update evaluation docs

update evaluation docs

Author: taigw

docs/source/usage.quickstart.rst

@@ -115,3 +115,51 @@ file used for segmentation of lung from radiograph, which can be find in
    label_source = [0, 1]
    label_target = [0, 255]
 
+
+Evaluation
+----------
+
+To evaluate a model's prediction results compared with the ground truth, 
+use the ``pymic_eval_seg`` and  ``pymic_eval_cls`` commands for segmentation
+and classfication tasks, respectively. Both of them accept a configuration 
+file to specify the evaluation metrics, predicted results, ground truth and
+other information. 
+
+For example, for segmentation tasks, run:
+
+.. code-block:: none
+
+   pymic_eval_seg evaluation.cfg 
+
+The configuration file is like (an example from ``PYMIC_examples/seg_ssl/ACDC``):
+
+.. code-block:: none
+
+   [evaluation]
+   metric = dice
+   label_list = [1,2,3]
+   organ_name = heart
+
+   ground_truth_folder_root  = ../../PyMIC_data/ACDC/preprocess
+   segmentation_folder_root  = result/unet2d_em
+   evaluation_image_pair     = config/data/image_test_gt_seg.csv
+
+See :mod:`pymic.util.evaluation_seg.evaluation` for details of the configuration required.
+
+For classification tasks, run:
+
+.. code-block:: none
+
+   pymic_eval_cls evaluation.cfg 
+
+The configuration file is like (an example from ``PYMIC_examples/classification/CHNCXR``):
+
+.. code-block:: none
+
+   [evaluation]
+   metric_list = [accuracy, auc]
+   ground_truth_csv = config/cxr_test.csv
+   predict_csv   = result/resnet18.csv
+   predict_prob_csv   = result/resnet18_prob.csv
+
+See :mod:`pymic.util.evaluation_cls.main` for details of the configuration required.

pymic/io/h5_dataset.py

@@ -1,13 +1,11 @@
 # -*- coding: utf-8 -*-
 
 from logging import root
-import os
-from re import S 
+import os 
 import torch
 import random
 import h5py 
 import pandas as pd
-from scipy import ndimage
 from torch.utils.data import Dataset
 from torch.utils.data.sampler import Sampler
 
@@ -40,7 +38,6 @@ def __getitem__(self, idx):
         sample = {'image': image, 'label': label}
         if self.transform:
             sample = self.transform(sample)
-        # sample["idx"] = idx
         return sample
 
 class TwoStreamBatchSampler(Sampler):

requirements.txt

@@ -4,7 +4,7 @@ pandas>=0.25.3
 scikit-image>=0.16.2
 scikit-learn>=0.22
 scipy>=1.3.3
-SimpleITK>=1.2.4
+SimpleITK>=2.0.0
 tensorboard>=2.1.0
 tensorboardX>=1.9
 torch>=1.7.1