bplusplus 1.2.1__py3-none-any.whl → 1.2.3__py3-none-any.whl

bplusplus/{hierarchical/train.py → train.py}

@@ -14,7 +14,7 @@ import logging
 from tqdm import tqdm  
 import sys
 
-def train_multitask(batch_size=4, epochs=30, patience=3, img_size=640, data_dir='/mnt/nvme0n1p1/datasets/insect/bjerge-train2', output_dir='./output', species_list=None):
+def train(batch_size=4, epochs=30, patience=3, img_size=640, data_dir='input', output_dir='./output', species_list=None):
     """
     Main function to run the entire training pipeline.
     Sets up datasets, model, training process and handles errors.
@@ -144,17 +144,17 @@ def train_multitask(batch_size=4, epochs=30, patience=3, img_size=640, data_dir=
 def get_taxonomy(species_list):
     """
     Retrieves taxonomic information for a list of species from GBIF API.
-    Creates a hierarchical taxonomy dictionary with order, family, and species relationships.
+    Creates a hierarchical taxonomy dictionary with family, genus, and species relationships.
     """
     taxonomy = {1: [], 2: {}, 3: {}}
-    species_to_family = {}
-    family_to_order = {}
+    species_to_genus = {}
+    genus_to_family = {}
     
     logger.info(f"Building taxonomy from GBIF for {len(species_list)} species")
     
     print("\nTaxonomy Results:")
     print("-" * 80)
-    print(f"{'Species':<30} {'Order':<20} {'Family':<20} {'Status'}")
+    print(f"{'Species':<30} {'Family':<20} {'Genus':<20} {'Status'}")
     print("-" * 80)
     
     for species_name in species_list:
@@ -165,23 +165,23 @@ def get_taxonomy(species_list):
             
             if data.get('status') == 'ACCEPTED' or data.get('status') == 'SYNONYM':
                 family = data.get('family')
-                order = data.get('order')
+                genus = data.get('genus')
                 
-                if family and order:
+                if family and genus:
                     status = "OK"
                     
-                    print(f"{species_name:<30} {order:<20} {family:<20} {status}")
+                    print(f"{species_name:<30} {family:<20} {genus:<20} {status}")
                     
-                    species_to_family[species_name] = family
-                    family_to_order[family] = order
+                    species_to_genus[species_name] = genus
+                    genus_to_family[genus] = family
                     
-                    if order not in taxonomy[1]:
-                        taxonomy[1].append(order)
+                    if family not in taxonomy[1]:
+                        taxonomy[1].append(family)
                     
-                    taxonomy[2][family] = order
-                    taxonomy[3][species_name] = family
+                    taxonomy[2][genus] = family
+                    taxonomy[3][species_name] = genus
                 else:
-                    error_msg = f"Species '{species_name}' found in GBIF but family and order not found, could be spelling error in species, check GBIF"
+                    error_msg = f"Species '{species_name}' found in GBIF but family and genus not found, could be spelling error in species, check GBIF"
                     logger.error(error_msg)
                     print(f"{species_name:<30} {'Not found':<20} {'Not found':<20} ERROR")
                     print(f"Error: {error_msg}")
@@ -203,23 +203,23 @@ def get_taxonomy(species_list):
     taxonomy[1] = sorted(list(set(taxonomy[1])))
     print("-" * 80)
     
-    num_orders = len(taxonomy[1])
-    num_families = len(taxonomy[2])
+    num_families = len(taxonomy[1])
+    num_genera = len(taxonomy[2])
     num_species = len(taxonomy[3])
     
-    print("\nOrder indices:")
-    for i, order in enumerate(taxonomy[1]):
-        print(f"  {i}: {order}")
-    
     print("\nFamily indices:")
-    for i, family in enumerate(taxonomy[2].keys()):
+    for i, family in enumerate(taxonomy[1]):
         print(f"  {i}: {family}")
     
+    print("\nGenus indices:")
+    for i, genus in enumerate(taxonomy[2].keys()):
+        print(f"  {i}: {genus}")
+    
     print("\nSpecies indices:")
     for i, species in enumerate(species_list):
         print(f"  {i}: {species}")
     
-    logger.info(f"Taxonomy built: {num_orders} orders, {num_families} families, {num_species} species")
+    logger.info(f"Taxonomy built: {num_families} families, {num_genera} genera, {num_species} species")
     return taxonomy
 
 def get_species_from_directory(train_dir):
@@ -276,15 +276,15 @@ class InsectDataset(Dataset):
         self.level_to_idx = level_to_idx
         self.samples = []
         
-        species_to_family = {species: family for species, family in taxonomy[3].items()}
-        family_to_order = {family: order for family, order in taxonomy[2].items()}
+        species_to_genus = {species: genus for species, genus in taxonomy[3].items()}
+        genus_to_family = {genus: family for genus, family in taxonomy[2].items()}
         
         for species_name in os.listdir(root_dir):
             species_path = os.path.join(root_dir, species_name)
             if os.path.isdir(species_path):
-                if species_name in species_to_family:
-                    family_name = species_to_family[species_name]
-                    order_name = family_to_order[family_name]
+                if species_name in species_to_genus:
+                    genus_name = species_to_genus[species_name]
+                    family_name = genus_to_family[genus_name]
                     
                     for img_file in os.listdir(species_path):
                         if img_file.endswith(('.jpg', '.png', '.jpeg')):
@@ -296,7 +296,7 @@ class InsectDataset(Dataset):
                                 # Only add valid images to samples
                                 self.samples.append({
                                     'image_path': img_path,
-                                    'labels': [order_name, family_name, species_name]
+                                    'labels': [family_name, genus_name, species_name]
                                 })
 
                             except Exception as e:

bplusplus-1.2.3.dist-info/METADATA

@@ -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.dist-info/RECORD

@@ -0,0 +1,11 @@
+bplusplus/__init__.py,sha256=GLqIx6Ln3Jt_Q95zkqXglKaSF3dbw-awax4dYry3tw0,145
+bplusplus/collect.py,sha256=lEJHXPpOo4DALBw6zemdmFuqAXZ12-BKwgesvq5ACYs,7135
+bplusplus/inference.py,sha256=3XmwzEfVTw5OFiMbMVgiuEa-r22HvMUWHVXESZsTIzo,37708
+bplusplus/prepare.py,sha256=pdXUVAzY030tM6f0Gf_zml8I26lS38wuvH13R2F00Do,25829
+bplusplus/test.py,sha256=kKjrsb3iCfljtRjot_kiVB5hopMkApoW9yvMcuI2O_U,30545
+bplusplus/tracker.py,sha256=JixV1ICGywGhVMTvkq3hrk4MLUUWDh3XJW4VLm4JdO0,11250
+bplusplus/train.py,sha256=wkHnKbTdZAFn2voJS7gSYXU7B9UVYVYmbTJCR0tFzs4,28058
+bplusplus-1.2.3.dist-info/LICENSE,sha256=rRkeHptDnlmviR0_WWgNT9t696eys_cjfVUU8FEO4k4,1071
+bplusplus-1.2.3.dist-info/METADATA,sha256=IDnokwF2CEyM_3xLmlRL30k2P9NglDjdjbxC7-UZoc4,4046
+bplusplus-1.2.3.dist-info/WHEEL,sha256=b4K_helf-jlQoXBBETfwnf4B04YC67LOev0jo4fX5m8,88
+bplusplus-1.2.3.dist-info/RECORD,,

{bplusplus-1.2.1.dist-info → bplusplus-1.2.3.dist-info}/WHEEL

@@ -1,4 +1,4 @@
 Wheel-Version: 1.0
-Generator: poetry-core 1.9.0
+Generator: poetry-core 2.1.3
 Root-Is-Purelib: true
 Tag: py3-none-any