renaming to naive - updating readme

hearbenchmark · Jul 9, 2021 · 8c526f6 · 8c526f6
1 parent 917dc93
commit 8c526f6
Show file tree

Hide file tree

Showing 5 changed files with 14 additions and 4 deletions.
diff --git a/README.md b/README.md
@@ -2,7 +2,7 @@
 # HEAR 2021 Baseline
 
 A simple DSP-based audio embedding consisting of a Mel-frequency spectrogram followed
-by a random projection. Serves as the baseline model for the HEAR 2021 and implements
+by a random projection. Serves as the naive baseline model for the HEAR 2021 and implements
 the [common API](https://neuralaudio.ai/hear2021-holistic-evaluation-of-audio-representations.html#common-api)
 required by the competition evaluation.
 
@@ -26,6 +26,16 @@ git clone https://github.com/neuralaudio/hear-baseline.git
 python3 -m pip install ./hear-baseline
 ```
 
+### Naive Baseline Model
+The naive baseline model produces log-scaled Mel-frequency spectrograms using a
+256-band Mel filter. Each frame of the spectrogram is then projected to 4096
+dimensions using a random projection matrix. Weights for the projection matrix were
+generated by sampling a normal distribution and are stored in this repository in the
+file `saved_models/naive_baseline.pt`.
+
+Using a random projection is less efficient
+than a CNN but is one of the simplest models to implement from a coding perspective.
+
 ### Usage
 
 Audio embeddings can be computed using one of two methods: 1)
@@ -38,7 +48,7 @@ import torch
 import hearbaseline
 
 # Load model with weights - located in the root directory of this repo
-model = hearbaseline.load_model("./baseline_weights.pt")
+model = hearbaseline.load_model("saved_models/naive_baseline.pt")
 
 # Create a batch of 2 white noise clips that are 2-seconds long
 # and compute scene embeddings for each clip

diff --git a/hearbaseline/__init__.py b/hearbaseline/__init__.py
@@ -1 +1 @@
-from .baseline import load_model, get_scene_embeddings, get_timestamp_embeddings
+from .naive import load_model, get_scene_embeddings, get_timestamp_embeddings
diff --git a/hearbaseline/baseline.py → hearbaseline/naive.py b/hearbaseline/baseline.py → hearbaseline/naive.py
diff --git a/baseline_weights.pt → saved_models/naive_baseline.pt b/baseline_weights.pt → saved_models/naive_baseline.pt
diff --git a/tests/test_baseline.py b/tests/test_baseline.py
@@ -10,7 +10,7 @@
     get_timestamp_embeddings,
 )
 from hearbaseline.util import frame_audio
-import hearbaseline.baseline as baseline
+import hearbaseline.naive as baseline
 
 
 torch.backends.cudnn.deterministic = True
Original file line number	Diff line number	Diff line change
		@@ -1 +1 @@
		from .baseline import load_model, get_scene_embeddings, get_timestamp_embeddings
		from .naive import load_model, get_scene_embeddings, get_timestamp_embeddings