Releases: BirdVox/birdvoxdetect
0.5.0
This is the first stable release of the 0.5 series. The main change with respect to the v0.4 series is a modification of the flight call classification algorithm which enforces hierarchical consistency in the TaxoNet output. We now ensure that the predicted species belongs to the predicted family and that the predicted family belongs to the predicted order. Additionally, BirdVoxDetect now reports order confidence, family confidence, and species confidence in addition to detection confidence. More details below.
Our numerical experiments on 300 hours of annotated audio have demonstrated that TaxoNet outperforms the classifier of BirdVoxDetect v0.3 (see previous release notes for details). However, we have noted that the output of TaxoNet is occasionally inconsistent across levels. For example, the "family" level may return "Turdidae" (Thrushes) while the "species" level would return "WTSP", i.e. White-Throated Sparrow.
Although infrequent, this lack of consistency may be confusing to users. To address it, we have implemented a new algorithm for hierarchical classification which ensures consistency by design: see #73
The key idea is to query TaxoNet in a coarse-to-fine fashion, while progressively narrowing down the list of candidate species corresponding to the detected flight call. Thanks to Justin Salamon for proposing this elegant solution.
We have taken the opportunity of rewriting the classify_species function (see #73) to enrich the information that is stored in the BirdVoxDetect checklist. In addition to textual labels for order, family, and species, we have added three new columns, corresponding to "order confidence", "family confidence" , and "species confidence".
These values of confidence all range between 50% and 100% and provide insight on the prediction of TaxoNet. Users should be warned, however, that the percentages are not calibrated, and thus do not come with any probabilistic interpretation. Rather, they are simply the output values of the sigmoid units in TaxoNet. This is unlike "Detection confidence (%)", which is carefully calibrated to match the precision of the detector (on a precision-recall curve).
0.5.0b2
0.5.0b1
This is the first beta release of the 0.5 series.
The main change with respect to the v0.4 series is a modification of the flight call classification algorithm which enforces hierarchical consistency in the TaxoNet output. We now ensure that the predicted species belongs to the predicted family and that the predicted family belongs to the predicted order.
See #73 for a description of the algorithm
Additionally, BirdVoxDetect now reports order confidence, family confidence, and species confidence in addition to detection confidence.
0.5.0a4
0.5.0a3
0.5.0a2
0.5.0a1
0.5.0a0
This is the first alpha release of the 0.5 series
The main change with respect to the v0.4 series is a modification of the flight call classification algorithm which enforces hierarchical consistency in the TaxoNet output. We now ensure that the predicted species belongs to the predicted family and that the predicted family belongs to the predicted order.
See #73 for a description of the algorithm
Additionally, BirdVoxDetect now reports order confidence, family confidence, and species confidence in addition to detection confidence.
0.4.1
0.4.0
This is the first stable release of the 0.4 series. It is functionally identical to 0.4.0b2.
The main change with respect to the v0.3 series is the improved species classifier (TaxoNet). Furthermore, each detected event now contains predictions at coarser taxonomical levels (family and order) in addition to species.
The process_file function now supports a new keyword argument, predict_proba, defaulting to False. If set to true, BirdVoxDetect will export a JSON file containing probabilistic predictions for every species, family, and order in TaxoNet. The JSON file also contains a copy of the BirdVoxClassify taxonomy, a copy of the sensor fault log given by BIrdVoxActivate, and additional metadata: file name, audio duration, MD5 checksum, package versions, hardware specifications, and elapsed time.
We have provided a command-line interface for the predict-proba keyword argument, via the optional flag --predict-proba.