ChannelDimCheckError
check_files_missing_coordinates() (opensoundscape.localization.synchronized_recorder_array.SynchronizedRecorderArray method)
check_labels() (in module opensoundscape.ml.utils)
class_aware_sample_generator() (in module opensoundscape.ml.sampling)
class_counts() (opensoundscape.ml.datasets.AudioFileDataset method)
class_labels (opensoundscape.annotations.CategoricalLabels property)
ClassAwareSampler (class in opensoundscape.ml.sampling)
classifier (opensoundscape.ml.cnn.SpectrogramModule property)
clip_labels() (opensoundscape.annotations.BoxedAnnotations method)
clipping_detector() (in module opensoundscape.audio)
CNN (class in opensoundscape.ml.cnn)
collate_audio_samples() (in module opensoundscape.sample)
collate_audio_samples_to_dict() (in module opensoundscape.sample)
collate_audio_samples_to_tensors() (in module opensoundscape.ml.utils)
concat() (in module opensoundscape.audio)
(opensoundscape.annotations.BoxedAnnotations class method)
configure_optimizers() (opensoundscape.ml.cnn.BaseModule method)
convert_labels() (opensoundscape.annotations.BoxedAnnotations method)
correct_sample_rate() (in module opensoundscape.localization.audiomoth_sync)
create_candidate_events() (opensoundscape.localization.synchronized_recorder_array.SynchronizedRecorderArray method)
create_rgb_heatmaps() (opensoundscape.ml.cam.CAM method)
CrossEntropyLoss_hot (class in opensoundscape.ml.loss)
current_epoch (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
CustomYamlDumper (class in opensoundscape.preprocess.io)
CustomYamlLoader (class in opensoundscape.preprocess.io)
cwt_peaks() (in module opensoundscape.signal_processing)
D
dBFS (opensoundscape.audio.Audio property)
default() (opensoundscape.preprocess.io.NumpyTypeEncoder method)
densenet121() (in module opensoundscape.ml.cnn_architectures)
detect_peak_sequence_cwt() (in module opensoundscape.signal_processing)
device (opensoundscape.ml.cnn.SpectrogramClassifier property)
df (opensoundscape.annotations.BoxedAnnotations attribute)
df_to_events() (in module opensoundscape.localization.spatial_event)
df_to_positions() (in module opensoundscape.localization.position_estimate)
diff() (in module opensoundscape.annotations)
duration (opensoundscape.audio.Audio property)
(opensoundscape.audio.MultiChannelAudio property)
(opensoundscape.spectrogram.Spectrogram property)
E
efficientnet_b0() (in module opensoundscape.ml.cnn_architectures)
efficientnet_b4() (in module opensoundscape.ml.cnn_architectures)
embed() (opensoundscape.ml.cnn.SpectrogramClassifier method)
end_time (opensoundscape.sample.AudioSample property)
estimate_delay() (in module opensoundscape.audio)
estimate_location() (opensoundscape.localization.spatial_event.SpatialEvent method)
eval() (opensoundscape.ml.cnn.SpectrogramClassifier method)
events_to_df() (in module opensoundscape.localization.spatial_event)
extend_by() (opensoundscape.audio.Audio method)
extend_to() (opensoundscape.audio.Audio method)
(opensoundscape.audio.MultiChannelAudio method)
F
find_accel_sequences() (in module opensoundscape.signal_processing)
find_overlapping_idxs_in_clip_df() (in module opensoundscape.annotations)
fit() (opensoundscape.ml.shallow_classifier.MLPClassifier method)
fit_classifier_on_embeddings() (in module opensoundscape.ml.shallow_classifier)
fit_with_trainer() (opensoundscape.ml.lightning.LightningSpectrogramModule method)
forward() (opensoundscape.ml.lightning.LightningSpectrogramModule method)
(opensoundscape.ml.loss.BCEWithLogitsLoss_hot method)
(opensoundscape.ml.loss.CrossEntropyLoss_hot method)
(opensoundscape.ml.loss.ResampleLoss method)
(opensoundscape.ml.shallow_classifier.MLPClassifier method)
(opensoundscape.preprocess.preprocessors.BasePreprocessor method)
freeze_feature_extractor() (opensoundscape.ml.cnn.SpectrogramModule method)
freeze_layers_except() (opensoundscape.ml.cnn.SpectrogramModule method)
freeze_params() (in module opensoundscape.ml.cnn_architectures)
freq_mask() (in module opensoundscape.preprocess.tensor_augment)
frequencies (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
frequency2scale() (in module opensoundscape.signal_processing)
frequency_mask() (in module opensoundscape.preprocess.action_functions)
from_audio() (opensoundscape.spectrogram.MelSpectrogram class method)
(opensoundscape.spectrogram.Spectrogram class method)
from_audio_list() (opensoundscape.audio.MultiChannelAudio class method)
from_bytesio() (opensoundscape.audio.Audio class method)
from_categorical_df() (opensoundscape.ml.datasets.AudioFileDataset class method)
from_categorical_labels_df() (opensoundscape.annotations.CategoricalLabels class method)
from_crowsetta() (opensoundscape.annotations.BoxedAnnotations class method)
from_crowsetta_bbox() (opensoundscape.annotations.BoxedAnnotations class method)
from_crowsetta_seq() (opensoundscape.annotations.BoxedAnnotations class method)
from_csv() (opensoundscape.annotations.BoxedAnnotations class method)
from_dict() (opensoundscape.localization.position_estimate.PositionEstimate class method)
(opensoundscape.localization.spatial_event.SpatialEvent class method)
(opensoundscape.preprocess.actions.Action class method)
(opensoundscape.preprocess.actions.BaseAction class method)
(opensoundscape.preprocess.overlay.Overlay class method)
(opensoundscape.preprocess.preprocessors.BasePreprocessor class method)
from_file() (opensoundscape.audio.Audio class method)
(opensoundscape.audio.MultiChannelAudio class method)
from_json() (opensoundscape.preprocess.preprocessors.BasePreprocessor class method)
from_multihot_df() (opensoundscape.annotations.CategoricalLabels class method)
from_raven_files() (opensoundscape.annotations.BoxedAnnotations class method)
from_series() (opensoundscape.sample.AudioSample class method)
from_torch_dict() (opensoundscape.ml.cnn.InceptionV3 class method)
from_url() (opensoundscape.audio.Audio class method)
from_yaml() (opensoundscape.preprocess.preprocessors.BasePreprocessor class method)
G
gcc() (in module opensoundscape.signal_processing)
generate_cams() (opensoundscape.ml.cnn.SpectrogramClassifier method)
generate_clip_times_df() (in module opensoundscape.utils)
generate_opacity_colormaps() (in module opensoundscape.utils)
generate_opso_metadata_str() (in module opensoundscape.audio)
generate_samples() (opensoundscape.ml.cnn.SpectrogramClassifier method)
generic_make_arch() (in module opensoundscape.ml.cnn_architectures)
get() (opensoundscape.preprocess.actions.BaseAction method)
get_args() (in module opensoundscape.preprocess.utils)
get_batch() (in module opensoundscape.ml.utils)
get_channel_dim() (in module opensoundscape.ml.cnn)
get_reqd_args() (in module opensoundscape.preprocess.utils)
get_sampler() (in module opensoundscape.ml.sampling)
GetDurationError
GetStartTimestamp (class in opensoundscape.localization.synchronized_recorder_array)
gillette_localize() (in module opensoundscape.localization.localization_algorithms)
global_multi_hot_labels() (opensoundscape.annotations.BoxedAnnotations method)
H
head() (opensoundscape.ml.datasets.AudioFileDataset method)
highpass() (opensoundscape.audio.Audio method)
highpass_filter() (in module opensoundscape.audio)
I
identity() (in module opensoundscape.utils)
image_to_tensor() (in module opensoundscape.preprocess.action_functions)
ImbalancedDatasetSampler (class in opensoundscape.ml.sampling)
inception_v3() (in module opensoundscape.ml.cnn_architectures)
InceptionV3 (class in opensoundscape.ml.cnn)
inference_dataloader_cls (opensoundscape.ml.cnn.BaseModule attribute)
inrange() (in module opensoundscape.utils)
insert_action() (opensoundscape.preprocess.preprocessors.BasePreprocessor method)
integer_to_categorical_labels() (in module opensoundscape.annotations)
integer_to_multi_hot() (in module opensoundscape.annotations)
InvalidIndexError
isNan() (in module opensoundscape.utils)
J
jitter() (in module opensoundscape.utils)
L
labels (opensoundscape.annotations.CategoricalLabels property)
labels_at_index() (opensoundscape.annotations.CategoricalLabels method)
labels_on_index() (opensoundscape.annotations.BoxedAnnotations method)
least_squares_localize() (in module opensoundscape.localization.localization_algorithms)
LightningSpectrogramModule (class in opensoundscape.ml.lightning)
limit_range() (opensoundscape.spectrogram.Spectrogram method)
linear_scale() (in module opensoundscape.utils)
(opensoundscape.spectrogram.Spectrogram method)
list_action_fns() (in module opensoundscape.preprocess.action_functions)
list_actions() (in module opensoundscape.preprocess.actions)
list_architectures() (in module opensoundscape.ml.cnn_architectures)
list_model_classes() (in module opensoundscape.ml.cnn)
list_models() (in module opensoundscape.ml.bioacoustics_model_zoo)
load() (in module opensoundscape.ml.bioacoustics_model_zoo)
(in module opensoundscape.preprocess.preprocessors)
(opensoundscape.ml.cnn.SpectrogramClassifier class method)
(opensoundscape.ml.shallow_classifier.MLPClassifier method)
load_aligned_audio_segments() (opensoundscape.localization.position_estimate.PositionEstimate method)
load_channels_as_audio() (in module opensoundscape.audio)
load_json() (in module opensoundscape.preprocess.preprocessors)
load_model() (in module opensoundscape.ml.cnn)
load_weights() (opensoundscape.ml.cnn.SpectrogramClassifier method)
(opensoundscape.ml.lightning.LightningSpectrogramModule method)
load_yaml() (in module opensoundscape.preprocess.preprocessors)
localize() (in module opensoundscape.localization.localization_algorithms)
localize_detections() (opensoundscape.localization.synchronized_recorder_array.SynchronizedRecorderArray method)
,
[1]
localize_events_parallel() (in module opensoundscape.localization.spatial_event)
log_file (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
logging_level (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
logit_reg_functions() (opensoundscape.ml.loss.ResampleLoss method)
loop() (opensoundscape.audio.Audio method)
lorentz_ip() (in module opensoundscape.localization.localization_algorithms)
loss_fn (opensoundscape.ml.cnn.BaseModule attribute)
loss_hist (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
lowpass() (opensoundscape.audio.Audio method)
lowpass_filter() (in module opensoundscape.audio)
lr_scheduler_params (opensoundscape.ml.cnn.BaseModule attribute)
lr_scheduler_step (opensoundscape.ml.cnn.SpectrogramModule attribute)
M
make_clip_df() (in module opensoundscape.utils)
make_nearby_files_dict() (opensoundscape.localization.synchronized_recorder_array.SynchronizedRecorderArray method)
MelSpectrogram (class in opensoundscape.spectrogram)
metadata (opensoundscape.audio.Audio attribute)
(opensoundscape.audio.MultiChannelAudio attribute)
min_max_scale() (in module opensoundscape.utils)
(opensoundscape.spectrogram.Spectrogram method)
mix() (in module opensoundscape.audio)
MLPClassifier (class in opensoundscape.ml.shallow_classifier)
module
opensoundscape
opensoundscape.annotations
opensoundscape.audio
opensoundscape.data_selection
opensoundscape.localization
opensoundscape.localization.audiomoth_sync
opensoundscape.localization.localization_algorithms
opensoundscape.localization.position_estimate
opensoundscape.localization.spatial_event
opensoundscape.localization.synchronized_recorder_array
opensoundscape.localization.utils
opensoundscape.logging
opensoundscape.metrics
opensoundscape.ml
opensoundscape.ml.bioacoustics_model_zoo
opensoundscape.ml.cam
opensoundscape.ml.cnn
opensoundscape.ml.cnn_architectures
opensoundscape.ml.dataloaders
opensoundscape.ml.datasets
opensoundscape.ml.lightning
opensoundscape.ml.loss
opensoundscape.ml.safe_dataset
opensoundscape.ml.sampling
opensoundscape.ml.shallow_classifier
opensoundscape.ml.utils
opensoundscape.preprocess
opensoundscape.preprocess.action_functions
opensoundscape.preprocess.actions
opensoundscape.preprocess.img_augment
opensoundscape.preprocess.io
opensoundscape.preprocess.overlay
opensoundscape.preprocess.preprocessors
opensoundscape.preprocess.tensor_augment
opensoundscape.preprocess.utils
opensoundscape.ribbit
opensoundscape.sample
opensoundscape.signal_processing
opensoundscape.spectrogram
opensoundscape.utils
multi_hot_to_categorical() (in module opensoundscape.annotations)
multi_hot_to_integer_labels() (in module opensoundscape.annotations)
multi_target_metrics() (in module opensoundscape.metrics)
MultiChannelAudio (class in opensoundscape.audio)
multihot_array() (opensoundscape.annotations.CategoricalLabels method)
multihot_dense (opensoundscape.annotations.CategoricalLabels property)
multihot_df() (opensoundscape.annotations.CategoricalLabels method)
multihot_df_dense (opensoundscape.annotations.CategoricalLabels property)
multihot_df_sparse (opensoundscape.annotations.CategoricalLabels property)
multihot_labels_at_index() (opensoundscape.annotations.CategoricalLabels method)
multihot_sparse (opensoundscape.annotations.CategoricalLabels property)
N
n_channels (opensoundscape.audio.MultiChannelAudio property)
name (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
net_amplitude() (opensoundscape.spectrogram.Spectrogram method)
network (opensoundscape.ml.cnn.BaseModule attribute)
(opensoundscape.ml.cnn.SpectrogramModule attribute)
noise() (opensoundscape.audio.Audio class method)
(opensoundscape.audio.MultiChannelAudio class method)
NoiseReduceAudioPreprocessor (class in opensoundscape.preprocess.preprocessors)
NoiseReduceSpectrogramPreprocessor (class in opensoundscape.preprocess.preprocessors)
normalize() (opensoundscape.audio.Audio method)
numpy_dtype_constructor() (in module opensoundscape.preprocess.io)
numpy_dtype_representer() (in module opensoundscape.preprocess.io)
NumpyTypeDecoder (class in opensoundscape.preprocess.io)
NumpyTypeEncoder (class in opensoundscape.preprocess.io)
O
object_hook() (opensoundscape.preprocess.io.NumpyTypeDecoder method)
opensoundscape
module
opensoundscape.annotations
module
opensoundscape.audio
module
opensoundscape.data_selection
module
opensoundscape.localization
module
opensoundscape.localization.audiomoth_sync
module
opensoundscape.localization.localization_algorithms
module
opensoundscape.localization.position_estimate
module
opensoundscape.localization.spatial_event
module
opensoundscape.localization.synchronized_recorder_array
module
opensoundscape.localization.utils
module
opensoundscape.logging
module
opensoundscape.metrics
module
opensoundscape.ml
module
opensoundscape.ml.bioacoustics_model_zoo
module
opensoundscape.ml.cam
module
opensoundscape.ml.cnn
module
opensoundscape.ml.cnn_architectures
module
opensoundscape.ml.dataloaders
module
opensoundscape.ml.datasets
module
opensoundscape.ml.lightning
module
opensoundscape.ml.loss
module
opensoundscape.ml.safe_dataset
module
opensoundscape.ml.sampling
module
opensoundscape.ml.shallow_classifier
module
opensoundscape.ml.utils
module
opensoundscape.preprocess
module
opensoundscape.preprocess.action_functions
module
opensoundscape.preprocess.actions
module
opensoundscape.preprocess.img_augment
module
opensoundscape.preprocess.io
module
opensoundscape.preprocess.overlay
module
opensoundscape.preprocess.preprocessors
module
opensoundscape.preprocess.tensor_augment
module
opensoundscape.preprocess.utils
module
opensoundscape.ribbit
module
opensoundscape.sample
module
opensoundscape.signal_processing
module
opensoundscape.spectrogram
module
opensoundscape.utils
module
OpsoLoadAudioInputError
optimizer_params (opensoundscape.ml.cnn.BaseModule attribute)
overlap() (in module opensoundscape.utils)
overlap_fraction() (in module opensoundscape.utils)
overlap_samples (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
Overlay (class in opensoundscape.preprocess.overlay)
overlay() (in module opensoundscape.preprocess.overlay)
P
parse_metadata() (in module opensoundscape.audio)
parse_opso_metadata() (in module opensoundscape.audio)
parse_RMC_time_to_datetime() (in module opensoundscape.localization.audiomoth_sync)
parse_RMC_time_to_seconds() (in module opensoundscape.localization.audiomoth_sync)
pcen() (in module opensoundscape.preprocess.action_functions)
PCENPreprocessor (class in opensoundscape.preprocess.preprocessors)
plot() (opensoundscape.ml.cam.CAM method)
(opensoundscape.spectrogram.MelSpectrogram method)
(opensoundscape.spectrogram.Spectrogram method)
PositionEstimate (class in opensoundscape.localization.position_estimate)
positions_to_df() (in module opensoundscape.localization.position_estimate)
predict() (opensoundscape.ml.cnn.SpectrogramClassifier method)
predict_dataloader() (opensoundscape.ml.cnn.BaseModule method)
predict_multi_target_labels() (in module opensoundscape.metrics)
predict_single_target_labels() (in module opensoundscape.metrics)
predict_with_trainer() (opensoundscape.ml.lightning.LightningSpectrogramModule method)
PreprocessingError
preprocessor (opensoundscape.ml.cnn.BaseModule attribute)
(opensoundscape.ml.dataloaders.SafeAudioDataloader attribute)
preprocessor_from_dict() (in module opensoundscape.preprocess.preprocessors)
Q
quick_fit() (in module opensoundscape.ml.shallow_classifier)
R
random_wrap_audio() (in module opensoundscape.preprocess.action_functions)
RandomCycleIter (class in opensoundscape.ml.sampling)
rebalance_weight() (opensoundscape.ml.loss.ResampleLoss method)
reduce_loss() (in module opensoundscape.ml.loss)
reduce_noise() (opensoundscape.audio.Audio method)
register_action_cls() (in module opensoundscape.preprocess.actions)
register_action_fn() (in module opensoundscape.preprocess.action_functions)
register_all_methods() (in module opensoundscape.preprocess.actions)
register_arch() (in module opensoundscape.ml.cnn_architectures)
register_model_cls() (in module opensoundscape.ml.cnn)
register_preprocessor_cls() (in module opensoundscape.preprocess.preprocessors)
remove_action() (opensoundscape.preprocess.preprocessors.BasePreprocessor method)
report() (opensoundscape.ml.safe_dataset.SafeDataset method)
resample() (in module opensoundscape.data_selection)
(opensoundscape.audio.Audio method)
resample_type (opensoundscape.audio.Audio attribute)
(opensoundscape.audio.MultiChannelAudio attribute)
ResampleLoss (class in opensoundscape.ml.loss)
rescale_features() (in module opensoundscape.utils)
residual_rms (opensoundscape.localization.position_estimate.PositionEstimate property)
resnet101() (in module opensoundscape.ml.cnn_architectures)
resnet152() (in module opensoundscape.ml.cnn_architectures)
resnet18() (in module opensoundscape.ml.cnn_architectures)
resnet34() (in module opensoundscape.ml.cnn_architectures)
resnet50() (in module opensoundscape.ml.cnn_architectures)
reweight_functions() (opensoundscape.ml.loss.ResampleLoss method)
ribbit() (in module opensoundscape.ribbit)
rms (opensoundscape.audio.Audio property)
run_validation() (opensoundscape.ml.cnn.SpectrogramClassifier method)
S
SafeAudioDataloader (class in opensoundscape.ml.dataloaders)
SafeDataset (class in opensoundscape.ml.safe_dataset)
Sample (class in opensoundscape.sample)
sample() (opensoundscape.ml.datasets.AudioFileDataset method)
sample_rate (opensoundscape.audio.Audio attribute)
(opensoundscape.audio.MultiChannelAudio attribute)
samples (opensoundscape.audio.Audio attribute)
(opensoundscape.audio.MultiChannelAudio attribute)
(opensoundscape.ml.dataloaders.SafeAudioDataloader attribute)
save() (opensoundscape.audio.Audio method)
(opensoundscape.audio.MultiChannelAudio method)
(opensoundscape.ml.cnn.SpectrogramClassifier method)
(opensoundscape.ml.lightning.LightningSpectrogramModule method)
(opensoundscape.ml.shallow_classifier.MLPClassifier method)
(opensoundscape.preprocess.preprocessors.BasePreprocessor method)
save_json() (opensoundscape.preprocess.preprocessors.BasePreprocessor method)
save_weights() (opensoundscape.ml.cnn.SpectrogramClassifier method)
(opensoundscape.ml.lightning.LightningSpectrogramModule method)
save_yaml() (opensoundscape.preprocess.preprocessors.BasePreprocessor method)
scale_tensor() (in module opensoundscape.preprocess.action_functions)
scaling (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
scheduler (opensoundscape.ml.cnn.BaseModule attribute)
score_metric (opensoundscape.ml.cnn.BaseModule attribute)
set() (opensoundscape.preprocess.actions.BaseAction method)
set_layer_from_name() (in module opensoundscape.ml.cnn_architectures)
set_seed() (in module opensoundscape.utils)
show_tensor() (in module opensoundscape.preprocess.utils)
show_tensor_grid() (in module opensoundscape.preprocess.utils)
show_widget() (opensoundscape.audio.Audio method)
sigmoid() (in module opensoundscape.utils)
silence() (opensoundscape.audio.Audio class method)
(opensoundscape.audio.MultiChannelAudio class method)
single_target (opensoundscape.ml.cnn.SpectrogramModule property)
single_target_metrics() (in module opensoundscape.metrics)
soundfinder_localize() (in module opensoundscape.localization.localization_algorithms)
SpatialEvent (class in opensoundscape.localization.spatial_event)
Spectrogram (class in opensoundscape.spectrogram)
spectrogram (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
SpectrogramClassifier (class in opensoundscape.ml.cnn)
SpectrogramModule (class in opensoundscape.ml.cnn)
SpectrogramPreprocessor (class in opensoundscape.preprocess.preprocessors)
SpectrogramToTensor (class in opensoundscape.preprocess.actions)
spectrum() (opensoundscape.audio.Audio method)
(opensoundscape.audio.MultiChannelAudio method)
split() (opensoundscape.audio.Audio method)
split_and_save() (opensoundscape.audio.Audio method)
(opensoundscape.audio.MultiChannelAudio method)
squeezenet1_0() (in module opensoundscape.ml.cnn_architectures)
subset() (opensoundscape.annotations.BoxedAnnotations method)
SynchronizedRecorderArray (class in opensoundscape.localization.synchronized_recorder_array)
T
tdoa() (in module opensoundscape.signal_processing)
tensor_add_noise() (in module opensoundscape.preprocess.action_functions)
thresholded_event_durations() (in module opensoundscape.signal_processing)
time_mask() (in module opensoundscape.preprocess.action_functions)
(in module opensoundscape.preprocess.tensor_augment)
time_split() (in module opensoundscape.preprocess.img_augment)
times (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
to_channels() (opensoundscape.audio.MultiChannelAudio method)
to_crowsetta() (opensoundscape.annotations.BoxedAnnotations method)
to_csv() (opensoundscape.annotations.BoxedAnnotations method)
to_dict() (opensoundscape.localization.position_estimate.PositionEstimate method)
(opensoundscape.localization.spatial_event.SpatialEvent method)
(opensoundscape.preprocess.actions.Action method)
(opensoundscape.preprocess.actions.BaseAction method)
(opensoundscape.preprocess.overlay.Overlay method)
(opensoundscape.preprocess.preprocessors.BasePreprocessor method)
to_image() (opensoundscape.spectrogram.Spectrogram method)
to_mono() (opensoundscape.audio.MultiChannelAudio method)
to_raven_files() (opensoundscape.annotations.BoxedAnnotations method)
torch_color_jitter() (in module opensoundscape.preprocess.action_functions)
torch_metrics (opensoundscape.ml.cnn.BaseModule attribute)
torch_random_affine() (in module opensoundscape.preprocess.action_functions)
train() (opensoundscape.ml.cnn.SpectrogramClassifier method)
(opensoundscape.ml.lightning.LightningSpectrogramModule method)
train_dataloader() (opensoundscape.ml.cnn.BaseModule method)
train_dataloader_cls (opensoundscape.ml.cnn.BaseModule attribute)
training_step() (opensoundscape.ml.cnn.BaseModule method)
(opensoundscape.ml.cnn.InceptionV3 method)
transpose_samples_decorator() (in module opensoundscape.audio)
travel_time() (in module opensoundscape.localization.localization_algorithms)
trim() (opensoundscape.annotations.BoxedAnnotations method)
(opensoundscape.audio.Audio method)
(opensoundscape.spectrogram.Spectrogram method)
trim_audio() (in module opensoundscape.preprocess.actions)
trim_samples() (opensoundscape.audio.Audio method)
(opensoundscape.audio.MultiChannelAudio method)
trim_with_timestamps() (opensoundscape.audio.Audio method)
U
unfreeze() (opensoundscape.ml.cnn.SpectrogramModule method)
unfreeze_params() (in module opensoundscape.ml.cnn_architectures)
unique() (in module opensoundscape.annotations)
unique_labels() (opensoundscape.annotations.BoxedAnnotations method)
upsample() (in module opensoundscape.data_selection)
use_amp (opensoundscape.ml.cnn.BaseModule attribute)
use_resample_loss() (in module opensoundscape.ml.cnn)
V
validation_step() (opensoundscape.ml.cnn.BaseModule method)
verbose (opensoundscape.ml.cnn.SpectrogramClassifier attribute)
vgg11_bn() (in module opensoundscape.ml.cnn_architectures)
W
wandb_table() (in module opensoundscape.logging)
weight_reduce_loss() (in module opensoundscape.ml.loss)
window_length (opensoundscape.spectrogram.Spectrogram property)
window_samples (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]
window_start_times (opensoundscape.spectrogram.Spectrogram property)
window_step (opensoundscape.spectrogram.Spectrogram property)
window_type (opensoundscape.spectrogram.MelSpectrogram attribute)
(opensoundscape.spectrogram.Spectrogram attribute)
,
[1]