bplusplus 1.2.0__tar.gz → 1.2.1__tar.gz

{bplusplus-1.2.0 → bplusplus-1.2.1}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: bplusplus
-Version: 1.2.0
+Version: 1.2.1
 Summary: A simple method to create AI models for biodiversity, with collect and prepare pipeline
 License: MIT
 Author: Titus Venverloo
@@ -15,6 +15,9 @@ Classifier: Programming Language :: Python :: 3.12
 Requires-Dist: prettytable (==3.7.0)
 Requires-Dist: pygbif (>=0.6.4,<0.7.0)
 Requires-Dist: requests (==2.25.1)
+Requires-Dist: scikit-learn (>=1.6.1,<2.0.0)
+Requires-Dist: tabulate (>=0.9.0,<0.10.0)
+Requires-Dist: torch (==2.5.0)
 Requires-Dist: ultralytics (==8.0.195)
 Requires-Dist: validators (>=0.33.0,<0.34.0)
 Description-Content-Type: text/markdown

{bplusplus-1.2.0 → bplusplus-1.2.1}/pyproject.toml

@@ -1,6 +1,6 @@
 [tool.poetry]
 name = "bplusplus"
-version = "1.2.0"
+version = "1.2.1"
 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>"]
 license = "MIT"
@@ -13,6 +13,9 @@ ultralytics = "8.0.195"
 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-1.2.0 → bplusplus-1.2.1}/src/bplusplus/collect.py

@@ -2,12 +2,13 @@ import os
 import random
 import threading
 from enum import Enum
-from typing import Any, Optional, List, Dict
-from tqdm import tqdm 
-import random
+from typing import Any, Dict, List, Optional
+
 import pygbif
 import requests
 import validators
+from tqdm import tqdm
+
 
 #this lists currently supported groupings, more can be added with proper testing
 class Group(str, Enum):
@@ -70,6 +71,10 @@ def __single_collect(group_by_key: Group, search_parameters: dict[str, Any], ima
 
 # threaded_collect: paralellize the collection of images
 def __threaded_collect(images_per_group: int, output_directory: str, num_threads: int, groups: list[str]):
+    # Handle edge case where num_threads is greater than number of groups
+    if num_threads >= len(groups):
+        num_threads = len(groups)
+
     # Divide the species list into num_threads parts
     chunk_size = len(groups) // num_threads
     species_chunks = [

{bplusplus-1.2.0 → bplusplus-1.2.1}/src/bplusplus/prepare.py

@@ -1,38 +1,38 @@
 import os
 import random
-from typing import Any, Optional
-import requests
-import tempfile
-from .collect import Group, collect
-from pathlib import Path
-from ultralytics import YOLO
 import shutil
-from PIL import Image, ImageDraw, ImageFont
+import tempfile
 from collections import defaultdict
-from prettytable import PrettyTable
+from pathlib import Path
+from typing import Any, Optional
+
 import matplotlib.pyplot as plt
+import numpy as np
 import requests
-from tqdm import tqdm
-import yaml
 import torch
+import yaml
+from PIL import Image, ImageDraw, ImageFont
+from prettytable import PrettyTable
 from torch import serialization
-from ultralytics.nn.tasks import DetectionModel
-from torch.nn.modules.container import Sequential
-from ultralytics.nn.modules.conv import Conv
-from torch.nn.modules.conv import Conv2d
+from torch.nn import Module, ModuleDict, ModuleList
+from torch.nn.modules.activation import LeakyReLU, ReLU, SiLU
 # Add more modules to prevent further errors
 from torch.nn.modules.batchnorm import BatchNorm2d
-from torch.nn.modules.activation import SiLU, ReLU, LeakyReLU
-from torch.nn.modules.pooling import MaxPool2d
-from torch.nn.modules.linear import Linear
+from torch.nn.modules.container import Sequential
+from torch.nn.modules.conv import Conv2d
 from torch.nn.modules.dropout import Dropout
+from torch.nn.modules.linear import Linear
+from torch.nn.modules.pooling import MaxPool2d
 from torch.nn.modules.upsampling import Upsample
-from torch.nn import Module, ModuleList, ModuleDict
-from ultralytics.nn.modules import (
-    Bottleneck, C2f, SPPF, Detect, Concat
-)
+from tqdm import tqdm
+from ultralytics import YOLO
+from ultralytics.nn.modules import SPPF, Bottleneck, C2f, Concat, Detect
 from ultralytics.nn.modules.block import DFL
-import numpy as np
+from ultralytics.nn.modules.conv import Conv
+from ultralytics.nn.tasks import DetectionModel
+
+from .collect import Group, collect
+
 
 def prepare(input_directory: str, output_directory: str, one_stage: bool = False, with_background: bool = False, size_filter: bool = False, sizes: list = None):
 
@@ -130,7 +130,8 @@ def prepare(input_directory: str, output_directory: str, one_stage: bool = False
                     group_by_key=Group.scientificName,
                     search_parameters=search, 
                     images_per_group=bg_images,
-                    output_directory=temp_dir_path
+                    output_directory=temp_dir_path,
+                    num_threads=3
                 )
 
                 __delete_corrupted_images(temp_dir_path / "Plantae")