birdnet.acoustic.inference.core.encoding package¶

Submodules¶

birdnet.acoustic.inference.core.encoding.encoding_benchmarking module¶

class birdnet.acoustic.inference.core.encoding.encoding_benchmarking.FullBenchmarkEmbMeta(_start_timepoint, _end_timepoint, _time_wall_time_s, _file_durations, file_formats, mem_result_total_memory_usage_MiB, mem_shm_size_file_indices_MiB, mem_shm_size_segment_indices_MiB, mem_shm_size_audio_samples_MiB, mem_shm_size_batch_sizes_MiB, mem_shm_size_flags_MiB, file_segments_total, model_segment_duration_seconds, _time_rampup_first_line_s, model_type, model_backend, model_version, model_is_custom, model_path, model_species, model_sig_fmin, model_sig_fmax, model_sample_rate, model_precision, file_segments_maximum, file_batches_processed, param_producers, param_workers, param_overlap_seconds, param_batch_size, param_prefetch_ratio, param_bandpass_fmin, param_bandpass_fmax, param_half_precision, param_devices, param_inference_library, worker_busy_average, worker_wait_time_average_milliseconds, speed_worker_xrt, speed_worker_xrt_max, _worker_avg_wall_time_s, mem_shm_ringsize, mem_memory_usage_maximum_MiB, mem_memory_usage_average_MiB, cpu_usage_maximum_pct, cpu_usage_average_pct, mem_shm_slots_average_free, mem_shm_slots_average_busy, mem_shm_slots_average_buffered, model_emb_dim)¶

Bases: FullBenchmarkMetaBase

Attributes:

file_count
file_duration_average
file_duration_maximum
file_duration_minimum
file_duration_sum
hw_cpu
hw_cpu_logical_cores
hw_cpu_physical_cores
hw_host
hw_ram_GiB
mem_shm_size_total_MiB
mem_shm_slots_average_filled
speed_total_audio_per_second
speed_total_rtf
speed_total_seg_per_second
speed_total_xrt
speed_worker_rtf
speed_worker_total_audio_per_second
speed_worker_total_seg_per_second
sw_litert_available
sw_os
sw_package_version
sw_python_implementation
sw_python_version
sw_start_method
sw_tf_available
time_begin
time_end
time_iso
time_rampup_first_line
time_wall_time

Methods

to_dict

model_emb_dim: int¶

class birdnet.acoustic.inference.core.encoding.encoding_benchmarking.MinimalBenchmarkEmbMeta(_start_timepoint, _end_timepoint, _time_wall_time_s, _file_durations, file_formats, mem_result_total_memory_usage_MiB, mem_shm_size_file_indices_MiB, mem_shm_size_segment_indices_MiB, mem_shm_size_audio_samples_MiB, mem_shm_size_batch_sizes_MiB, mem_shm_size_flags_MiB, file_segments_total, model_segment_duration_seconds)¶

Bases: MinimalBenchmarkMetaBase

Attributes:

file_count
file_duration_average
file_duration_maximum
file_duration_minimum
file_duration_sum
mem_shm_size_total_MiB
speed_total_audio_per_second
speed_total_rtf
speed_total_seg_per_second
speed_total_xrt
time_begin
time_end
time_wall_time

birdnet.acoustic.inference.core.encoding.encoding_result module¶

class birdnet.acoustic.inference.core.encoding.encoding_result.AcousticDataEncodingResult(tensor, input_durations, segment_duration_s, overlap_duration_s, speed, model_path, model_fmin, model_fmax, model_sr, model_precision, model_version)¶

Bases: AcousticEncodingResultBase

Attributes:

emb_dim: Return the embedding dimensionality.
embeddings: Return the raw embedding tensor produced by the encoder.
embeddings_masked: Return the mask that marks relevant segments across files.
hop_duration_s
input_durations: Durations of each input in seconds.
inputs: Identifiers for each input processed by the result.
max_n_segments: Return the maximum segment count reserved per input.
memory_size_MiB: Return the total result memory usage including embeddings buffers.
model_fmax: Upper bound of the model’s bandpass filter.
model_fmin: Lower bound of the model’s bandpass filter.
model_path
model_precision
model_sr: Sampling rate expected by the model.
model_version
n_inputs: Number of inputs in the result payload.
overlap_duration_s: Overlap duration between sliding windows in seconds.
segment_duration_s: Segment duration as configured on the inference pipeline.
speed: Speed multiplier that was applied to the inputs.

Methods

`to_arrow_table`()	Produce a PyArrow table that serializes each embedding with timing metadata.
`to_csv`(path, *[, encoding, buffer_size_kb, ...])	Dump the structured embeddings to a CSV file for downstream analysis.
`to_dataframe`()	Convert the structured array into a pandas DataFrame.
`to_parquet`(path, *[, compression, ...])	Write the contents to disk as an Arrow Parquet file.
`to_structured_array`()	Convert the embeddings and timing metadata into a structured array.
`unprocessable_inputs`()	Return the indices of inputs that could not be processed.

load
save

class birdnet.acoustic.inference.core.encoding.encoding_result.AcousticEncodingResultBase(inputs, input_durations, model_path, model_fmin, model_fmax, model_sr, model_precision, model_version, segment_duration_s, overlap_duration_s, speed, tensor)¶

Bases: AcousticResultBase

Attributes:

emb_dim: Return the embedding dimensionality.
embeddings: Return the raw embedding tensor produced by the encoder.
embeddings_masked: Return the mask that marks relevant segments across files.
hop_duration_s
input_durations: Durations of each input in seconds.
inputs: Identifiers for each input processed by the result.
max_n_segments: Return the maximum segment count reserved per input.
memory_size_MiB: Return the total result memory usage including embeddings buffers.
model_fmax: Upper bound of the model’s bandpass filter.
model_fmin: Lower bound of the model’s bandpass filter.
model_path
model_precision
model_sr: Sampling rate expected by the model.
model_version
n_inputs: Number of inputs in the result payload.
overlap_duration_s: Overlap duration between sliding windows in seconds.
segment_duration_s: Segment duration as configured on the inference pipeline.
speed: Speed multiplier that was applied to the inputs.

Methods

`to_arrow_table`()	Produce a PyArrow table that serializes each embedding with timing metadata.
`to_csv`(path, *[, encoding, buffer_size_kb, ...])	Dump the structured embeddings to a CSV file for downstream analysis.
`to_dataframe`()	Convert the structured array into a pandas DataFrame.
`to_parquet`(path, *[, compression, ...])	Write the contents to disk as an Arrow Parquet file.
`to_structured_array`()	Convert the embeddings and timing metadata into a structured array.
`unprocessable_inputs`()	Return the indices of inputs that could not be processed.

load
save

property emb_dim: int¶

Return the embedding dimensionality.

Returns:: int: Number of coefficients per embedding vector.

property embeddings: ndarray¶

Return the raw embedding tensor produced by the encoder.

Returns:: np.ndarray: Embeddings with shape (n_inputs, n_segments, emb_dim).

property embeddings_masked: ndarray¶

Return the mask that marks relevant segments across files.

Returns:: np.ndarray: Boolean mask of the same shape as embeddings.

property max_n_segments: int¶

Return the maximum segment count reserved per input.

Returns:: int: Number of overlapping windows available per file.

property memory_size_MiB: float¶

Return the total result memory usage including embeddings buffers.

Returns:: float: Memory size in mebibytes.

to_arrow_table()¶

Produce a PyArrow table that serializes each embedding with timing metadata.

Return type:: Table

Returns:: pa.Table: Table containing dictionary-encoded inputs and embeddings lists.

to_csv(path, *, encoding='utf-8', buffer_size_kb=1024, silent=False)¶

Dump the structured embeddings to a CSV file for downstream analysis.

Return type:: None

Args:: path: File path where the CSV will be written (must end with .csv). encoding: Text encoding for the output file. buffer_size_kb: Buffer size used when writing the file. silent: Suppress progress messages when True.

to_structured_array()¶

Convert the embeddings and timing metadata into a structured array.

Return type:: ndarray

Returns:: np.ndarray: Array with fields for input path, start/end times, and embedding.

unprocessable_inputs()¶

Return the indices of inputs that could not be processed.

Return type:: ndarray

Returns:: np.ndarray: Boolean mask or indices for skipped inputs.

class birdnet.acoustic.inference.core.encoding.encoding_result.AcousticFileEncodingResult(tensor, files, file_durations, segment_duration_s, overlap_duration_s, speed, model_path, model_fmin, model_fmax, model_sr, model_precision, model_version)¶

Bases: AcousticEncodingResultBase

Attributes:

emb_dim: Return the embedding dimensionality.
embeddings: Return the raw embedding tensor produced by the encoder.
embeddings_masked: Return the mask that marks relevant segments across files.
hop_duration_s
input_durations: Durations of each input in seconds.
inputs: Identifiers for each input processed by the result.
max_n_segments: Return the maximum segment count reserved per input.
memory_size_MiB: Return the total result memory usage including embeddings buffers.
model_fmax: Upper bound of the model’s bandpass filter.
model_fmin: Lower bound of the model’s bandpass filter.
model_path
model_precision
model_sr: Sampling rate expected by the model.
model_version
n_inputs: Number of inputs in the result payload.
overlap_duration_s: Overlap duration between sliding windows in seconds.
segment_duration_s: Segment duration as configured on the inference pipeline.
speed: Speed multiplier that was applied to the inputs.

Methods

`to_arrow_table`()	Produce a PyArrow table that serializes each embedding with timing metadata.
`to_csv`(path, *[, encoding, buffer_size_kb, ...])	Dump the structured embeddings to a CSV file for downstream analysis.
`to_dataframe`()	Convert the structured array into a pandas DataFrame.
`to_parquet`(path, *[, compression, ...])	Write the contents to disk as an Arrow Parquet file.
`to_structured_array`()	Convert the embeddings and timing metadata into a structured array.
`unprocessable_inputs`()	Return the indices of inputs that could not be processed.

load
save

birdnet.acoustic.inference.core.encoding.encoding_tensor module¶

class birdnet.acoustic.inference.core.encoding.encoding_tensor.AcousticEncodingTensor(session_id, n_inputs, emb_dim, half_precision, input_indices_dtype, segment_indices_dtype, max_segment_index)¶

Bases: AcousticTensorBase

Attributes:

current_n_segments
memory_usage_mb
unprocessable_inputs

Methods

set_unprocessable_inputs
write_block

property current_n_segments: int¶

property memory_usage_mb: float¶

set_unprocessable_inputs(unprocessable_inputs)¶

Return type:: None

write_block(file_indices, segment_indices, emb)¶

Return type:: None

birdnet.acoustic.inference.core.encoding.encoding_worker module¶

class birdnet.acoustic.inference.core.encoding.encoding_worker.EncodingWorker(session_id, backend_loader, batch_size, n_slots, rf_file_indices, rf_segment_indices, rf_audio_samples, rf_batch_sizes, rf_flags, segment_duration_samples, out_q, wkr_ring_access_lock, sem_free, sem_fill, sem_active_workers, half_precision, wkr_stats_queue, logging_queue, logging_level, device, cancel_event, prd_all_done_event, start_signal, finish_signal, end_event)¶

Bases: WorkerBase

Methods

__call__()

Call self as a function.

run_main
run_main_loop

birdnet.acoustic.inference.core.encoding package¶

Submodules¶

birdnet.acoustic.inference.core.encoding.encoding_benchmarking module¶

birdnet.acoustic.inference.core.encoding.encoding_result module¶

birdnet.acoustic.inference.core.encoding.encoding_tensor module¶

birdnet.acoustic.inference.core.encoding.encoding_worker module¶

Module contents¶

birdnet

Navigation

Related Topics