[Auto3DSeg] Update ALGO_BASH for support num_worker and test cases to reflect unification of epoch-based training (#5763)

Signed-off-by: dongy <[email protected]>

### Description

- Update ALGO_HASH to support `num_workers` override
- Update test cases.

### Types of changes
<!--- Put an `x` in all the boxes that apply, and remove the not
applicable items -->
- [x] Non-breaking change (fix or new feature that would not break
existing functionality).
- [x] New tests added to cover the changes.
- [x] Integration tests passed locally by running `./runtests.sh -f -u
--net --coverage`.
- [x] Quick tests passed locally by running `./runtests.sh --quick
--unittests --disttests`.

Signed-off-by: dongy <[email protected]>
Co-authored-by: dongy <[email protected]>
Co-authored-by: Mingxin Zheng <[email protected]>

Author: 3 people

CITATION.cff

@@ -48,8 +48,6 @@ preferred-citation:
     family-names: "Xu"
   - given-names: "Ali"
     family-names: "Hatamizadeh"
-  - given-names: "Andriy"
-    family-names: "Myronenko"
   - given-names: "Wentao"
     family-names: "Zhu"
   - given-names: "Yun"

monai/apps/auto3dseg/bundle_gen.py

@@ -32,7 +32,7 @@
 from monai.utils import ensure_tuple
 
 logger = get_logger(module_name=__name__)
-ALGO_HASH = os.environ.get("MONAI_ALGO_HASH", "c812e5f")
+ALGO_HASH = os.environ.get("MONAI_ALGO_HASH", "1dde7a1")
 
 __all__ = ["BundleAlgo", "BundleGen"]
 

tests/test_auto3dseg_ensemble.py

@@ -49,11 +49,10 @@
 train_param = (
     {
         "CUDA_VISIBLE_DEVICES": list(range(num_gpus)),
-        "num_iterations": int(4 / num_gpus),
-        "num_iterations_per_validation": int(4 / num_gpus),
         "num_images_per_batch": 2,
-        "num_epochs": 1,
-        "num_warmup_iterations": int(4 / num_gpus),
+        "num_epochs": 2,
+        "num_epochs_per_validation": 1,
+        "num_warmup_epochs": 1,
         "use_pretrain": False,
         "pretrained_path": "",
     }

tests/test_auto3dseg_hpo.py

@@ -33,11 +33,10 @@
 override_param = (
     {
         "CUDA_VISIBLE_DEVICES": list(range(num_gpus)),
-        "num_iterations": int(4 / num_gpus),
-        "num_iterations_per_validation": int(4 / num_gpus),
         "num_images_per_batch": 2,
-        "num_epochs": 1,
-        "num_warmup_iterations": int(4 / num_gpus),
+        "num_epochs": 2,
+        "num_epochs_per_validation": 1,
+        "num_warmup_epochs": 1,
         "use_pretrain": False,
         "pretrained_path": "",
     }

tests/test_integration_autorunner.py

@@ -49,11 +49,10 @@
 train_param = (
     {
         "CUDA_VISIBLE_DEVICES": list(range(num_gpus)),
-        "num_iterations": int(4 / num_gpus),
-        "num_iterations_per_validation": int(4 / num_gpus),
         "num_images_per_batch": 2,
-        "num_epochs": 1,
-        "num_warmup_iterations": int(4 / num_gpus),
+        "num_epochs": 2,
+        "num_epochs_per_validation": 1,
+        "num_warmup_epochs": 1,
         "use_pretrain": False,
         "pretrained_path": "",
     }
@@ -145,24 +144,21 @@ def test_autorunner_hpo(self) -> None:
         runner = AutoRunner(work_dir=work_dir, input=self.data_src_cfg, hpo=True, ensemble=False)
         hpo_param = {
             "CUDA_VISIBLE_DEVICES": train_param["CUDA_VISIBLE_DEVICES"],
-            "num_iterations": train_param["num_iterations"],
-            "num_iterations_per_validation": train_param["num_iterations_per_validation"],
+            "num_epochs_per_validation": train_param["num_epochs_per_validation"],
             "num_images_per_batch": train_param["num_images_per_batch"],
             "num_epochs": train_param["num_epochs"],
-            "num_warmup_iterations": train_param["num_warmup_iterations"],
+            "num_warmup_epochs": train_param["num_warmup_epochs"],
             "use_pretrain": train_param["use_pretrain"],
             "pretrained_path": train_param["pretrained_path"],
             # below are to shorten the time for dints
-            "training#num_iterations": train_param["num_iterations"],
-            "training#num_iterations_per_validation": train_param["num_iterations_per_validation"],
+            "training#num_epochs_per_validation": train_param["num_epochs_per_validation"],
             "training#num_images_per_batch": train_param["num_images_per_batch"],
             "training#num_epochs": train_param["num_epochs"],
-            "training#num_warmup_iterations": train_param["num_warmup_iterations"],
-            "searching#num_iterations": train_param["num_iterations"],
-            "searching#num_iterations_per_validation": train_param["num_iterations_per_validation"],
+            "training#num_warmup_epochs": train_param["num_warmup_epochs"],
+            "searching#num_epochs_per_validation": train_param["num_epochs_per_validation"],
             "searching#num_images_per_batch": train_param["num_images_per_batch"],
             "searching#num_epochs": train_param["num_epochs"],
-            "searching#num_warmup_iterations": train_param["num_warmup_iterations"],
+            "searching#num_warmup_epochs": train_param["num_warmup_epochs"],
             "nni_dry_run": True,
         }
         search_space = {"learning_rate": {"_type": "choice", "_value": [0.0001, 0.001, 0.01, 0.1]}}

tests/test_integration_gpu_customization.py

@@ -49,11 +49,10 @@
 train_param = (
     {
         "CUDA_VISIBLE_DEVICES": list(range(num_gpus)),
-        "num_iterations": int(4 / num_gpus),
-        "num_iterations_per_validation": int(4 / num_gpus),
         "num_images_per_batch": 2,
-        "num_epochs": 1,
-        "num_warmup_iterations": int(4 / num_gpus),
+        "num_epochs": 2,
+        "num_epochs_per_validation": 1,
+        "num_warmup_epochs": 1,
         "use_pretrain": False,
         "pretrained_path": "",
     }