fusion-bench 0.2.31__tar.gz → 0.2.32__tar.gz

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: fusion-bench
-Version: 0.2.31
+Version: 0.2.32
 Summary: A Comprehensive Benchmark of Deep Model Fusion
 Author-email: Anke Tang <tang.anke@foxmail.com>
 Project-URL: Repository, https://github.com/tanganke/fusion_bench
@@ -61,6 +61,8 @@ Dynamic: license-file
 
 FusionBench is a benchmark suite designed to evaluate the performance of various deep model fusion techniques. It aims to provide a comprehensive comparison of different methods on a variety of datasets and tasks.
 
+## :newspaper: News and Related
+
 Projects based on FusionBench and news from the community (descending order of date. If you have any work based on FusionBench, please feel free to let us know, we are willing to add it to the list. :partying_face:):
 
 <details>

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/README.md

@@ -21,6 +21,8 @@
 
 FusionBench is a benchmark suite designed to evaluate the performance of various deep model fusion techniques. It aims to provide a comprehensive comparison of different methods on a variety of datasets and tasks.
 
+## :newspaper: News and Related
+
 Projects based on FusionBench and news from the community (descending order of date. If you have any work based on FusionBench, please feel free to let us know, we are willing to add it to the list. :partying_face:):
 
 <details>

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/fusion_bench/__init__.py

@@ -86,6 +86,9 @@ _import_structure = {
         "set_print_function_call",
         "set_print_function_call_permeanent",
         "timeit_context",
+        "initialize_hydra_config",
+        "get_default_config_path",
+        "get_hydra_output_dir",
     ],
 }
 
@@ -144,8 +147,11 @@ if TYPE_CHECKING:
         StateDictType,
         TorchModelType,
         cache_with_joblib,
+        get_default_config_path,
+        get_hydra_output_dir,
         get_rankzero_logger,
         import_object,
+        initialize_hydra_config,
         instantiate,
         parse_dtype,
         print_parameters,

fusion_bench-0.2.32/fusion_bench/__main__.py

@@ -0,0 +1,4 @@
+from fusion_bench.scripts.cli import _hydra_main
+
+if __name__ == "__main__":
+    _hydra_main()

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/fusion_bench/dataset/__init__.py

@@ -38,10 +38,12 @@ _extra_objects = {
 }
 _import_structure = {
     "clip_dataset": ["CLIPDataset"],
+    "image_dataset": ["ImageClassificationDataset"],
 }
 
 if TYPE_CHECKING:
     from .clip_dataset import CLIPDataset
+    from .image_dataset import ImageClassificationDataset
 
 else:
     sys.modules[__name__] = LazyImporter(

fusion_bench-0.2.32/fusion_bench/dataset/clip_dataset.py

@@ -0,0 +1,13 @@
+"""
+This module provides a class to convert a dataset whose object is a list of dictionaries with keys "image" and "label" to a dataset whose object is a tuple of tensors (inputs, label) for CLIP models.
+"""
+
+from fusion_bench.utils import DeprecationWarningMeta
+
+from .image_dataset import ImageClassificationDataset
+
+__all__ = ["CLIPDataset"]
+
+
+class CLIPDataset(ImageClassificationDataset, metaclass=DeprecationWarningMeta):
+    pass

fusion_bench-0.2.31/fusion_bench/dataset/clip_dataset.py → fusion_bench-0.2.32/fusion_bench/dataset/image_dataset.py

@@ -1,35 +1,31 @@
-"""
-This module provides a class to convert a dataset whose object is a list of dictionaries with keys "image" and "label" to a dataset whose object is a tuple of tensors (inputs, label) for CLIP models.
-"""
-
-from typing import Optional, Tuple
+from typing import TYPE_CHECKING, Any, Callable, Optional, Tuple, Union
 
 import torch
 from torch.utils.data import Dataset
-from transformers import BaseImageProcessor, CLIPProcessor, ProcessorMixin
-
-__all__ = ["CLIPDataset"]
+from transformers import BaseImageProcessor, ProcessorMixin
 
 
-class CLIPDataset(torch.utils.data.Dataset):
+class ImageClassificationDataset(Dataset):
     """
-    A dataset class for CLIP models that converts a dataset of dictionaries or tuples
-    into a format suitable for CLIP processing.
+    A dataset class for image classification models that converts a dataset of dictionaries or tuples
+    into a format suitable for model processing.
 
-    This class wraps an existing dataset and applies CLIP preprocessing to the images.
+    This class wraps an existing dataset and applies preprocessing to the images.
     It expects each item in the dataset to be either a dictionary with 'image' and 'label' keys,
     or a tuple/list of (image, label).
-
-    Args:
-        dataset: The original dataset to wrap.
-        processor (CLIPProcessor): The CLIP processor for preparing inputs. If None, no preprocessing is applied and raw images are returned.
-
-    Attributes:
-        dataset: The wrapped dataset.
-        processor (CLIPProcessor): The CLIP processor used for image preprocessing.
     """
 
-    def __init__(self, dataset: Dataset, processor: Optional[CLIPProcessor] = None):
+    def __init__(
+        self,
+        dataset: Dataset,
+        processor: Optional[Union["ProcessorMixin", "BaseImageProcessor"]] = None,
+    ):
+        """
+        Args:
+            dataset (Dataset): The original dataset to wrap.
+            processor (Optional[Union[ProcessorMixin, BaseImageProcessor]]): The processor for preparing inputs.
+                If None, no preprocessing is applied and raw images are returned.
+        """
         self.dataset = dataset
         self.processor = processor
 
@@ -50,6 +46,8 @@ class CLIPDataset(torch.utils.data.Dataset):
         Raises:
             ValueError: If the item is neither a dictionary nor a tuple/list of length 2.
         """
+        # Standardize the item to a dictionary format
+        # {"image": ..., "label": ...}
         item = self.dataset[idx]
         if isinstance(item, dict):
             item = item
@@ -58,6 +56,8 @@ class CLIPDataset(torch.utils.data.Dataset):
             item = {"image": item[0], "label": item[1]}
         else:
             raise ValueError("Each item should be a dictionary or a tuple of length 2")
+
+        # Process the image using the provided processor, if any
         image = item["image"]
         if self.processor is not None:
             if isinstance(self.processor, (ProcessorMixin, BaseImageProcessor)):
@@ -70,7 +70,7 @@ class CLIPDataset(torch.utils.data.Dataset):
                 inputs = self.processor(image)
             else:
                 raise ValueError(
-                    "The processor should be a CLIPProcessor or a callable function"
+                    "The processor should be a transformers Processor or a callable function"
                 )
         else:
             # if processor is None, return the raw image directly

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/fusion_bench/method/base_algorithm.py

@@ -59,6 +59,10 @@ class BaseAlgorithm(BaseYAMLSerializable):
     core fusion logic in the `run` method, while optional lifecycle hooks allow for
     setup and cleanup operations.
 
+    If model has `_fusion_bench_target_modules` attribute, the algorithm will only fuse
+    the specified target modules. This is useful for models where only certain layers
+    should be fused (e.g., classification heads on top of a shared backbone are not merged).
+
     Attributes:
         _program: Optional program reference for algorithm execution context.
         _config_key (str): Configuration key used for YAML serialization, defaults to "method".

{fusion_bench-0.2.31 → fusion_bench-0.2.32}/fusion_bench/method/dop/dop.py

@@ -79,28 +79,6 @@ class ContinualDOPForCLIP(BaseAlgorithm, LightningFabricMixin):
         ), "The alpha should be in the range of [0, 1]"
         super().__init__(**kwargs)
 
-    def print_params(self, pretrained_model):
-        total_params = 0
-        linear_params = 0
-        linear_weight_params = 0
-        for module_name, module in pretrained_model.named_modules():
-            if not is_leaf_module(module):
-                continue
-            if isinstance(module, nn.Linear):
-                linear_params += sum(p.numel() for n, p in module.named_parameters())
-                linear_weight_params += sum(
-                    p.numel() for n, p in module.named_parameters() if "weight" in n
-                )
-            total_params += sum(p.numel() for p in module.parameters())
-
-        linear_ratio = linear_params / total_params * 100
-        linear_weight_ratio = linear_weight_params / total_params * 100
-        print(f"Total Parameters: {total_params}")
-        print(f"Linear Parameters: {linear_params}")
-        print(f"Linear Weight Parameters: {linear_weight_params}")
-        print(f"Linear Ratio: {linear_ratio:.2f}%")
-        print(f"Linear Weight Ratio: {linear_weight_ratio:.2f}%")
-
     def run(self, modelpool: BaseModelPool):
         if self.seed is not None:
             L.seed_everything(self.seed)