diff --git a/README.md b/README.md
index f44928fe9c3a84e7f49eb76bbb12d285fee0f354..2e52430e3aec78f0e3632fd3147f1a9b01b15868 100644
--- a/README.md
+++ b/README.md
@@ -9,16 +9,24 @@ This project heavily depends on the [`TaggingBackends`](https://gitlab.pasteur.f
MaggotUBA is an autoencoder trained on randomly sampled 20-time-step time segments drawn from the t5 and t15 databases, with a computational budget of 1000 training epochs.
In its original "unsupervised" or self-supervised form, it reconstructs series of spines from a compressed latent representation.
-For the automatic tagging, the encoder is extracted and a classifier is stacked atop the encoder.
-On the same dataset, the combined encoder and classifier are (re-)trained to predict discrete behaviors.
+For the automatic tagging, the encoder is combined with a classifier.
+On the same dataset, the combined encoder-classifier are (re-)trained to predict discrete behaviors.
-## Prototypes and validated taggers
+## Taggers
+
+### 6-behavior classification task
+
+*6-behavior* refers to *run*, *cast*, *back*, *hunch*, *roll* and *stop_large*.
+
+#### `20220418`
As a first prototype, the [`20220418`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/tree/20220418) trained model is based on a simple random forest classifier, and only the classifier was trained; the encoder was not retrained.
See module [`maggotuba.models.randomforest`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/20220418/src/maggotuba/models/randomforest.py).
It was trained on the entire t5+t15 database. No interpolation was performed and the prototype does not properly handle data with different frame rates.
+#### `20221005` and `20221005-1`
+
A second tagger called [`20221005`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/tree/20221005) involves a classifier with dense layers, and the encoder was fine-tuned while training the combined encoder+classifier.
See modules [`maggotuba.models.trainers`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/20221005/src/maggotuba/models/trainers.py) and [`maggotuba.models.modules`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/20221005/src/maggotuba/models/modules.py).
@@ -26,6 +34,28 @@ This second tagger was dimensioned following a [parametric exploration for the 6
It was trained on a subset of 5000 files from the t5 and t15 databases. Spines were/are linearly interpolated at 10 Hz in each time segment individually.
+The `20221005-1` tagger is identical. It was first thought to implement a post-prediction correction step referred to as *ABA -> AAA*, but actually did not.
+
+#### `20221228`
+
+This tagger combines 25 taggers based on a 1.5-s time window and 25 taggers based on a 3-s time window, and uses a voting approach (or bagging).
+All simple taggers featured 25 latent dimensions and 1 dense layer (as classifier) only, following another [parametric exploration for the 6-behavior classification task](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/design/notebooks/parametric_exploration_6-behavior_classification_2.ipynb).
+
+This complex tagger was not distributed in any `latest` Docker image. See experimental image [0.7.2-20221228](https://hub.docker.com/layers/flaur/larvatagger/0.7.2-20221228/images/sha256-bac83d7ec499da9e868af893b58f8dd7b75317e0b16d99b1dcc1d456aac3c8a0?context=explore).
+
+It runs 50 times slower and does not solve any of the issues of `20221005`.
+
+### 7-behavior classification task
+
+*7-behavior* refers to *run_large*, *cast_large*, *back_large*, *hunch_large*, *roll_large*, *stop_large* and *small_motion*.
+
+#### `20230111`
+
+As a stronger default tagger, the `small_motion` was reintroduced to lower the detection rate of hunches and rolls.
+
+The `20230111` tagger uses a 2-s time window, features 25 latent dimensions and a single dense layer as classifier.
+It applies a post-prediction rule referred to as *ABC -> AAC* that consists in correcting all single-step actions with the previous action.
+
## Usage
For installation, see [TaggingBackends' README](https://gitlab.pasteur.fr/nyx/TaggingBackends/-/tree/dev#recommended-installation).
@@ -36,25 +66,30 @@ All the [command arguments supported by `TaggingBackends`](https://gitlab.pasteu
### Automatic tagging
-Using the [`20221005`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/tree/20221005) branch, the `20221005` tagger can be called on a supported tracking data file with:
+Using the [`20230111`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/tree/20230111) branch, the `20230111` tagger can be called on a supported tracking data file with:
```
-poetry run tagging-backend predict --model-instance 20221005 --skip-make-dataset
+poetry run tagging-backend predict --model-instance 20230111 --skip-make-dataset
```
The `--skip-make-dataset` option is optional. It only makes *tagging-backend* slightly faster.
-For the above command to work, the track data file must be placed (*e.g.* copied) in the `data/raw/20221005` directory, to be first created or cleared.
+For the above command to work, the track data file must be placed (*e.g.* copied) in the `data/raw/20230111` directory, to be first created or cleared.
-The resulting label file can be found as *data/processed/20221005/predicted.label*.
+The resulting label file can be found as *data/processed/20230111/predicted.label*.
Like all *.label* files, this file should be stored as a sibling of the corresponding track data file (in the same directory).
-Similarly, with an arbitrary tagger named, say *mytagger*, in the above explanation all occurences of `20221005` or *20221005* must be replaced by the tagger's name.
+Similarly, with an arbitrary tagger named, say *mytagger*, in the above explanation all occurences of `20230111` or *20230111* must be replaced by the tagger's name.
For example, the input data file would go into *data/raw/mytagger*.
+#### On HPC clusters
+
+Simultaneously tagging multiple tracking data files result in file conflicts because the same data directories are used internally.
+Use the *larvatagger.jl* script of the [LarvaTagger.jl](https://gitlab.pasteur.fr/nyx/larvatagger.jl) project instead, with argument `--data-isolation`.
+
### Retraining a tagger
-A new model instance can be trained on a data repository, using the `main` or `dev` branch of `MaggotUBA-adapter` (the `20221005` branch is also suitable) with:
+A new model instance can be trained on a data repository with:
```
poetry run tagging-backend train --model-instance <tagger-name>
@@ -64,7 +99,11 @@ Similarly to the *predict* command, for this one to work, the data repository mu
The above command will first load a pretrained model (`pretrained_models/default` in `MaggotUBA-adapter`) to determine additional parameters, such as whether to interpolate the spines or not and at which frequency, or the window length.
-The current default pretrained model involves linearly interpolating the spines at 10 Hz, and relies on a 20-time-step window (2 seconds). The dimensionality of the latent space is 100.
+Beware that the default pretrained model may depend on the branch you are on.
+
+The default pretrained model in the *20221005* branch involves linearly interpolating the spines at 10 Hz, and relies on a 20-time-step window (2 seconds). The dimensionality of the latent space is 100.
+
+The default pretrained model in the *20230111* branch similarly interpolates spines at 10 Hz and relies on a 20-time-step window (2 seconds), but features 25 latent dimensions only.
Alternative pretrained models can be specified using the `--pretrained-model-instance` option.
@@ -72,9 +111,9 @@ The data files are discovered in the repository (more exactly in *data/raw/\<tag
A subset of tags can be specified using the `--labels` option followed by a list of comma-separated tags.
A two-level balancing rule is followed to randomly select time segments and thus form a training dataset in the shape of a *larva_dataset* hdf5 file.
-See also the [`make_dataset.py`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/20221005/src/maggotuba/data/make_dataset.py) script.
+See also the [`make_dataset.py`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/dev/src/maggotuba/data/make_dataset.py) script.
Training operates in two steps, first pretraining the dense-layer classifier, second simultaneously fine-tuning the encoder and classifier.
-See also the [`train_model.py`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/20221005/src/maggotuba/models/train_model.py) script.
+See also the [`train_model.py`](https://gitlab.pasteur.fr/nyx/MaggotUBA-adapter/-/blob/dev/src/maggotuba/models/train_model.py) script.
This generates a new sub-directory in the `models` directory of the `MaggotUBA-adapter` project, which makes the trained model discoverable for automatic tagging (*predict* command).
diff --git a/pretrained_models/default/autoencoder_config.json b/pretrained_models/default/autoencoder_config.json
index 2b55fb459c9b2f87c33c78442f86d6cd311efe5a..c91c44c77c558c21237a770fc95890387b944cf9 100644
--- a/pretrained_models/default/autoencoder_config.json
+++ b/pretrained_models/default/autoencoder_config.json
@@ -1,17 +1,17 @@
{
- "project_dir": "subset2_interp10_len20",
+ "project_dir": "",
"seed": 100,
- "exp_name": "latent-100",
- "data_dir": "subset2_interp10_len20/larva_dataset_2022_10_05_20_20_100000.hdf5",
- "raw_data_dir": "larva_dataset/t5-t15-subset2",
- "log_dir": "subset2_interp10_len20/training_log/latent-100",
- "exp_folder": "subset2_interp10_len20/training_log/latent-100",
- "config": "subset2_interp10_len20/config-100.json",
+ "exp_name": "20230111",
+ "data_dir": "/pasteur/appa/scratch/flaurent/MaggotUBA-adapter/data/20230111/pretrain/20/1/larva_dataset_2023_01_12_20_20_100000.hdf5",
+ "raw_data_dir": "/pasteur/zeus/projets/p02/hecatonchire/screens",
+ "log_dir": "",
+ "exp_folder": "",
+ "config": "models/20230111/autoencoder_config.json",
"num_workers": 4,
"n_features": 10,
"len_traj": 20,
"len_pred": 20,
- "dim_latent": 100,
+ "dim_latent": 25,
"activation": "relu",
"enc_filters": [
128,
diff --git a/pretrained_models/default/best_validated_encoder.pt b/pretrained_models/default/best_validated_encoder.pt
index bd684ae54a3e7dfc504cfc709609d6bec80fe9ac..2eeea93eb9f5c2329726db457e6182260d9bd66a 100644
Binary files a/pretrained_models/default/best_validated_encoder.pt and b/pretrained_models/default/best_validated_encoder.pt differ
diff --git a/pyproject.toml b/pyproject.toml
index 63190e6f33740abb6cc0ca42c9669bf16aece0e6..53777e20537530cd2cc236d0077940209e2fd3a3 100644
--- a/pyproject.toml
+++ b/pyproject.toml
@@ -1,6 +1,6 @@
[tool.poetry]
name = "MaggotUBA-adapter"
-version = "0.8"
+version = "0.9"
description = "Interface between MaggotUBA and the Nyx tagging UI"
authors = ["François Laurent"]
license = "MIT"
diff --git a/src/maggotuba/models/predict_model.py b/src/maggotuba/models/predict_model.py
index c1abd548e048cd4b73d07b6d9c9f2a1f45a15da0..12c5507ea7326a2906bf5de3b0666b9c392487ab 100644
--- a/src/maggotuba/models/predict_model.py
+++ b/src/maggotuba/models/predict_model.py
@@ -175,8 +175,13 @@ def apply_filters(labels, post_filters):
# modify sequentially
for k in range(1, len(labels)-1):
label = labels[k-1]
- if labels[k-1] != label and label == labels[k+1]:
+ if labels[k] != label and label == labels[k+1]:
labels[k] = label
+ elif post_filter == 'ABC->AAC':
+ # modify sequentially
+ for k in range(1, len(labels)-1):
+ if labels[k-1] != labels[k] and labels[k] != labels[k+1]:
+ labels[k] = labels[k-1]
else:
raise ValueError(f"filter not supported: {post_filter}")
return labels