code-loader 1.0.199__tar.gz → 1.0.201.dev0__tar.gz

{code_loader-1.0.199 → code_loader-1.0.201.dev0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: code-loader
-Version: 1.0.199
+Version: 1.0.201.dev0
 Summary: 
 Home-page: https://github.com/tensorleap/code-loader
 License: MIT

{code_loader-1.0.199 → code_loader-1.0.201.dev0}/code_loader/contract/datasetclasses.py

@@ -8,7 +8,7 @@ import numpy.typing as npt
 from code_loader.contract.enums import DataStateType, DataStateEnum, LeapDataType, ConfusionMatrixValue, \
     MetricDirection, DatasetMetadataType
 from code_loader.contract.visualizer_classes import LeapImage, LeapText, LeapGraph, LeapHorizontalBar, \
-    LeapTextMask, LeapImageMask, LeapImageWithBBox, LeapImageWithHeatmap, LeapVideo
+    LeapTextMask, LeapImageMask, LeapImageWithBBox, LeapImageWithHeatmap, LeapVideo, LeapAudio
 from code_loader.contract.sim_config import SimConfig
 
 custom_latent_space_attribute = "custom_latent_space"
@@ -194,11 +194,12 @@ VisualizerCallableInterface = Union[
     Callable[..., LeapImageMask],
     Callable[..., LeapTextMask],
     Callable[..., LeapImageWithBBox],
-    Callable[..., LeapImageWithHeatmap]
+    Callable[..., LeapImageWithHeatmap],
+    Callable[..., LeapAudio]
 ]
 
 LeapData = Union[LeapImage, LeapText, LeapGraph, LeapHorizontalBar, LeapImageMask, LeapTextMask, LeapImageWithBBox,
-LeapImageWithHeatmap, LeapVideo]
+LeapImageWithHeatmap, LeapVideo, LeapAudio]
 
 CustomCallableInterface = Callable[..., Any]
 

{code_loader-1.0.199 → code_loader-1.0.201.dev0}/code_loader/contract/visualizer_classes.py

@@ -357,16 +357,14 @@ class LeapAudio:
         should be mixed down before constructing LeapAudio.
     sample_rate (int): Samples per second — needed to encode the clip and to map
         the playhead position to time.
-    visual (Union[LeapImage, LeapGraph]): The thing you look at.
-    x_range (Optional[Tuple[float, float]]): Time extent (in seconds) that the
-        visual's horizontal axis spans, used to align the tick. Defaults to
-        (0, N / sample_rate).
+    visual (Union[LeapImage, LeapGraph]): The thing you look at. For a waveform
+        the nested LeapGraph carries its own x_range (time span); the playhead is
+        driven by the audio element's currentTime, so no time range is needed here.
     type (LeapDataType): The data type, default is LeapDataType.Audio.
     """
     audio: npt.NDArray
     sample_rate: int
     visual: Union[LeapImage, LeapGraph]
-    x_range: Optional[Tuple[float, float]] = None
     type: LeapDataType = LeapDataType.Audio
 
     def __post_init__(self) -> None:
@@ -377,11 +375,6 @@ class LeapAudio:
                       'Audio visual must be a LeapImage (spectrogram) or LeapGraph (waveform)')
         if not isinstance(self.sample_rate, int) or self.sample_rate <= 0:
             raise LeapValidationError(f'sample_rate must be a positive int, got {self.sample_rate}')
-        if self.x_range is not None:
-            if len(self.x_range) != 2:
-                raise LeapValidationError('x_range must be a tuple of length 2')
-            validate_type(type(self.x_range[0]), [float, int], 'x_range must be a tuple of floats or integers')
-            validate_type(type(self.x_range[1]), [float, int], 'x_range must be a tuple of floats or integers')
 
 
 map_leap_data_type_to_visualizer_class = {

{code_loader-1.0.199 → code_loader-1.0.201.dev0}/code_loader/visualizers/default_visualizers.py

@@ -31,7 +31,6 @@ def default_video_visualizer(data: npt.NDArray[np.float32]) -> LeapVideo:
 
 
 _MAX_WAVEFORM_POINTS = 2000
-_VISUAL_KINDS = ('waveform', 'spectrogram', 'image')
 
 
 def _to_mono(audio: npt.NDArray) -> npt.NDArray:
@@ -54,49 +53,43 @@ def _waveform_graph(series: npt.NDArray, duration: float) -> LeapGraph:
 def default_audio_visualizer(audio: npt.NDArray,
                              sample_rate: int,
                              visual: Optional[npt.NDArray] = None,
-                             visual_kind: Optional[str] = None,
                              time_axis_index: int = -1) -> LeapAudio:
     """Package a playable audio sample plus the visual a playhead runs through.
 
     audio: waveform samples (mono [N], or multi-channel that is mixed down).
     sample_rate: samples per second.
-    visual: the array to display. For 'waveform' a 1-D series; for 'spectrogram'
-        a raw 2-D [freq, time] (or [time, freq]) array to be rendered grayscale;
-        for 'image' an already-rendered [H, W, 1] or [H, W, 3] image (e.g. a
-        spectrogram the caller already ran through their own colormap).
+    visual: the array to display; its kind is deduced from its shape.
+        1-D [N]        -> waveform graph of the samples.
+        2-D [H, W]     -> spectrogram, rendered grayscale.
+        3-D [H, W, C]  -> already-rendered image; C must be 3 (rgb) or 1 (grayscale).
         If omitted, a waveform graph is built from `audio` itself.
-    visual_kind: 'waveform', 'spectrogram', or 'image'. The caller states this
-        explicitly; the shape of `visual` is never inspected to guess it.
-        Required when `visual` is given; ignored when `visual` is omitted.
-    time_axis_index: for 'spectrogram', which axis of `visual` is time (moved to columns).
-        Unused for 'waveform'/'image'.
+    time_axis_index: for a spectrogram, which axis of `visual` is time (moved to columns).
+        Unused otherwise.
     """
     mono = _to_mono(audio)
     duration = mono.shape[0] / float(sample_rate)
-    x_range = (0.0, duration)
 
     if visual is None:  # no visual given: show the raw signal as a waveform
-        return LeapAudio(mono, sample_rate, _waveform_graph(mono, duration), x_range)
-
-    if visual_kind not in _VISUAL_KINDS:
-        raise ValueError(f"visual_kind must be one of {_VISUAL_KINDS}, got {visual_kind!r}")
+        return LeapAudio(mono, sample_rate, _waveform_graph(mono, duration))
 
     v = np.asarray(visual)
 
-    if visual_kind == 'waveform':
-        return LeapAudio(mono, sample_rate, _waveform_graph(v, duration), x_range)
+    if v.ndim == 1:  # waveform
+        return LeapAudio(mono, sample_rate, _waveform_graph(v, duration))
+
+    if v.ndim == 3:  # already-rendered image
+        if v.shape[-1] not in (1, 3):
+            raise ValueError(f'image visual must have 1 (grayscale) or 3 (rgb) channels, got shape {v.shape}')
+        return LeapAudio(mono, sample_rate, LeapImage(v))
 
-    if visual_kind == 'image':
-        return LeapAudio(mono, sample_rate, LeapImage(v), x_range)
+    if v.ndim == 2:  # spectrogram
+        spec = v
+        if time_axis_index % 2 == 0:  # move time onto the horizontal axis (columns)
+            spec = spec.T
+        img = rescale_min_max(spec.astype(np.float32))[..., None]  # [freq, time, 1]
+        return LeapAudio(mono, sample_rate, LeapImage(img))
 
-    # spectrogram
-    spec = np.squeeze(v)
-    if spec.ndim != 2:
-        raise ValueError(f'spectrogram visual must be 2-D (freq x time), got shape {v.shape}')
-    if time_axis_index % spec.ndim == 0:  # move time onto the horizontal axis (columns)
-        spec = spec.T
-    img = rescale_min_max(spec.astype(np.float32))[..., None]  # [freq, time, 1]
-    return LeapAudio(mono, sample_rate, LeapImage(img), x_range)
+    raise ValueError(f'visual must be 1-D, 2-D, or 3-D, got shape {v.shape}')
 
 
 def default_graph_visualizer(data: npt.NDArray[np.float32]) -> LeapGraph:

{code_loader-1.0.199 → code_loader-1.0.201.dev0}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "code-loader"
-version = "1.0.199"
+version = "1.0.201.dev0"
 description = ""
 authors = ["dorhar <doron.harnoy@tensorleap.ai>"]
 license = "MIT"