0.15.13

global initialization (torch) removed

Author: bartzbeielstein

pyproject.toml

@@ -7,7 +7,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "spotpython"
-version = "0.15.12"
+version = "0.15.13"
 authors = [
   { name="T. Bartz-Beielstein", email="tbb@bartzundbartz.de" }
 ]

src/spotpython/light/cvmodel.py

@@ -3,7 +3,6 @@
 from spotpython.utils.eda import generate_config_id
 from pytorch_lightning.loggers import TensorBoardLogger
 from lightning.pytorch.callbacks.early_stopping import EarlyStopping
-from spotpython.torch.initialization import kaiming_init, xavier_init
 import os
 
 
@@ -54,14 +53,6 @@ def cv_model(config: dict, fun_control: dict) -> float:
         print("k:", k)
 
         model = fun_control["core_model"](**config, _L_in=_L_in, _L_out=_L_out, _torchmetric=_torchmetric)
-        initialization = config["initialization"]
-        if initialization == "Xavier":
-            xavier_init(model)
-        elif initialization == "Kaiming":
-            kaiming_init(model)
-        else:
-            pass
-        # print(f"model: {model}")
 
         dm = LightCrossValidationDataModule(
             k=k,

src/spotpython/light/predictmodel.py

@@ -4,7 +4,6 @@
 from pytorch_lightning.loggers import TensorBoardLogger
 from lightning.pytorch.callbacks import ModelCheckpoint
 from lightning.pytorch.callbacks.early_stopping import EarlyStopping
-from spotpython.torch.initialization import kaiming_init, xavier_init
 import os
 from typing import Tuple
 
@@ -76,15 +75,7 @@ def predict_model(config: dict, fun_control: dict) -> Tuple[float, float]:
     # dm.setup(stage="train")
     # Init model from datamodule's attributes
     model = fun_control["core_model"](**config, _L_in=_L_in, _L_out=_L_out, _torchmetric=_torchmetric)
-    initialization = config["initialization"]
-    if initialization == "Xavier":
-        xavier_init(model)
-    elif initialization == "Kaiming":
-        kaiming_init(model)
-    else:
-        pass
-    # print(f"model: {model}")
-    # Init trainer
+
     trainer = L.Trainer(
         # Where to save models
         default_root_dir=os.path.join(fun_control["CHECKPOINT_PATH"], config_id),

src/spotpython/light/testmodel.py

@@ -4,7 +4,6 @@
 from pytorch_lightning.loggers import TensorBoardLogger
 from lightning.pytorch.callbacks import ModelCheckpoint
 from lightning.pytorch.callbacks.early_stopping import EarlyStopping
-from spotpython.torch.initialization import kaiming_init, xavier_init
 import os
 from typing import Tuple
 
@@ -77,15 +76,7 @@ def test_model(config: dict, fun_control: dict) -> Tuple[float, float]:
     # dm.setup()
     # Init model from datamodule's attributes
     model = fun_control["core_model"](**config, _L_in=_L_in, _L_out=_L_out, _torchmetric=_torchmetric)
-    initialization = config["initialization"]
-    if initialization == "Xavier":
-        xavier_init(model)
-    elif initialization == "Kaiming":
-        kaiming_init(model)
-    else:
-        pass
-    # print(f"model: {model}")
-    # Init trainer
+
     trainer = L.Trainer(
         # Where to save models
         default_root_dir=os.path.join(fun_control["CHECKPOINT_PATH"], config_id),

src/spotpython/light/trainmodel.py

@@ -3,7 +3,6 @@
 from spotpython.utils.eda import generate_config_id
 from pytorch_lightning.loggers import TensorBoardLogger
 from lightning.pytorch.callbacks.early_stopping import EarlyStopping
-from spotpython.torch.initialization import kaiming_init, xavier_init
 from lightning.pytorch.callbacks import ModelCheckpoint
 import os
 
@@ -88,13 +87,6 @@ def train_model(config: dict, fun_control: dict, timestamp: bool = True) -> floa
         # the config id is generated here without a timestamp.
         config_id = generate_config_id(config, timestamp=False) + "_TRAIN"
     model = fun_control["core_model"](**config, _L_in=_L_in, _L_out=_L_out, _torchmetric=_torchmetric)
-    initialization = config["initialization"]
-    if initialization == "Xavier":
-        xavier_init(model)
-    elif initialization == "Kaiming":
-        kaiming_init(model)
-    else:
-        pass
 
     dm = LightDataModule(
         dataset=fun_control["data_set"],