SKZ 3D Printing Defect Detection, Nozzle Camera: YOLO-Labeled FFF Print Errors

Provider
SKZ - Das Kunststoff-Zentrum
License
CC-BY-SA-4.0 (source)
Size
11,087 files
Format
PNG, CSV (in sampled files)
Stored at
Hugging Face (https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam)
Access
Free and public. No account with the data provider is needed.
Category
Computer Vision
Source
https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam

About SKZ 3D Printing Defect Detection, Nozzle Camera: YOLO-Labeled FFF Print Errors

Object detection images of fused filament fabrication (FFF) 3D printing captured by a camera mounted directly next to the nozzle of the printer, released by SKZ (Das Kunststoff-Zentrum, the German Plastics Center) from the BMBF-funded project on AI for automated error correction in additive manufacturing (grant 16IS23050B). Images are annotated with nine classes: nozzle, printed object, purge line, and the print defects spaghetti, stringing, under-extrusion (Unterextrusion), warping, poor first layer (schlechte erste Schicht) and double print. The repository holds 5,541 PNG images with matching YOLO label text files (class id and normalized box center, width and height), split into images/ and labels/ train, val and test folders, plus dataset.yaml and class and split summary CSVs; it trains directly with Ultralytics YOLO. Useful for in-situ process monitoring and defect detection in additive manufacturing. Licensed CC BY-SA 4.0 as stated in the dataset card; credit SKZ.

How to load this dataset in Python

import pandas as pd
df = pd.read_csv("hf://datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Nozzle_Cam/summary_classes.csv")
df.head()

Data structure

File types in sampled files: PNG, CSV

Files

Example file: summary_classes.csv

Analyze this dataset without downloading it

On Scigantic, SKZ 3D Printing Defect Detection, Nozzle Camera: YOLO-Labeled FFF Print Errors opens in a hosted JupyterLab notebook with the data already mounted, so you can read files where they are stored instead of copying them first. Each notebook includes an AI assistant that can see the mounted files and write and run analysis code. Open the dataset page to launch a notebook, or browse the full catalog.

This page is also available as Markdown and as JSON.

Related Computer Vision datasets