homa 0.1.2__tar.gz → 0.1.5__tar.gz

{homa-0.1.2 → homa-0.1.5}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: homa
-Version: 0.1.2
+Version: 0.1.5
 Summary: A curated list of machine learning and deep learning helpers.
 Author-email: Taha Shieenavaz <tahashieenavaz@gmail.com>
 Requires-Python: >=3.7

{homa-0.1.2 → homa-0.1.5}/pyproject.toml

@@ -4,7 +4,7 @@ build-backend = "setuptools.build_meta"
 
 [project]
 name = "homa"
-version = "0.1.2"
+version = "0.1.5"
 description = "A curated list of machine learning and deep learning helpers."
 authors = [
   { name="Taha Shieenavaz", email="tahashieenavaz@gmail.com" },

homa-0.1.5/src/homa/torch/__init__.py

@@ -0,0 +1 @@
+from .helpers import *

homa-0.1.5/src/homa/vision/ClassificationModel.py

@@ -0,0 +1,5 @@
+from .Model import Model
+
+
+class ClassificationModel(Model):
+    pass

{homa-0.1.2 → homa-0.1.5}/src/homa/vision/Resnet.py

@@ -1,12 +1,13 @@
 import torch
 from .modules import ResnetModule
-from .Model import Model
-from .concerns import Trainable
+from .ClassificationModel import ClassificationModel
+from .concerns import Trainable, ReportsMetrics
+from ..device import get_device
 
 
-class Resnet(Model, Trainable):
+class Resnet(ClassificationModel, Trainable, ReportsMetrics):
     def __init__(self, num_classes: int, lr: float):
         super().__init__()
-        self.network = ResnetModule(num_classes)
+        self.network = ResnetModule(num_classes).to(get_device())
         self.criterion = torch.nn.CrossEntropyLoss()
         self.optimizer = torch.optim.SGD(self.network.parameters(), lr=lr, momentum=0.9)

homa-0.1.5/src/homa/vision/concerns/Predicts.py

@@ -0,0 +1,9 @@
+import torch
+
+
+class Predicts:
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    def predict(self, x: torch.Tensor):
+        return torch.softmax(self.logits(x), dim=1)

homa-0.1.5/src/homa/vision/concerns/ReportsAccuracy.py

@@ -0,0 +1,29 @@
+from torch import Tensor, no_grad
+from torch.utils.data.dataloader import DataLoader
+from ...device import get_device
+
+
+class ReportsAccuracy:
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    @no_grad()
+    def accuracy_tensors(self, x: Tensor, y: Tensor) -> float:
+        predictions = self.predict(x)
+        return (predictions == y).float().mean().item()
+
+    @no_grad()
+    def accuracy_dataloader(self, dataloader: DataLoader):
+        correct, total = 0, 0
+        for x, y in dataloader:
+            x, y = x.to(get_device()), y.to(get_device())
+            predictions = self.predict(x)
+            correct += (predictions == y).sum().item()
+            total += y.numel()
+        return correct / total if total > 0 else 0.0
+
+    def accuracy(self, x: Tensor | DataLoader, y: Tensor | None = None) -> float:
+        self.network.eval()
+        if isinstance(x, DataLoader):
+            return self.accuracy_dataloader(x)
+        return self.accuracy_tensors(x, y)

homa-0.1.5/src/homa/vision/concerns/ReportsLogits.py

@@ -0,0 +1,9 @@
+import torch
+
+
+class ReportsLogits:
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)
+
+    def logits(self, x: torch.Tensor) -> torch.Tensor:
+        return self.network(x)

homa-0.1.5/src/homa/vision/concerns/ReportsMetrics.py

@@ -0,0 +1,6 @@
+from .ReportsAccuracy import ReportsAccuracy
+
+
+class ReportsMetrics(ReportsAccuracy):
+    def __init__(self, *args, **kwargs):
+        super().__init__(*args, **kwargs)

{homa-0.1.2 → homa-0.1.5}/src/homa/vision/concerns/Trainable.py

@@ -1,9 +1,11 @@
 from torch import Tensor
 from torch.utils.data.dataloader import DataLoader
+from .ReportsLogits import ReportsLogits
+from .Predicts import Predicts
 from ...device import get_device
 
 
-class Trainable:
+class Trainable(ReportsLogits, Predicts):
     def __init__(self, *args, **kwargs):
         super().__init__(*args, **kwargs)
 

homa-0.1.5/src/homa/vision/concerns/__init__.py

@@ -0,0 +1,5 @@
+from .Predicts import Predicts
+from .ReportsAccuracy import ReportsAccuracy
+from .ReportsLogits import ReportsLogits
+from .ReportsMetrics import ReportsMetrics
+from .Trainable import Trainable

{homa-0.1.2 → homa-0.1.5}/src/homa.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: homa
-Version: 0.1.2
+Version: 0.1.5
 Summary: A curated list of machine learning and deep learning helpers.
 Author-email: Taha Shieenavaz <tahashieenavaz@gmail.com>
 Requires-Python: >=3.7

{homa-0.1.2 → homa-0.1.5}/src/homa.egg-info/SOURCES.txt

@@ -39,14 +39,18 @@ src/homa/ensemble/concerns/ReportsEnsembleKappa.py
 src/homa/ensemble/concerns/ReportsLogits.py
 src/homa/ensemble/concerns/ReportsSize.py
 src/homa/ensemble/concerns/__init__.py
-src/homa/torch/Module.py
 src/homa/torch/__init__.py
 src/homa/torch/helpers.py
+src/homa/vision/ClassificationModel.py
 src/homa/vision/Model.py
 src/homa/vision/Resnet.py
 src/homa/vision/StochasticResnet.py
 src/homa/vision/__init__.py
 src/homa/vision/utils.py
+src/homa/vision/concerns/Predicts.py
+src/homa/vision/concerns/ReportsAccuracy.py
+src/homa/vision/concerns/ReportsLogits.py
+src/homa/vision/concerns/ReportsMetrics.py
 src/homa/vision/concerns/Trainable.py
 src/homa/vision/concerns/__init__.py
 src/homa/vision/modules/ResnetModule.py

{homa-0.1.2 → homa-0.1.5}/tests/test_resnet.py

@@ -2,6 +2,7 @@ import pytest
 import torch
 from homa.vision import Resnet, Model
 from homa.vision.modules import ResnetModule
+from homa import get_device
 
 
 @pytest.fixture
@@ -19,3 +20,15 @@ def test_resnet_initialization(resnet_model):
     assert isinstance(resnet_model.network, ResnetModule)
     assert isinstance(resnet_model.optimizer, torch.optim.SGD)
     assert isinstance(resnet_model.criterion, torch.nn.CrossEntropyLoss)
+
+
+def test_reports_accuracy(resnet_model):
+    x = torch.randn(10, 3, 84, 84).to(get_device())
+    y = torch.randint(0, 3, (10, 1)).to(get_device())
+    accuracy = resnet_model.accuracy(x, y)
+    assert isinstance(accuracy, float)
+
+    dataset = torch.utils.data.TensorDataset(x, y)
+    dataloader = torch.utils.data.DataLoader(dataset, batch_size=2, shuffle=True)
+    accuracy = resnet_model.accuracy(dataloader)
+    assert isinstance(accuracy, float)

homa-0.1.2/src/homa/torch/Module.py

@@ -1,8 +0,0 @@
-import torch
-from ..device import get_device
-
-
-class Module(torch.nn.Module):
-    def __init__(self):
-        super(Module, self).__init__()
-        self.to(get_device())

homa-0.1.2/src/homa/torch/__init__.py

@@ -1,2 +0,0 @@
-from .Module import Module
-from .helpers import *

homa-0.1.2/src/homa/vision/concerns/__init__.py

@@ -1 +0,0 @@
-from .Trainable import Trainable