DEV: Initial AVA implementation review

.gitignore

@@ -3,6 +3,7 @@
 
 # IDE
 .idea
+.vscode
 
 # Jupyter
 .ipynb_checkpoints/
@@ -26,4 +27,7 @@ tests/data_for_tests/generated/
 
 # coverage / pytest-cov
 .coverage
-coverage.xml
+coverage.xml
+
+#nox 
+.nox/

.vscode/settings.json

@@ -0,0 +1,6 @@
+{
+    "[python]": {
+        "editor.defaultFormatter": "ms-python.autopep8"
+    },
+    "python.formatting.provider": "none"
+}

src/scripts/test_vae.ipynb

@@ -0,0 +1,49 @@
+{
+ "cells": [
+  {
+   "cell_type": "code",
+   "execution_count": 2,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "from src.vak.nets.ava import Ava\n",
+    "import torch"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": 8,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "x_shape = (3, 128, 512)\n",
+    "input = torch.zeros(x_shape)\n",
+    "net = Ava(x_shape=(x_shape[1], x_shape[2]))\n",
+    "output, _ = net.forward(input)\n",
+    "assert output.shape == x_shape, 'Error'"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "Python 3",
+   "language": "python",
+   "name": "python3"
+  },
+  "language_info": {
+   "codemirror_mode": {
+    "name": "ipython",
+    "version": 3
+   },
+   "file_extension": ".py",
+   "mimetype": "text/x-python",
+   "name": "python",
+   "nbconvert_exporter": "python",
+   "pygments_lexer": "ipython3",
+   "version": "3.10.13"
+  },
+  "orig_nbformat": 4
+ },
+ "nbformat": 4,
+ "nbformat_minor": 2
+}

src/vak/cli/prep.py

@@ -139,6 +139,9 @@ def prep(toml_path):
         test_dur=cfg.prep.test_dur,
         train_set_durs=cfg.prep.train_set_durs,
         num_replicates=cfg.prep.num_replicates,
+        context_s=cfg.prep.context_s,
+        max_dur=cfg.prep.max_dur,
+        target_shape=cfg.prep.target_shape,
     )
 
     # use config and section from above to add dataset_path to config.toml file

src/vak/config/prep.py

@@ -25,7 +25,7 @@ def is_valid_duration(instance, attribute, value):
     """validator for dataset split durations"""
     if type(value) not in {int, float}:
         raise TypeError(
-            f"invalid type for {attribute} of {instance}: {type(value)}. Type should be float or int."
+            f"invalid type for {attribute.name} of {instance}: {type(value)}. Type should be float or int."
         )
 
     if value == -1:  # specifies "use the remainder of the dataset"
@@ -34,7 +34,7 @@ def is_valid_duration(instance, attribute, value):
 
     if not value >= 0:
         raise ValueError(
-            f"value specified for {attribute} of {instance} must be greater than or equal to zero, was {value}"
+            f"value specified for {attribute.name} of {instance} must be greater than or equal to zero, was {value}"
         )
 
 
@@ -60,6 +60,25 @@ def are_valid_dask_bag_kwargs(instance, attribute, value):
         )
 
 
+def is_valid_target_shape(instance, attribute, value):
+    """validator for target shape"""
+    if not isinstance(value, (tuple, list)):
+        raise TypeError(
+            f"invalid type for {attribute.name} of {instance}: {type(value)}. Type should be tuple or list."
+        )
+
+    if not all([isinstance(val, int) for val in value]):
+        raise ValueError(
+            f"All values in {attribute.name} of {instance} should be integers"
+        )
+
+    if not len(value) == 2:
+        raise ValueError(
+            f"{attribute.name} of {instance} should have length 2: "
+            f"(number of frequency bins, number of time bins). "
+            f"Length was: {len(value)}"
+        )
+
 @attr.s
 class PrepConfig:
     """class to represent [PREP] section of config.toml file
@@ -125,6 +144,31 @@ class PrepConfig:
         in a learning curve. Each replicate uses a different
         randomly drawn subset of the training data (but of the same duration).
         Default is None. Required if config file has a learncurve section.
+    context_s : float
+        Number of seconds of "context" around a segment to
+        add, i.e., time before and after the onset
+        and offset respectively. Default is 0.005s,
+        5 milliseconds. This parameter is only used for
+        Parametric UMAP and segment-VAE datasets.
+    max_dur : float
+        Maximum duration for segments.
+        If a float value is specified,
+        any segment with a duration larger than
+        that value (in seconds) will be omitted
+        from the dataset. Default is None.
+        This parameter is only used for
+        vae-segment datasets.
+    target_shape : tuple
+        Of ints, (target number of frequency bins,
+        target number of time bins).
+        Spectrograms of units will be reshaped
+        by interpolation to have the specified
+        number of frequency and time bins.
+        The transformation is only applied if both this
+        parameter and ``max_dur`` are specified.
+        Default is None.
+        This parameter is only used for
+        vae-segment datasets.
     """
 
     data_dir = attr.ib(converter=expanded_user_path)
@@ -195,6 +239,30 @@ def is_valid_input_type(self, attribute, value):
         validator=validators.optional(instance_of(int)), default=None
     )
 
+    context_s = attr.ib(
+        default=0.005
+    )
+    @context_s.validator
+    def is_valid_context_s(self, attribute, value):
+        if not isinstance(value, float):
+            raise TypeError(
+                f"Value for {attribute.name} should be float but type was: {type(value)}"
+            )
+        if not value >= 0.:
+            raise ValueError(
+                f"Value for {attribute.name} should be greater than or equal to 0., "
+                f"but was: {value}"
+            )
+
+    max_dur = attr.ib(
+        validator=validators.optional(instance_of(float)), default=None
+    )
+    target_shape = attr.ib(
+        converter=converters.optional(tuple),
+        validator=validators.optional(is_valid_target_shape),
+        default=None
+    )
+
     def __attrs_post_init__(self):
         if self.audio_format is not None and self.spect_format is not None:
             raise ValueError("cannot specify audio_format and spect_format")

src/vak/config/spect_params.py

@@ -15,7 +15,9 @@ def freq_cutoffs_validator(instance, attribute, value):
         )
 
 
-VALID_TRANSFORM_TYPES = {"log_spect", "log_spect_plus_one"}
+VALID_TRANSFORM_TYPES = {
+    "log", "log_spect", "log_spect_plus_one"
+}
 
 
 def is_valid_transform_type(instance, attribute, value):
@@ -57,6 +59,24 @@ class SpectParamsConfig:
     audio_path_key : str
         key for accessing path to source audio file for spectogram in files.
         Default is 'audio_path'.
+    min_val : float, optional
+        Minimum value to allow in spectrogram.
+        All values less than this will be set to this value.
+        This operation is applied *after* the transform
+        specified by ``transform_type``.
+        Default is None.
+    max_val : float, optional
+        Maximum value to allow in spectrogram.
+        All values greater than this will be set to this value.
+        This operation is applied *after* the transform
+        specified by ``transform_type``.
+        Default is None.
+    normalize : bool
+        If True, min-max normalize the spectrogram.
+        Normalization is done *after* the transform
+        specified by ``transform_type``, and *after*
+        the ``min_val`` and ``max_val`` operations.
+        Default is False.
     """
 
     fft_size = attr.ib(converter=int, validator=instance_of(int), default=512)
@@ -79,3 +99,16 @@ class SpectParamsConfig:
     freqbins_key = attr.ib(validator=instance_of(str), default="f")
     timebins_key = attr.ib(validator=instance_of(str), default="t")
     audio_path_key = attr.ib(validator=instance_of(str), default="audio_path")
+    min_val = attr.ib(
+        validator=validators.optional(instance_of(float)),
+        default=None
+    )
+    max_val = attr.ib(
+        validator=validators.optional(instance_of(float)),
+        default=None
+    )
+    normalize = attr.ib(
+        validator=instance_of(bool),
+        default=False,
+    )
+

src/vak/config/valid.toml

@@ -21,6 +21,9 @@ val_dur = 15
 test_dur = 30
 train_set_durs = [ 4.5, 6.0 ]
 num_replicates = 2
+context_s = 0.005
+max_dur = 0.2
+target_shape = [128, 128]
 
 [SPECT_PARAMS]
 fft_size = 512
@@ -32,6 +35,9 @@ spect_key = 's'
 freqbins_key = 'f'
 timebins_key = 't'
 audio_path_key = 'audio_path'
+min_val = -6.0
+max_val = 0.0
+normalize = true
 
 [TRAIN]
 model = 'TweetyNet'

src/vak/datasets/__init__.py

@@ -1,3 +1,3 @@
-from . import frame_classification, parametric_umap
+from . import frame_classification, parametric_umap, vae
 
-__all__ = ["frame_classification", "parametric_umap"]
+__all__ = ["frame_classification", "parametric_umap", "vae"]