Add: fix image transform to float

.github/pull_request_template.md

@@ -22,4 +22,4 @@ Before you submit your pull request, please make sure you have completed the fol
 - [ ] 📚 I have made the necessary updates to the documentation (if applicable).
 - [ ] 🧪 I have written tests that support my changes and prove that my fix is effective or my feature works (if applicable).
 
-For more information about code review checklists, see the [Code Review Checklist](../docs/source/markdown/guides/developer/code_review_checklist.md).
+For more information about code review checklists, see the [Code Review Checklist](https://github.com/openvinotoolkit/anomalib/blob/main/docs/source/markdown/guides/developer/code_review_checklist.md).

.github/workflows/nightly.yml

@@ -23,3 +23,10 @@ jobs:
         with:
           name: coverage
           path: .tox/coverage.xml
+  md-dead-link-check:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+      - uses: AlexanderDokuchaev/[email protected]
+        with:
+          config: pyproject.toml

.github/workflows/pre_merge.yml

@@ -75,3 +75,11 @@ jobs:
           else
             ./codecov -t "${CODECOV_TOKEN}"  --sha $COMMIT_ID -U $HTTP_PROXY -f .tox/coverage.xml
           fi
+
+  md-dead-link-check:
+    runs-on: ubuntu-22.04
+    steps:
+      - uses: actions/checkout@v4
+      - uses: AlexanderDokuchaev/[email protected]
+        with:
+          config: pyproject.toml

CONTRIBUTING.md

@@ -86,7 +86,7 @@ However, make sure to address any pre-commit issues before finalizing your pull
 
 ### Making Changes
 
-1. **Write Code:** Follow the project's coding standards and write your code with clear intent. Ensure your code is well-documented and includes examples where appropriate. For code quality we use ruff, whose configuration is in [`pyproject.toml`](https://github.com/openvinotoolkit/anomalib/blob/main/pyproject.toml) file.
+1. **Write Code:** Follow the project's coding standards and write your code with clear intent. Ensure your code is well-documented and includes examples where appropriate. For code quality we use ruff, whose configuration is in [`pyproject.toml`](pyproject.toml) file.
 
 2. **Add Tests:** If your code includes new functionality, add corresponding tests using [pytest](https://docs.pytest.org/en/7.4.x/) to maintain coverage and reliability.
 
@@ -99,7 +99,7 @@ However, make sure to address any pre-commit issues before finalizing your pull
    pytest tests/
    ```
 
-5. **Update the Changelog:** For significant changes, add a summary to the [CHANGELOG](https://github.com/openvinotoolkit/anomalib/blob/main/CHANGELOG.md).
+5. **Update the Changelog:** For significant changes, add a summary to the [CHANGELOG](CHANGELOG.md).
 
 6. **Check Licensing:** Ensure you own the code or have rights to use it, adhering to appropriate licensing.
 

README.md

@@ -9,7 +9,7 @@
 [Key Features](#key-features) •
 [Docs](https://anomalib.readthedocs.io/en/latest/) •
 [Notebooks](notebooks) •
-[License](https://github.com/openvinotoolkit/anomalib/blob/main/LICENSE)
+[License](LICENSE)
 
 [![python](https://img.shields.io/badge/python-3.7%2B-green)]()
 [![pytorch](https://img.shields.io/badge/pytorch-1.8.1%2B-orange)]()
@@ -52,7 +52,7 @@ Installing the library with pip is the easiest way to get started with anomalib.
 pip install anomalib
 ```
 
-This will install Anomalib CLI using the [installer](requirements/installer.txt) dependecies. Anomalib CLI is a command line interface for training, inference, benchmarking, and hyperparameter optimization. If you want to use the library as a Python package, you can install the library with the following command:
+This will install Anomalib CLI using the [installer](requirements/installer.txt) dependencies. Anomalib CLI is a command line interface for training, inference, benchmarking, and hyperparameter optimization. If you want to use the library as a Python package, you can install the library with the following command:
 
 ```bash
 # Get help for the installation arguments
@@ -78,7 +78,7 @@ anomalib install --option openvino
 To install from source, you need to clone the repository and install the library using pip via editable mode.
 
 ```bash
-# Use of virtual environment is highy recommended
+# Use of virtual environment is highly recommended
 # Using conda
 yes | conda create -n anomalib_env python=3.10
 conda activate anomalib_env
@@ -92,7 +92,7 @@ cd anomalib
 pip install -e .
 ```
 
-This will install Anomalib CLI using the [installer](requirements/installer.txt) dependecies. Anomalib CLI is a command line interface for training, inference, benchmarking, and hyperparameter optimization. If you want to use the library as a Python package, you can install the library with the following command:
+This will install Anomalib CLI using the [installer](requirements/installer.txt) dependencies. Anomalib CLI is a command line interface for training, inference, benchmarking, and hyperparameter optimization. If you want to use the library as a Python package, you can install the library with the following command:
 
 ```bash
 # Get help for the installation arguments
@@ -259,7 +259,7 @@ You first need to modify the `config.yaml` file to enable logging. The following
 
 Anomalib provides a benchmarking tool to evaluate the performance of the anomaly detection models on a given dataset. The benchmarking tool can be used to evaluate the performance of the models on a given dataset, or to compare the performance of multiple models on a given dataset.
 
-Each model in anomalib is benchmarked on a set of datasets, and the results are available in `src/anomalib/models/<model_name>README.md`. For example, the MVTec AD results for the Patchcore model are available in the corresponding [README.md](https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/patchcore#mvtec-ad-dataset) file.
+Each model in anomalib is benchmarked on a set of datasets, and the results are available in `src/anomalib/models/<type>/<model_name>/README.md`. For example, the MVTec AD results for the Patchcore model are available in the corresponding [README.md](src/anomalib/models/image/patchcore/README.md#mvtec-ad-dataset) file.
 
 <details>
 <summary>Benchmarking via API</summary>

docs/source/markdown/announcements/recognition.md

@@ -11,7 +11,7 @@ Anomalib is committed to excellence and innovation in open-source software devel
 [![OpenSSF Best Practices](https://www.bestpractices.dev/projects/8330/badge)](https://www.bestpractices.dev/projects/8330)
 
 - **Date:** January 25, 2024
-- **Details:** Anomalib recived the passing grade for the [Open Source Initiative Best Practices Badge](https://opensource.org/best-practices-badge). This badge recognizes our commitment to high-quality coding standards and community engagement.
+- **Details:** Anomalib received the passing grade for the [Open Source Initiative Best Practices Badge](https://opensource.org/best-practices-badge). This badge recognizes our commitment to high-quality coding standards and community engagement.
 
 [Learn more about this award](https://opensource.org/best-practices-badge)
 :::

docs/source/markdown/get_started/anomalib.md

@@ -253,7 +253,7 @@ By using the configuration file above, you can run the experiment with the follo
 
 Anomalib provides a benchmarking tool to evaluate the performance of the anomaly detection models on a given dataset. The benchmarking tool can be used to evaluate the performance of the models on a given dataset, or to compare the performance of multiple models on a given dataset.
 
-Each model in anomalib is benchmarked on a set of datasets, and the results are available in `src/anomalib/models/<model_name>README.md`. For example, the MVTec AD results for the Patchcore model are available in the corresponding [README.md](https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/patchcore#mvtec-ad-dataset) file.
+Each model in anomalib is benchmarked on a set of datasets, and the results are available in `src/anomalib/models/<model_name>README.md`. For example, the MVTec AD results for the Patchcore model are available in the corresponding [README.md](https://github.com/openvinotoolkit/anomalib/tree/main/src/anomalib/models/image/patchcore#mvtec-ad-dataset) file.
 
 ::::{tab-set}
 

notebooks/100_datamodules/README.md

@@ -1,11 +1,11 @@
 # Anomalib DataModules Tutorial
 
-| Notebook | GitHub                                         | Colab                                                                                                                                                                                                |
-| -------- | ---------------------------------------------- | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| BTech    | [101_btech](100_datamodules/101_btech.ipynb)   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/101_btech.ipynb)  |
-| MVTec    | [102_mvtec](100_datamodules/102_mvtec.ipynb)   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/102_mvtec.ipynb)  |
-| Folder   | [103_folder](100_datamodules/103_folder.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/103_folder.ipynb) |
-| Tiling   | [104_tiling](100_datamodules/104_tiling.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/104_tiling.ipynb) |
+| Notebook | GitHub                         | Colab                                                                                                                                                                                                |
+| -------- | ------------------------------ | ---------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
+| BTech    | [101_btech](101_btech.ipynb)   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/101_btech.ipynb)  |
+| MVTec    | [102_mvtec](102_mvtec.ipynb)   | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/102_mvtec.ipynb)  |
+| Folder   | [103_folder](103_folder.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/103_folder.ipynb) |
+| Tiling   | [104_tiling](104_tiling.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/100_datamodules/104_tiling.ipynb) |
 
 ## Notebook Contents
 

notebooks/500_use_cases/501_dobot/README.md

@@ -54,9 +54,9 @@ d. Then, replace those coordinates in the notebook
 
 ### Data acquisition and inferencing
 
-For data acquisition and inferencing we will use [501b notebook](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/500_use_cases/501_dobot/501_dobot/501b_inference_with_a_robotic_arm.ipynb). There we need to identify the `acquisition` flag, **True** for _acquisition mode_ and **False** for _inferencing mode_. In acquisition mode be aware of the _normal_ or _abnormal_ folder we want to create, in this mode the notebook will save every image in the anomalib/datasets/cubes/{FOLDER} for further training. In inferencing mode the notebook won't save images, it will run the inference and show the results.
+For data acquisition and inferencing we will use [501b notebook](501b_inference_with_a_robotic_arm.ipynb). There we need to identify the `acquisition` flag, **True** for _acquisition mode_ and **False** for _inferencing mode_. In acquisition mode be aware of the _normal_ or _abnormal_ folder we want to create, in this mode the notebook will save every image in the anomalib/datasets/cubes/{FOLDER} for further training. In inferencing mode the notebook won't save images, it will run the inference and show the results.
 
-_Note_: If you dont have the robot you could jump to the another notebook [501a](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/500_use_cases/501_dobot/501a_training_a_model_with_cubes_from_a_robotic_arm.ipynb) and download the dataset from this [link](https://github.com/openvinotoolkit/anomalib/releases/tag/dobot)
+_Note_: If you dont have the robot you could jump to the another notebook [501a](501a_training_a_model_with_cubes_from_a_robotic_arm.ipynb) and download the dataset from this [link](https://github.com/openvinotoolkit/anomalib/releases/tag/dobot)
 
 ### Training
 

notebooks/README.md

@@ -39,22 +39,15 @@ To install Python, Git and other required tools, [OpenVINO Notebooks](https://gi
 | -------- | --------------------------------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
 | Model    | [201_fastflow](200_models/201_fastflow.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/200_models/201_fastflow.ipynb) |
 
-## 3. Benchmarking and Hyperparameter Optimization
+## 3. OpenVINO Optimization
 
-| Notebook       | GitHub                                                      | Colab                                                                                                                                                                                                       |
-| -------------- | ----------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- |
-| Benchmarking   | [301_benchmarking](300_benchmarking/301_benchmarking.ipynb) | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/300_benchmarking/301_benchmarking.ipynb) |
-| HPO with wandb | [302_hpo_wandb](300_benchmarking/302_hpo_wandb.ipynb)       | [![Open In Colab](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/openvinotoolkit/anomalib/blob/main/notebooks/300_benchmarking/302_hpo_wandb.ipynb)    |
+| Notebook     | GitHub                                             | Colab |
+| ------------ | -------------------------------------------------- | ----- |
+| Quantization | [401_NNCF](/notebooks/400_openvino/401_nncf.ipynb) |       |
 
-## 4. OpenVINO Optimization
+## 4. Use cases
 
-| Notebook     | GitHub                                                                                                  | Colab |
-| ------------ | ------------------------------------------------------------------------------------------------------- | ----- |
-| Quantization | [401_NNCF](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/400_openvino/401_nncf.ipynb) |       |
-
-## 3. Use cases
-
-| Notebook               | GitHub                                                                                                                                                             | Colab |
-| ---------------------- | ------------------------------------------------------------------------------------------------------------------------------------------------------------------ | ----- |
-| Dobot Dataset Creation | [501a_training](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/500_use_cases/501_dobot/501a_training_a_model_with_cubes_from_a_robotic_arm.ipynb) |       |
-| Training               | [501b_training](https://github.com/openvinotoolkit/anomalib/blob/main/notebooks/500_use_cases/501_dobot/501b_inference_with_a_robotic_arm.ipynb)                   |       |
+| Notebook               | GitHub                                                                                                        | Colab |
+| ---------------------- | ------------------------------------------------------------------------------------------------------------- | ----- |
+| Dobot Dataset Creation | [501a_training](/notebooks/500_use_cases/501_dobot/501a_training_a_model_with_cubes_from_a_robotic_arm.ipynb) |       |
+| Training               | [501b_training](/notebooks/500_use_cases/501_dobot/501b_inference_with_a_robotic_arm.ipynb)                   |       |

pyproject.toml

@@ -246,3 +246,13 @@ source = ["src", ".tox/*/site-packages"]
 # NBQA CONFIGURATION                                                          #
 [tool.nbqa.addopts]
 ruff = ["--ignore=E402"]
+
+# # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # # #
+# LINK CHECKER CONFIGURATION                                                  #
+[tool.md_dead_link_check]
+exclude_links = [
+    "https://github.com/openvinotoolkit/anomalib/settings/actions/runners/new",
+    "https://openvinotoolkit.github.io/anomalib/*", # Remove it after publish documentation
+]
+exclude_files = ["docs/*"]
+force_get_requests_for_links = ["https://secure.ethicspoint.com/*"]

src/anomalib/data/base/video.py

@@ -10,6 +10,7 @@
 import torch
 from pandas import DataFrame
 from torchvision.transforms.v2 import Transform
+from torchvision.transforms.v2.functional import to_dtype_video
 from torchvision.tv_tensors import Mask
 
 from anomalib import TaskType
@@ -153,6 +154,7 @@ def __getitem__(self, index: int) -> dict[str, str | torch.Tensor]:
             msg = "self.indexer must be an instance of ClipsIndexer."
             raise TypeError(msg)
         item = self.indexer.get_item(index)
+        item["image"] = to_dtype_video(video=item["image"], scale=True)
         # include the untransformed image for visualization
         item["original_image"] = item["image"].to(torch.uint8)
 

src/anomalib/deploy/inferencers/openvino_inferencer.py

@@ -15,6 +15,7 @@
 from PIL import Image
 
 from anomalib import TaskType
+from anomalib.data.utils.label import LabelName
 from anomalib.utils.visualization import ImageResult
 
 from .base_inferencer import Inferencer
@@ -253,7 +254,7 @@ def post_process(self, predictions: np.ndarray, metadata: dict | DictConfig | No
 
         # Initialize the result variables.
         anomaly_map: np.ndarray | None = None
-        pred_label: float | None = None
+        pred_label: LabelName | None = None
         pred_mask: float | None = None
 
         # If predictions returns a single value, this means that the task is
@@ -270,7 +271,8 @@ def post_process(self, predictions: np.ndarray, metadata: dict | DictConfig | No
         # label to the prediction if the prediction score is greater
         # than the image threshold.
         if "image_threshold" in metadata:
-            pred_label = pred_score >= metadata["image_threshold"]
+            pred_idx = pred_score >= metadata["image_threshold"]
+            pred_label = LabelName.ABNORMAL if pred_idx else LabelName.NORMAL
 
         if task == TaskType.CLASSIFICATION:
             _, pred_score = self._normalize(pred_scores=pred_score, metadata=metadata)