# brouillon_pour_mes_competitions — Data

来源：https://www.kaggle.com/competitions/brouillonpourmescompetitions/data

采集时间：2026-10-20T03:42:03Z

## Data:
In this competition, participants will have access to a meticulously curated dataset comprising 128 images of vias, each measuring 129x129 pixels in size, **note that in all the provided images the via is always located at the center of the image**. These images have been carefully selected to contain the characteristics of the "Alignment Offset Error".

## Ground Truth Data:
Accompanying the image dataset is a CSV file containing ground truth values for the evaluated area of the Alignment Offset Error, measured in **pixels**. This CSV file is linked with the names of the corresponding images, this provides the participants with the ability to use these labeled data to train a model if desired, to facilitate the process for the participants we have already split the data into training and testing subsets, that can be found in the following files:

*   **train.csv** - the training set
*   **test.csv** - the test set
*   **sample_submission.csv** - a sample submission file in the correct format. **note that you are required to provide values for the area of all provided images.**

**Columns**

*   `index` - name of the image
*   `area` - calculated area of Alignment Offset Error

**It is important to note that the CSV file named "Ground_Truth.csv" and therefore the combination of the "training.csv" and "testing.csv" contains ground truth values for only 102 images out of the total 128 images in the dataset**. This intentional omission of ground truth values for certain images serves two primary purposes: to facilitate model evaluation and validation and to discourage overfitting by penalizing models that rely excessively on the provided data. 

## Data Format:
Participants are welcome to utilize the provided CSV file to read the images as input data and extract the corresponding ground truth values for the evaluated area of Alignment Offset Error. The ultimate goal of this competition is to through the development of an algorithmic approach or training a machine learning model to predict the area of the Alignment Offset Error in nanometers within the images accurately.

## Image Format:
All images in the dataset are encoded in JPEG format, ensuring compatibility and ease of access for participants across various computational environments and platforms. 

## Conversion factor:
**The Ground Truth data provide the Misalignment error Area in pixels, in order to convert it and therefore get the area in nanometers participants can multiply their predictions by the current conversion factor:**
![](assets/aea8742589d8c30c5d1c6166.gif)

## The Expected Output:
Keep in mind that what is expected from the participants is to **provide either csv file or notebook** that would generate a file named **"submission.csv"** that should contain the predicted area in nanometers **for ALL the provided images**. Please refer to the provided "sample_submission.csv" file.