justdata 1.0.0__py3-none-any.whl
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- justdata/__init__.py +3 -0
- justdata/acoustic/__init__.py +381 -0
- justdata/acoustic/adapters.py +329 -0
- justdata/acoustic/augment/__init__.py +119 -0
- justdata/acoustic/augment/batch.py +813 -0
- justdata/acoustic/augment/configs.py +204 -0
- justdata/acoustic/augment/patchout.py +331 -0
- justdata/acoustic/augment/spectrogram.py +806 -0
- justdata/acoustic/augment/waveform.py +879 -0
- justdata/acoustic/batching.py +27 -0
- justdata/acoustic/channel.py +53 -0
- justdata/acoustic/compat/__init__.py +95 -0
- justdata/acoustic/compat/ast.py +626 -0
- justdata/acoustic/compat/ced.py +152 -0
- justdata/acoustic/compat/efficientat.py +243 -0
- justdata/acoustic/compat/panns.py +115 -0
- justdata/acoustic/compat/passt.py +191 -0
- justdata/acoustic/configs.py +519 -0
- justdata/acoustic/corruptions/__init__.py +33 -0
- justdata/acoustic/corruptions/codec.py +92 -0
- justdata/acoustic/corruptions/datasets.py +155 -0
- justdata/acoustic/corruptions/device.py +39 -0
- justdata/acoustic/corruptions/dynamics.py +55 -0
- justdata/acoustic/corruptions/filters.py +105 -0
- justdata/acoustic/corruptions/noise.py +173 -0
- justdata/acoustic/corruptions/registry.py +230 -0
- justdata/acoustic/corruptions/reverb.py +49 -0
- justdata/acoustic/corruptions/timefreq.py +127 -0
- justdata/acoustic/datasets.py +52 -0
- justdata/acoustic/dcase2025.py +814 -0
- justdata/acoustic/decoding.py +73 -0
- justdata/acoustic/eval_views.py +54 -0
- justdata/acoustic/evals.py +71 -0
- justdata/acoustic/filters.py +18 -0
- justdata/acoustic/frontends/__init__.py +37 -0
- justdata/acoustic/frontends/ast.py +116 -0
- justdata/acoustic/frontends/kaldi.py +34 -0
- justdata/acoustic/frontends/log.py +94 -0
- justdata/acoustic/frontends/mel.py +173 -0
- justdata/acoustic/frontends/mfcc.py +26 -0
- justdata/acoustic/frontends/pcen.py +26 -0
- justdata/acoustic/frontends/stft.py +174 -0
- justdata/acoustic/jax.py +23 -0
- justdata/acoustic/labels.py +169 -0
- justdata/acoustic/layouts.py +86 -0
- justdata/acoustic/metadata.py +152 -0
- justdata/acoustic/normalization.py +196 -0
- justdata/acoustic/pipelines.py +112 -0
- justdata/acoustic/postprocessing.py +328 -0
- justdata/acoustic/preprocessing.py +175 -0
- justdata/acoustic/presets.py +257 -0
- justdata/acoustic/registry.py +381 -0
- justdata/acoustic/resampling.py +218 -0
- justdata/acoustic/schema.py +51 -0
- justdata/acoustic/segment.py +369 -0
- justdata/acoustic/sources.py +503 -0
- justdata/acoustic/stages.py +59 -0
- justdata/acoustic/stats.py +50 -0
- justdata/acoustic/tasks.py +375 -0
- justdata/audio/__init__.py +20 -0
- justdata/core/__init__.py +74 -0
- justdata/core/adapters.py +46 -0
- justdata/core/augmentations.py +34 -0
- justdata/core/filters.py +94 -0
- justdata/core/finalization.py +173 -0
- justdata/core/label_mixing.py +129 -0
- justdata/core/loader.py +384 -0
- justdata/core/metadata.py +250 -0
- justdata/core/presets.py +155 -0
- justdata/core/registry.py +229 -0
- justdata/core/sources.py +87 -0
- justdata/core/stats.py +227 -0
- justdata/corruptions.py +52 -0
- justdata/py.typed +0 -0
- justdata/vision/__init__.py +17 -0
- justdata/vision/augmentations/__init__.py +31 -0
- justdata/vision/augmentations/auto.py +480 -0
- justdata/vision/augmentations/color.py +163 -0
- justdata/vision/augmentations/composed.py +156 -0
- justdata/vision/augmentations/geometric.py +302 -0
- justdata/vision/augmentations/mixing.py +232 -0
- justdata/vision/augmentations/registry.py +142 -0
- justdata/vision/corruptions/__init__.py +16 -0
- justdata/vision/corruptions/blur.py +65 -0
- justdata/vision/corruptions/digital.py +26 -0
- justdata/vision/corruptions/noise.py +20 -0
- justdata/vision/corruptions/registry.py +113 -0
- justdata/vision/corruptions/weather.py +100 -0
- justdata/vision/datasets.py +34 -0
- justdata/vision/encodings/__init__.py +1 -0
- justdata/vision/encodings/heatmaps.py +196 -0
- justdata/vision/minic.py +69 -0
- justdata/vision/pipelines.py +62 -0
- justdata/vision/presets.py +509 -0
- justdata/vision/sources.py +1080 -0
- justdata/vision/stages.py +271 -0
- justdata/vision/tasks/__init__.py +1 -0
- justdata/vision/tasks/classification.py +321 -0
- justdata/vision/tasks/depth.py +25 -0
- justdata/vision/tasks/segmentation.py +194 -0
- justdata/vision/transforms.py +113 -0
- justdata/vision/utils.py +741 -0
- justdata-1.0.0.dist-info/METADATA +860 -0
- justdata-1.0.0.dist-info/RECORD +106 -0
- justdata-1.0.0.dist-info/WHEEL +4 -0
- justdata-1.0.0.dist-info/licenses/LICENSE +23 -0
|
@@ -0,0 +1,27 @@
|
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
3
|
+
import tensorflow as tf
|
|
4
|
+
|
|
5
|
+
|
|
6
|
+
def pad_nested(value, pad_size, *, metadata_mode: str = "full"):
|
|
7
|
+
"""Pad the first dimension of tensors in nested dictionaries."""
|
|
8
|
+
if isinstance(value, dict):
|
|
9
|
+
padded = {}
|
|
10
|
+
for key, child in value.items():
|
|
11
|
+
child = pad_nested(child, pad_size, metadata_mode=metadata_mode)
|
|
12
|
+
if child is not None:
|
|
13
|
+
padded[key] = child
|
|
14
|
+
return padded
|
|
15
|
+
|
|
16
|
+
if metadata_mode != "full" and value.dtype == tf.string:
|
|
17
|
+
return None
|
|
18
|
+
|
|
19
|
+
pad_shape = tf.concat([[pad_size], tf.shape(value)[1:]], axis=0)
|
|
20
|
+
if value.dtype == tf.string:
|
|
21
|
+
fill = tf.fill(pad_shape, tf.constant("", dtype=tf.string))
|
|
22
|
+
else:
|
|
23
|
+
fill = tf.zeros(pad_shape, dtype=value.dtype)
|
|
24
|
+
return tf.concat([value, fill], axis=0)
|
|
25
|
+
|
|
26
|
+
|
|
27
|
+
__all__ = ["pad_nested"]
|
|
@@ -0,0 +1,53 @@
|
|
|
1
|
+
from __future__ import annotations
|
|
2
|
+
|
|
3
|
+
import tensorflow as tf
|
|
4
|
+
|
|
5
|
+
from justdata.acoustic.registry import register_audio_channel_strategy
|
|
6
|
+
|
|
7
|
+
|
|
8
|
+
@register_audio_channel_strategy("mono_mean")
|
|
9
|
+
def mono_mean(audio: tf.Tensor) -> tf.Tensor:
|
|
10
|
+
audio = tf.convert_to_tensor(audio)
|
|
11
|
+
return tf.reduce_mean(audio, axis=-1, keepdims=True)
|
|
12
|
+
|
|
13
|
+
|
|
14
|
+
@register_audio_channel_strategy("mono_left")
|
|
15
|
+
def mono_left(audio: tf.Tensor) -> tf.Tensor:
|
|
16
|
+
audio = tf.convert_to_tensor(audio)
|
|
17
|
+
return audio[:, :1]
|
|
18
|
+
|
|
19
|
+
|
|
20
|
+
@register_audio_channel_strategy("mono_right")
|
|
21
|
+
def mono_right(audio: tf.Tensor) -> tf.Tensor:
|
|
22
|
+
audio = tf.convert_to_tensor(audio)
|
|
23
|
+
return tf.cond(
|
|
24
|
+
tf.shape(audio)[-1] < 2,
|
|
25
|
+
lambda: audio[:, :1],
|
|
26
|
+
lambda: audio[:, 1:2],
|
|
27
|
+
)
|
|
28
|
+
|
|
29
|
+
|
|
30
|
+
@register_audio_channel_strategy("keep")
|
|
31
|
+
def keep(audio: tf.Tensor) -> tf.Tensor:
|
|
32
|
+
return tf.convert_to_tensor(audio)
|
|
33
|
+
|
|
34
|
+
|
|
35
|
+
def apply_channel_strategy(audio: tf.Tensor, strategy: str) -> tf.Tensor:
|
|
36
|
+
if strategy == "mono_mean":
|
|
37
|
+
return mono_mean(audio)
|
|
38
|
+
if strategy == "mono_left":
|
|
39
|
+
return mono_left(audio)
|
|
40
|
+
if strategy == "mono_right":
|
|
41
|
+
return mono_right(audio)
|
|
42
|
+
if strategy == "keep":
|
|
43
|
+
return keep(audio)
|
|
44
|
+
raise ValueError(f"Unknown channel strategy: {strategy!r}")
|
|
45
|
+
|
|
46
|
+
|
|
47
|
+
__all__ = [
|
|
48
|
+
"apply_channel_strategy",
|
|
49
|
+
"keep",
|
|
50
|
+
"mono_left",
|
|
51
|
+
"mono_mean",
|
|
52
|
+
"mono_right",
|
|
53
|
+
]
|
|
@@ -0,0 +1,95 @@
|
|
|
1
|
+
from justdata.acoustic.compat.ast import (
|
|
2
|
+
AST_MIX_LABEL,
|
|
3
|
+
AST_MIX_LAMBDA,
|
|
4
|
+
AST_MIX_WAVEFORM,
|
|
5
|
+
AST_RECIPE_CONFIGS,
|
|
6
|
+
AST_REFERENCE_COMMIT,
|
|
7
|
+
ast_add_noise_and_roll,
|
|
8
|
+
ast_audioset_16k_10s_fbank128,
|
|
9
|
+
ast_esc50_16k_5s_fbank128,
|
|
10
|
+
ast_frequency_mask,
|
|
11
|
+
ast_frontend,
|
|
12
|
+
ast_mix_waveforms,
|
|
13
|
+
ast_normalize_fbank,
|
|
14
|
+
ast_pad_or_crop_fbank,
|
|
15
|
+
ast_pipeline,
|
|
16
|
+
ast_specaugment,
|
|
17
|
+
ast_speechcommands_16k_1s_fbank128,
|
|
18
|
+
ast_time_mask,
|
|
19
|
+
)
|
|
20
|
+
from justdata.acoustic.compat.ced import (
|
|
21
|
+
ced_base_16k_logmel64,
|
|
22
|
+
ced_frontend,
|
|
23
|
+
ced_mini_16k_logmel64,
|
|
24
|
+
ced_small_16k_logmel64,
|
|
25
|
+
ced_tiny_16k_logmel64,
|
|
26
|
+
dcase2025_task1_ced_16k_1s,
|
|
27
|
+
)
|
|
28
|
+
from justdata.acoustic.compat.efficientat import (
|
|
29
|
+
DCASE_CLASSES,
|
|
30
|
+
dcase2025_task1_dymn_32k_1s,
|
|
31
|
+
dcase2025_task1_efficientat_32k_1s,
|
|
32
|
+
dcase2025_task1_efficientat_32k_1s_repeat_to_10s,
|
|
33
|
+
dcase2025_task1_efficientat_32k_1s_zero_pad_to_10s,
|
|
34
|
+
dymn_32k_10s_logmel128,
|
|
35
|
+
efficientat_32k_10s_logmel128,
|
|
36
|
+
efficientat_frontend,
|
|
37
|
+
)
|
|
38
|
+
from justdata.acoustic.compat.panns import (
|
|
39
|
+
panns_cnn14_16k_10s_logmel64,
|
|
40
|
+
panns_cnn14_32k_10s_logmel64,
|
|
41
|
+
panns_frontend,
|
|
42
|
+
)
|
|
43
|
+
from justdata.acoustic.compat.passt import (
|
|
44
|
+
PATCH_GRID,
|
|
45
|
+
PATCHOUT,
|
|
46
|
+
dcase2025_task1_passt_32k_1s,
|
|
47
|
+
dcase2025_task1_passt_32k_1s_repeat_to_10s,
|
|
48
|
+
dcase2025_task1_passt_32k_1s_zero_pad_to_10s,
|
|
49
|
+
passt_32k_10s_logmel128,
|
|
50
|
+
passt_frontend,
|
|
51
|
+
)
|
|
52
|
+
|
|
53
|
+
__all__ = [
|
|
54
|
+
"AST_MIX_LABEL",
|
|
55
|
+
"AST_MIX_LAMBDA",
|
|
56
|
+
"AST_MIX_WAVEFORM",
|
|
57
|
+
"AST_RECIPE_CONFIGS",
|
|
58
|
+
"AST_REFERENCE_COMMIT",
|
|
59
|
+
"DCASE_CLASSES",
|
|
60
|
+
"PATCH_GRID",
|
|
61
|
+
"PATCHOUT",
|
|
62
|
+
"ast_add_noise_and_roll",
|
|
63
|
+
"ast_audioset_16k_10s_fbank128",
|
|
64
|
+
"ast_esc50_16k_5s_fbank128",
|
|
65
|
+
"ast_frequency_mask",
|
|
66
|
+
"ast_frontend",
|
|
67
|
+
"ast_mix_waveforms",
|
|
68
|
+
"ast_normalize_fbank",
|
|
69
|
+
"ast_pad_or_crop_fbank",
|
|
70
|
+
"ast_pipeline",
|
|
71
|
+
"ast_specaugment",
|
|
72
|
+
"ast_speechcommands_16k_1s_fbank128",
|
|
73
|
+
"ast_time_mask",
|
|
74
|
+
"ced_base_16k_logmel64",
|
|
75
|
+
"ced_frontend",
|
|
76
|
+
"ced_mini_16k_logmel64",
|
|
77
|
+
"ced_small_16k_logmel64",
|
|
78
|
+
"ced_tiny_16k_logmel64",
|
|
79
|
+
"dcase2025_task1_ced_16k_1s",
|
|
80
|
+
"dcase2025_task1_dymn_32k_1s",
|
|
81
|
+
"dcase2025_task1_efficientat_32k_1s",
|
|
82
|
+
"dcase2025_task1_efficientat_32k_1s_repeat_to_10s",
|
|
83
|
+
"dcase2025_task1_efficientat_32k_1s_zero_pad_to_10s",
|
|
84
|
+
"dcase2025_task1_passt_32k_1s",
|
|
85
|
+
"dcase2025_task1_passt_32k_1s_repeat_to_10s",
|
|
86
|
+
"dcase2025_task1_passt_32k_1s_zero_pad_to_10s",
|
|
87
|
+
"dymn_32k_10s_logmel128",
|
|
88
|
+
"efficientat_32k_10s_logmel128",
|
|
89
|
+
"efficientat_frontend",
|
|
90
|
+
"panns_cnn14_16k_10s_logmel64",
|
|
91
|
+
"panns_cnn14_32k_10s_logmel64",
|
|
92
|
+
"panns_frontend",
|
|
93
|
+
"passt_32k_10s_logmel128",
|
|
94
|
+
"passt_frontend",
|
|
95
|
+
]
|