Version 1.1.2: Bug fixes in portpy.ai module.

Author: gourav3017

examples/python_files/imrt_dose_prediction.py

@@ -42,7 +42,7 @@
 
 
 # preprocess portpy data
-# data_preprocess(in_dir, out_dir)
+data_preprocess(in_dir, out_dir)
 
 # **Note** split the data in train and test folder in the output directory before running further code
 # e.g. out_dir\train\Lung_Patient_2 out_dir\test\Lung_Patient_9

portpy/__init__.py

@@ -15,6 +15,6 @@
 # a separate commercial license.
 # ----------------------------------------------------------------------
 
-__version__ = "1.1.1"
+__version__ = "1.1.2"
 # Change version here manually to reflect it everywhere
 from portpy import photon

portpy/ai/data/__init__.py

@@ -15,6 +15,76 @@
 # a separate commercial license.
 # ----------------------------------------------------------------------
 
+"""This package includes all the modules related to data loading and preprocessing
+
+ To add a custom dataset class called 'dummy', you need to add a file called 'dummy_dataset.py' and define a subclass 'DummyDataset' inherited from BaseDataset.
+ You need to implement four functions:
+    -- <__init__>:                      initialize the class, first call BaseDataset.__init__(self, opt).
+    -- <__len__>:                       return the size of dataset.
+    -- <__getitem__>:                   get a data point from data loader.
+    -- <modify_commandline_options>:    (optionally) add dataset-specific options and set default options.
+
+Now you can use the dataset class by specifying flag '--dataset_mode dummy'.
+See our template dataset class 'template_dataset.py' for more details.
+"""
+import os
+import sys
+project_root = os.path.abspath(os.path.join(os.path.dirname(__file__), "../../.."))
+if project_root not in sys.path:
+    sys.path.append(project_root)
+
+import importlib
+import torch.utils.data
+from portpy.ai.data.base_dataset import BaseDataset
+
+
+def find_dataset_using_name(dataset_name):
+    """Import the module "data/[dataset_name]_dataset.py".
+
+    In the file, the class called DatasetNameDataset() will
+    be instantiated. It has to be a subclass of BaseDataset,
+    and it is case-insensitive.
+    """
+    dataset_filename = "portpy.ai.data." + dataset_name + "_dataset"
+    datasetlib = importlib.import_module(dataset_filename)
+
+    dataset = None
+    target_dataset_name = dataset_name.replace('_', '') + 'dataset'
+    for name, cls in datasetlib.__dict__.items():
+        if name.lower() == target_dataset_name.lower() \
+           and issubclass(cls, BaseDataset):
+            dataset = cls
+
+    if dataset is None:
+        raise NotImplementedError("In %s.py, there should be a subclass of BaseDataset with class name that matches %s in lowercase." % (dataset_filename, target_dataset_name))
+
+    return dataset
+
+
+def get_option_setter(dataset_name):
+    """Return the static method <modify_commandline_options> of the dataset class."""
+    dataset_class = find_dataset_using_name(dataset_name)
+    return dataset_class.modify_commandline_options
+
+
+def create_dataset(opt):
+    """Create a dataset given the option.
+
+    This function wraps the class CustomDatasetDataLoader.
+        This is the main interface between this package and 'train.py'/'test.py'
+
+    Example:
+        from data import create_dataset
+        dataset = create_dataset(opt)
+    """
+    data_loader = CustomDatasetDataLoader(opt)
+    dataset = data_loader.load_data()
+    return dataset
+
+
+class CustomDatasetDataLoader():
+    """Wrapper class of Dataset class that performs multi-threaded data loading"""
+
     def __init__(self, opt):
         """Initialize this class
 
@@ -44,4 +114,4 @@ def __iter__(self):
         for i, data in enumerate(self.dataloader):
             if i * self.opt.batch_size >= self.opt.max_dataset_size:
                 break
-            yield data
+            yield data

portpy/ai/data/base_dataset.py

@@ -15,6 +15,36 @@
 # a separate commercial license.
 # ----------------------------------------------------------------------
 
+
+"""This module implements an abstract base class (ABC) 'BaseDataset' for datasets.
+
+It also includes common transformation functions (e.g., get_transform, __scale_width), which can be later used in subclasses.
+"""
+import random
+import numpy as np
+import torch.utils.data as data
+from PIL import Image
+import torchvision.transforms as transforms
+import torchvision.transforms.functional as TF
+from abc import ABC, abstractmethod
+import torch
+import warnings
+from scipy.ndimage import affine_transform
+
+
+warnings.filterwarnings("ignore")
+
+
+class BaseDataset(data.Dataset, ABC):
+    """This class is an abstract base class (ABC) for datasets.
+
+    To create a subclass, you need to implement the following four functions:
+    -- <__init__>:                      initialize the class, first call BaseDataset.__init__(self, opt).
+    -- <__len__>:                       return the size of dataset.
+    -- <__getitem__>:                   get a data point.
+    -- <modify_commandline_options>:    (optionally) add dataset-specific options and set default options.
+    """
+
     def __init__(self, opt):
         """Initialize the class; save the options in the class
 

portpy/ai/data/dosepred3d_dataset.py

@@ -88,7 +88,7 @@ def __getitem__(self, index):
         if self.phase == 'train':
             # A, B, OAR, beam, hist, bins = transform_3d_data(A, B, OAR, PTV, beam, hist, bins, transform=False)
 
-            A, B, OAR, beam = transform_3d_data(A, B, OAR, PTV, beam, augment=self.transform)
+            A, B, OAR, beam = transform_3d_data(A, B, OAR, PTV, beam, augment=self.augment)
             A = torch.unsqueeze(A, dim=0)  # Add channel dimensions as data is 3D
             B = torch.unsqueeze(B, dim=0)
             beam = torch.unsqueeze(beam, dim=0)