Fix/luxonis dataset converter (#90)

* Fix annotation yielding * Add delete_existing param * Polishing * chore: trigger tests only manually --------- Co-authored-by: Nikita Sokovnin <49622375+sokovninn@users.noreply.github.com>
luxonis · Mar 3, 2025 · b39a334 · b39a334
1 parent 0492085
commit b39a334
Show file tree

Hide file tree

Showing 2 changed files with 33 additions and 33 deletions.
diff --git a/.github/workflows/tests.yaml b/.github/workflows/tests.yaml
@@ -1,11 +1,6 @@
 name: Tests
 
 on:
-  pull_request:
-    paths:
-      - 'datadreamer/**/**.py'
-      - 'tests/core_tests/**/**.py'
-      - .github/workflows/tests.yaml
   workflow_dispatch:
 
 jobs:

diff --git a/datadreamer/utils/luxonis_dataset_converter.py b/datadreamer/utils/luxonis_dataset_converter.py
@@ -122,44 +122,44 @@ def dataset_generator():
                         h = min(box[3] / height - y, 1 - y)
                         annotation["boundingbox"] = {"x": x, "y": y, "w": w, "h": h}
 
-                if has_masks:
-                    mask = image_data["masks"][i]
-                    if isinstance(mask, list):
-                        poly = [(point[0] / width, point[1] / height) for point in mask]
-                        annotation["instance_segmentation"] = {
-                            "points": poly,
-                            "height": height,
-                            "width": width,
-                        }
-                    else:
-                        annotation["instance_segmentation"] = {
-                            "counts": mask["counts"],
-                            "height": mask["size"][0],
-                            "width": mask["size"][1],
-                        }
-
-                yield {
-                    "file": image_full_path,
-                    "task": f"datadreamer_{task}",
-                    "annotation": annotation,
-                }
+                    if has_masks:
+                        mask = image_data["masks"][i]
+                        if isinstance(mask, list):
+                            poly = [
+                                (point[0] / width, point[1] / height) for point in mask
+                            ]
+                            annotation["instance_segmentation"] = {
+                                "points": poly,
+                                "height": height,
+                                "width": width,
+                            }
+                        else:
+                            annotation["instance_segmentation"] = {
+                                "counts": mask["counts"],
+                                "height": mask["size"][0],
+                                "width": mask["size"][1],
+                            }
+
+                    yield {
+                        "file": image_full_path,
+                        "task": f"datadreamer_{task}",
+                        "annotation": annotation,
+                    }
 
         dataset_name = (
             os.path.basename(output_dir)
             if self.dataset_name is None or self.dataset_name == ""
             else self.dataset_name
         )
 
-        if LuxonisDataset.exists(dataset_name):
-            dataset = LuxonisDataset(dataset_name)
-            dataset.delete_dataset()
-
         # if dataset_plugin is set, use that
         if self.dataset_plugin:
             if "GOOGLE_APPLICATION_CREDENTIALS" in os.environ:
                 logger.info(f"Using {self.dataset_plugin} dataset")
                 dataset_constructor = DATASETS_REGISTRY.get(self.dataset_plugin)
-                dataset = dataset_constructor(dataset_name)
+                dataset = dataset_constructor(
+                    dataset_name, delete_existing=True, delete_remote=True
+                )
             else:
                 raise ValueError(
                     "GOOGLE_APPLICATION_CREDENTIALS environment variable is not set for using the dataset plugin."
@@ -170,10 +170,15 @@ def dataset_generator():
             and "GOOGLE_APPLICATION_CREDENTIALS" in os.environ
         ):
             logger.info("Using GCS bucket")
-            dataset = LuxonisDataset(dataset_name, bucket_storage=BucketStorage.GCS)
+            dataset = LuxonisDataset(
+                dataset_name,
+                bucket_storage=BucketStorage.GCS,
+                delete_existing=True,
+                delete_remote=True,
+            )
         else:
             logger.info("Using local dataset")
-            dataset = LuxonisDataset(dataset_name)
+            dataset = LuxonisDataset(dataset_name, delete_existing=True)
 
         dataset.add(dataset_generator())