write one run_metadata.json file per run

.github/workflows/ci.yml

@@ -61,7 +61,7 @@ jobs:
           cd ..
           docker run --rm --shm-size=512m --volume $(pwd):/work --workdir /work wsinferimage run \
             --wsi-dir slides/ --results-dir results/ --model resnet34 --weights TCGA-BRCA-v1
-          test -f results/run_metadata.json
+          test -f results/run_metadata_*.json
           test -f results/patches/JP2K-33003-1.h5
           test -f results/model-outputs/JP2K-33003-1.csv
           test $(wc -l < results/model-outputs/JP2K-33003-1.csv) -eq 653
@@ -85,7 +85,7 @@ jobs:
           wget -q https://openslide.cs.cmu.edu/download/openslide-testdata/Aperio/JP2K-33003-1.svs
           cd ..
           wsinfer run --wsi-dir slides/ --results-dir results/ --model resnet34 --weights TCGA-BRCA-v1
-          test -f results/run_metadata.json
+          test -f results/run_metadata_*.json
           test -f results/patches/JP2K-33003-1.h5
           test -f results/model-outputs/JP2K-33003-1.csv
           test $(wc -l < results/model-outputs/JP2K-33003-1.csv) -eq 653

tests/test_all.py

@@ -313,7 +313,9 @@ def test_cli_run_regression(
         assert np.allclose(df.loc[:, col], col_prob)
 
     # Test that metadata path exists.
-    metadata_path = results_dir / "run_metadata.json"
+    metadata_paths = list(results_dir.glob("run_metadata_*.json"))
+    assert len(metadata_paths) == 1
+    metadata_path = metadata_paths[0]
     assert metadata_path.exists()
     with open(metadata_path) as f:
         meta = json.load(f)
@@ -1019,3 +1021,47 @@ def test_issue_94(tmp_path: Path, tiff_image: Path):
     assert result.exit_code == 0
     assert results_dir.joinpath("model-outputs").joinpath("purple.csv").exists()
     assert not results_dir.joinpath("model-outputs").joinpath("bad.csv").exists()
+
+
+def test_issue_97(tmp_path: Path, tiff_image: Path):
+    """Write a run_metadata file per run."""
+    from wsinfer.cli.cli import cli
+
+    runner = CliRunner()
+    results_dir = tmp_path / "inference"
+    result = runner.invoke(
+        cli,
+        [
+            "run",
+            "--wsi-dir",
+            str(tiff_image.parent),
+            "--model",
+            "resnet34",
+            "--weights",
+            "TCGA-BRCA-v1",
+            "--results-dir",
+            str(results_dir),
+        ],
+    )
+    assert result.exit_code == 0
+    metas = list(results_dir.glob("run_metadata_*.json"))
+    assert len(metas) == 1
+
+    # Run again...
+    result = runner.invoke(
+        cli,
+        [
+            "run",
+            "--wsi-dir",
+            str(tiff_image.parent),
+            "--model",
+            "resnet34",
+            "--weights",
+            "TCGA-BRCA-v1",
+            "--results-dir",
+            str(results_dir),
+        ],
+    )
+    assert result.exit_code == 0
+    metas = list(results_dir.glob("run_metadata_*.json"))
+    assert len(metas) == 2

wsinfer/cli/infer.py

@@ -1,5 +1,6 @@
 """Detect cancerous regions in a whole slide image."""
 
+from datetime import datetime
 import getpass
 import json
 import os
@@ -44,8 +45,6 @@ def _inside_container() -> str:
 
 
 def _get_timestamp() -> str:
-    from datetime import datetime
-
     dt = datetime.now().astimezone()
     # Thu Aug 25 23:32:17 2022 EDT
     return dt.strftime("%c %Z")
@@ -354,7 +353,8 @@ def run(
         )
         click.secho("\n".join(failed_inference), fg="yellow")
 
-    run_metadata_outpath = results_dir / "run_metadata.json"
+    timestamp = datetime.now().astimezone().strftime("%Y%m%dT%H%M%S")
+    run_metadata_outpath = results_dir / f"run_metadata_{timestamp}.json"
     click.echo(f"Saving metadata about run to {run_metadata_outpath}")
     run_metadata = _get_info_for_save(weights_obj)
     with open(run_metadata_outpath, "w") as f: