Refactor/samet/data

README.md

@@ -4,7 +4,6 @@
 [![pytorch](https://img.shields.io/badge/pytorch-1.7.1%2B-orange)]()
 [![openvino](https://img.shields.io/badge/openvino-2021.4-purple)]()
 ![example branch parameter](https://github.com/openvinotoolkit/anomalib/actions/workflows/tox.yml/badge.svg?branch=development)
-[![coverage report](https://gitlab-icv.inn.intel.com/algo_rnd_team/anomaly/badges/development/coverage.svg)](https://gitlab-icv.inn.intel.com/algo_rnd_team/anomaly/-/commits/development)
 
 
 This repository contains state-of-the art anomaly detection algorithms trained and evaluated on both public and private

anomalib/__init__.py

@@ -14,4 +14,4 @@
 # See the License for the specific language governing permissions
 # and limitations under the License.
 
-__version__ = "0.1.0"
+__version__ = "0.1.1"

anomalib/core/callbacks/nncf_callback.py

@@ -13,7 +13,7 @@
 from pytorch_lightning import Callback
 from torch.utils.data.dataloader import DataLoader
 
-from anomalib.datasets import get_datamodule
+from anomalib.data import get_datamodule
 
 
 def criterion_fn(outputs, criterion):

anomalib/core/callbacks/visualizer_callback.py

@@ -9,7 +9,7 @@
 from anomalib import loggers
 from anomalib.core.model import AnomalyModule
 from anomalib.core.results import SegmentationResults
-from anomalib.datasets.utils import Denormalize
+from anomalib.data.transforms import Denormalize
 from anomalib.utils.metrics import compute_threshold_and_f1_score
 from anomalib.utils.post_process import compute_mask, superimpose_anomaly_map
 from anomalib.utils.visualizer import Visualizer
@@ -22,7 +22,7 @@ class VisualizerCallback(Callback):
     the predicted error heat map, and the predicted segmentation mask.
 
     To save the images to the filesystem, add the 'local' keyword to the project.log_images_to parameter in the
-    config.yaml file. .
+    config.yaml file.
     """
 
     def __init__(self):

anomalib/core/model/inference.py

@@ -26,8 +26,8 @@
 from torch import Tensor, nn
 
 from anomalib.core.model import AnomalyModule
-from anomalib.datasets.transforms.pre_process import PreProcessor
-from anomalib.datasets.utils import read_image
+from anomalib.data.transforms.pre_process import PreProcessor
+from anomalib.data.utils import read_image
 from anomalib.models import get_model
 from anomalib.utils.post_process import superimpose_anomaly_map
 

anomalib/datasets/__init__.py → anomalib/data/__init__.py

@@ -19,7 +19,6 @@
 from omegaconf import DictConfig, ListConfig
 from pytorch_lightning import LightningDataModule
 
-from .anomaly_dataset import AnomalyDataModule
 from .mvtec import MVTecDataModule
 
 
@@ -37,26 +36,14 @@ def get_datamodule(config: Union[DictConfig, ListConfig]):
 
     if config.dataset.format.lower() == "mvtec":
         datamodule = MVTecDataModule(
+            # TODO: Remove config values. IAAALD-211
             root=config.dataset.path,
             category=config.dataset.category,
-            image_size=config.dataset.image_size,
-            crop_size=config.dataset.image_size,
+            image_size=(config.dataset.image_size[0], config.dataset.image_size[0]),
             train_batch_size=config.dataset.train_batch_size,
             test_batch_size=config.dataset.test_batch_size,
             num_workers=config.dataset.num_workers,
         )
-    elif config.dataset.format.lower() == "anomaly_dataset":
-        datamodule = AnomalyDataModule(
-            root=config.dataset.path,
-            url=config.dataset.url,
-            category=config.dataset.category,
-            task=config.dataset.task,
-            label_format=config.dataset.label_format,
-            train_batch_size=config.dataset.train_batch_size,
-            test_batch_size=config.dataset.test_batch_size,
-            num_workers=config.dataset.num_workers,
-            image_size=(config.dataset.image_size[0], config.dataset.image_size[1]),
-        )
     else:
         raise ValueError("Unknown dataset!")