bplusplus 1.2.1__tar.gz → 1.2.3__tar.gz

bplusplus-1.2.3/PKG-INFO

@@ -0,0 +1,101 @@
+Metadata-Version: 2.3
+Name: bplusplus
+Version: 1.2.3
+Summary: A simple method to create AI models for biodiversity, with collect and prepare pipeline
+License: MIT
+Author: Titus Venverloo
+Author-email: tvenver@mit.edu
+Requires-Python: >=3.9.0,<4.0.0
+Classifier: License :: OSI Approved :: MIT License
+Classifier: Programming Language :: Python :: 3
+Classifier: Programming Language :: Python :: 3.9
+Classifier: Programming Language :: Python :: 3.10
+Classifier: Programming Language :: Python :: 3.11
+Classifier: Programming Language :: Python :: 3.12
+Classifier: Programming Language :: Python :: 3.13
+Requires-Dist: numpy
+Requires-Dist: pandas (==2.1.4)
+Requires-Dist: pillow
+Requires-Dist: prettytable (==3.7.0)
+Requires-Dist: pygbif (>=0.6.4,<0.7.0)
+Requires-Dist: pyyaml (==6.0.1)
+Requires-Dist: requests (==2.25.1)
+Requires-Dist: scikit-learn
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: torch (>=2.5.0,<3.0.0)
+Requires-Dist: torchvision
+Requires-Dist: tqdm (==4.66.4)
+Requires-Dist: ultralytics (>=8.3.0)
+Requires-Dist: validators (>=0.33.0,<0.34.0)
+Description-Content-Type: text/markdown
+
+# Domain-Agnostic Insect Classification Pipeline
+
+This project provides a complete, end-to-end pipeline for building a custom insect classification system. The framework is designed to be **domain-agnostic**, allowing you to train a powerful detection and classification model for **any insect species** by simply providing a list of names.
+
+Using the `Bplusplus` library, this pipeline automates the entire machine learning workflow, from data collection to video inference.
+
+## Key Features
+
+- **Automated Data Collection**: Downloads hundreds of images for any species from the GBIF database.
+- **Intelligent Data Preparation**: Uses a pre-trained model to automatically find, crop, and resize insects from raw images, ensuring high-quality training data.
+- **Hierarchical Classification**: Trains a model to identify insects at three taxonomic levels: **family, genus, and species**.
+- **Video Inference & Tracking**: Processes video files to detect, classify, and track individual insects over time, providing aggregated predictions.
+## Pipeline Overview
+
+The process is broken down into six main steps, all detailed in the `full_pipeline.ipynb` notebook:
+
+1.  **Collect Data**: Select your target species and fetch raw insect images from the web.
+2.  **Prepare Data**: Filter, clean, and prepare images for training.
+3.  **Train Model**: Train the hierarchical classification model.
+4.  **Download Weights**: Fetch pre-trained weights for the detection model.
+5.  **Test Model**: Evaluate the performance of the trained model.
+6.  **Run Inference**: Run the full pipeline on a video file for real-world application.
+
+## How to Use
+
+### Prerequisites
+
+- Python 3.8+
+- `venv` for creating a virtual environment (recommended)
+
+### Setup
+
+1.  **Create and activate a virtual environment:**
+    ```bash
+    python3 -m venv venv
+    source venv/bin/activate
+    ```
+
+2.  **Install the required packages:**
+    ```bash
+    pip install bplusplus
+    ```
+
+### Running the Pipeline
+
+The entire workflow is contained within **`full_pipeline.ipynb`**. Open it with a Jupyter Notebook or JupyterLab environment and run the cells sequentially to execute the full pipeline.
+
+### Customization
+
+To train the model on different insect species, simply modify the `names` list in **Step 1** of the notebook:
+
+```python
+# a/full_pipeline.ipynb
+
+# To use your own species, change the names in this list
+names = [
+    "Vespa crabro", "Vespula vulgaris", "Dolichovespula media"
+]
+```
+
+The pipeline will automatically handle the rest, from data collection to training, for your new set of species.
+
+## Directory Structure
+
+The pipeline will create the following directories to store artifacts:
+
+- `GBIF_data/`: Stores the raw images downloaded from GBIF.
+- `prepared_data/`: Contains the cleaned, cropped, and resized images ready for training.
+- `trained_model/`: Saves the trained model weights (`best_multitask.pt`) and pre-trained detection weights.
+

bplusplus-1.2.3/README.md

@@ -0,0 +1,69 @@
+# Domain-Agnostic Insect Classification Pipeline
+
+This project provides a complete, end-to-end pipeline for building a custom insect classification system. The framework is designed to be **domain-agnostic**, allowing you to train a powerful detection and classification model for **any insect species** by simply providing a list of names.
+
+Using the `Bplusplus` library, this pipeline automates the entire machine learning workflow, from data collection to video inference.
+
+## Key Features
+
+- **Automated Data Collection**: Downloads hundreds of images for any species from the GBIF database.
+- **Intelligent Data Preparation**: Uses a pre-trained model to automatically find, crop, and resize insects from raw images, ensuring high-quality training data.
+- **Hierarchical Classification**: Trains a model to identify insects at three taxonomic levels: **family, genus, and species**.
+- **Video Inference & Tracking**: Processes video files to detect, classify, and track individual insects over time, providing aggregated predictions.
+## Pipeline Overview
+
+The process is broken down into six main steps, all detailed in the `full_pipeline.ipynb` notebook:
+
+1.  **Collect Data**: Select your target species and fetch raw insect images from the web.
+2.  **Prepare Data**: Filter, clean, and prepare images for training.
+3.  **Train Model**: Train the hierarchical classification model.
+4.  **Download Weights**: Fetch pre-trained weights for the detection model.
+5.  **Test Model**: Evaluate the performance of the trained model.
+6.  **Run Inference**: Run the full pipeline on a video file for real-world application.
+
+## How to Use
+
+### Prerequisites
+
+- Python 3.8+
+- `venv` for creating a virtual environment (recommended)
+
+### Setup
+
+1.  **Create and activate a virtual environment:**
+    ```bash
+    python3 -m venv venv
+    source venv/bin/activate
+    ```
+
+2.  **Install the required packages:**
+    ```bash
+    pip install bplusplus
+    ```
+
+### Running the Pipeline
+
+The entire workflow is contained within **`full_pipeline.ipynb`**. Open it with a Jupyter Notebook or JupyterLab environment and run the cells sequentially to execute the full pipeline.
+
+### Customization
+
+To train the model on different insect species, simply modify the `names` list in **Step 1** of the notebook:
+
+```python
+# a/full_pipeline.ipynb
+
+# To use your own species, change the names in this list
+names = [
+    "Vespa crabro", "Vespula vulgaris", "Dolichovespula media"
+]
+```
+
+The pipeline will automatically handle the rest, from data collection to training, for your new set of species.
+
+## Directory Structure
+
+The pipeline will create the following directories to store artifacts:
+
+- `GBIF_data/`: Stores the raw images downloaded from GBIF.
+- `prepared_data/`: Contains the cleaned, cropped, and resized images ready for training.
+- `trained_model/`: Saves the trained model weights (`best_multitask.pt`) and pre-trained detection weights.

{bplusplus-1.2.1 → bplusplus-1.2.3}/pyproject.toml

@@ -1,21 +1,27 @@
 [tool.poetry]
 name = "bplusplus"
-version = "1.2.1"
+version = "1.2.3"
 description = "A simple method to create AI models for biodiversity, with collect and prepare pipeline"
-authors = ["Titus Venverloo <tvenver@mit.edu>", "Deniz Aydemir <deniz@aydemir.us>", "Orlando Closs <orlando.closs@wur.nl>", "Ase Hatveit <aase@mit.edu>"]
+authors = ["Titus Venverloo <tvenver@mit.edu>", "Deniz Aydemir <deniz@aydemir.us>", "Orlando Closs <orlandocloss@pm.me>", "Ase Hatveit <aase@mit.edu>"]
 license = "MIT"
 readme = "README.md"
 
 [tool.poetry.dependencies]
 python = "^3.9.0"
 requests = "2.25.1"
-ultralytics = "8.0.195"
+pandas = "2.1.4"
+ultralytics = ">=8.3.0"
+pyyaml = "6.0.1"
+tqdm = "4.66.4"
+prettytable = "3.7.0"
+torch = "^2.5.0"
+torchvision = "*"
+pillow = "*"
+numpy = "*"
+scikit-learn = "*"
 pygbif = "^0.6.4"
 validators = "^0.33.0"
-prettytable = "3.7.0"
-scikit-learn = "^1.6.1"
 tabulate = "^0.9.0"
-torch = "2.5.0"
 
 [tool.poetry.group.dev.dependencies]
 jupyter = "^1.0.0"

bplusplus-1.2.3/src/bplusplus/__init__.py

@@ -0,0 +1,5 @@
+from .collect import Group, collect
+from .prepare import prepare
+from .train import train
+from .test import test
+from .inference import inference

{bplusplus-1.2.1 → bplusplus-1.2.3}/src/bplusplus/collect.py

@@ -114,6 +114,8 @@ def __next_batch(parameters: dict[str, Any], total_limit: int, offset: int, curr
         parameters["limit"] = total_limit
         parameters["offset"] = offset
         parameters["mediaType"] = ["StillImage"]
+        parameters["basisOfRecord"] = ["HUMAN_OBSERVATION", "LIVING_SPECIMEN", "MACHINE_OBSERVATION", "OBSERVATION", "OCCURRENCE"]
+        parameters["lifeStage"] = ["Adult"]
         search = pygbif.occurrences.search(**parameters)
         occurrences = search["results"]
         if search["endOfRecords"] or len(current) >= total_limit: