Flatfield correction and metadata

README.md

@@ -1,4 +1,4 @@
-[![Build Status](https://github.com/czbiohub/microDL/workflows/build/badge.svg)]
+![Build Status](https://github.com/czbiohub/microDL/workflows/build/badge.svg)
 [![Code Coverage](https://codecov.io/gh/czbiohub/microDL/branch/master/graphs/badge.svg)](https://codecov.io/gh/czbiohub/microDL)
 
 # microDL

micro_dl/cli/dataset_pooling.py

@@ -38,7 +38,7 @@ def pool_dataset(config):
     num_workers = pool_config['num_workers']
     pool_mode = pool_config['pool_mode']
     frames_meta_dst_path = os.path.join(dst_dir, 'frames_meta.csv')
-    ints_meta_dst_path = os.path.join(dst_dir, 'ints_meta.csv')
+    ints_meta_dst_path = os.path.join(dst_dir, 'intensity_meta.csv')
     pos_idx_cur = 0
     os.makedirs(dst_dir, exist_ok=True)
     if os.path.exists(frames_meta_dst_path) and pool_mode == 'add':

micro_dl/cli/generate_meta.py

@@ -36,6 +36,12 @@ def parse_args():
         default=4,
         help="number of workers for multiprocessing",
     )
+    parser.add_argument(
+        '--block_size',
+        type=int,
+        default=256,
+        help="Pixel block size for intensity sampling",
+    )
     parser.add_argument(
         '--normalize_im',
         type=str,
@@ -46,19 +52,40 @@ def parse_args():
 
 
 def main(parsed_args):
-    meta_utils.frames_meta_generator(parsed_args.input,
-                                     parsed_args.order,
-                                     parsed_args.name_parser,
-                                     )
+    """
+    Generate metadata for each file by interpreting the file name.
+    Writes found data in frames_metadata.csv in input directory.
+    Assumed default file naming convention is:
+    dir_name
+    |
+    |- im_c***_z***_t***_p***.png
+    |- im_c***_z***_t***_p***.png
+
+    c is channel
+    z is slice in stack (z)
+    t is time
+    p is position (FOV)
+
+    Other naming convention is:
+    img_channelname_t***_p***_z***.tif for parse_sms_name
+
+    :param argparse parsed_args: Input arguments
+    """
+    # Collect metadata for all image files
+    meta_utils.frames_meta_generator(
+        input_dir=parsed_args.input,
+        order=parsed_args.order,
+        name_parser=parsed_args.name_parser,
+    )
+    # Compute intensity stats for all images
     if parsed_args.normalize_im in ['dataset', 'volume', 'slice']:
-        meta_utils.ints_meta_generator(parsed_args.input,
-                                       parsed_args.order,
-                                       parsed_args.name_parser,
-                                       parsed_args.num_workers,
-                                       )
+        meta_utils.ints_meta_generator(
+            input_dir=parsed_args.input,
+            num_workers=parsed_args.num_workers,
+            block_size=parsed_args.block_size,
+        )
 
 
 if __name__ == '__main__':
     parsed_args = parse_args()
     main(parsed_args)
-

micro_dl/cli/inference_script.py

@@ -91,7 +91,6 @@ def run_inference(config_fname,
         inference_inst.run_prediction()
 
 
-
 if __name__ == '__main__':
     args = parse_args()
     # Get GPU ID and memory fraction

micro_dl/cli/metrics_script.py

@@ -93,11 +93,13 @@ def compute_metrics(model_dir,
         (see evaluation_metrics)
     :param bool test_data: Uses test indices in split_samples.json,
     otherwise all indices
+    :param str name_parser: Type of name parser (default or parse_idx_from_name)
     """
     # Load config file
     config_name = os.path.join(model_dir, 'config.yml')
     with open(config_name, 'r') as f:
         config = yaml.safe_load(f)
+
     preprocess_config = preprocess_utils.get_preprocess_config(config['dataset']['data_dir'])
     # Load frames metadata and determine indices
     frames_meta = pd.read_csv(os.path.join(image_dir, 'frames_meta.csv'))
@@ -117,7 +119,6 @@ def compute_metrics(model_dir,
     else:
         test_ids = np.sort(np.unique(frames_meta[split_idx_name]))
 
-
     # Find other indices to iterate over than split index name
     # E.g. if split is position, we also need to iterate over time and slice
     test_meta = pd.read_csv(os.path.join(model_dir, 'test_metadata.csv'))