{"success":true,"data":{"author":"SKZ - Das Kunststoff-Zentrum","bucketAccessType":"public","bucketName":"DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam","bucketPrefix":"","category":"Computer Vision","cloudProvider":"huggingface","createdAt":"2026-11-18T00:06:05.842Z","description":"Object detection images of fused filament fabrication (FFF) 3D printing captured by a camera viewing the whole build platform 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 3,145 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.","displayTitle":"SKZ 3D Printing Defect Detection, Platform Camera: YOLO-Labeled FFF Print Errors","huggingFaceUrl":"https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam","id":"07b800e6-7479-5f1a-b325-7aa6eea2e5c8","license":"CC-BY-SA-4.0","licenseEvidenceUrl":"https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam","objectCountEstimate":6295,"probeStatus":"ok","region":"us","schemaCard":{"accessHints":[{"language":"python-datasets","snippet":"from datasets import load_dataset\nds = load_dataset(\"DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam\")"},{"language":"python-hub","snippet":"from huggingface_hub import snapshot_download\nsnapshot_download(repo_id=\"DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam\", repo_type=\"dataset\")"}],"caveats":["HuggingFace metadata: author=DasKunststoffZentrumSKZ, license:cc, size_categories:10K<n<100K, format:text, downloads=462"],"format":"mixed","generatedAt":"2026-11-18T00:09:57.173Z","layout":{"example":"summary_classes.csv","pattern":"{repoId}/{filename}"},"mountPath":"/mnt/archive","sampleHeaders":[{"bytes":"class_name,count\r\nPurge Line,3634\r\nObject,3138\r\nSpaghetti,3094\r\nNozzle,3051\r\nUnterextrusion,278\r\nDouble Print,49\r\nStringing,29\r\nschlechte erste Schicht,21\r\n","encoding":"utf8","key":"summary_classes.csv","truncatedAt":512}],"sampleObjects":["dataset.yaml","images/test/Profile_180.0_0.8_50.0_100_20.0_0.1_180.0__89baa596-frame_01459.png","images/test/Profile_180.0_0.8_50.0_100_20.0_0.1_180.0__bb1eb04d-frame_03117.png","images/test/Profile_180.0_0.8_60.0_50_20.0_0.1_0.0__0d11c71e-frame_00133.png","images/test/Profile_180.0_0.8_60.0_50_20.0_0.1_0.0__1a392b1f-frame_00096.png"],"sidecars":[{"bytes":"---\r\nlicense: cc\r\ntask_categories:\r\n- object-detection\r\nlanguage:\r\n- en\r\ntags:\r\n- chemistry\r\npretty_name: Errors3DPrinting\r\nsize_categories:\r\n- 1K<n<10K\r\n---\r\n# Errors_Additive_Manufacturing_Plattform_Cam\r\n\r\n## 3D Printing Nozzle Camera – YOLO Object Detection Dataset\r\n\r\nThis Repository is part of the Project: Künstliche Intelligenz zur Automatiserten Fehlerkorrektur in der Additiven Fertigung(Förderkennzeichen: 16IS23050B).\r\n\r\n\r\nThis dataset contains images captured from a camera positioned to capture the whole plattform of a 3D printer.\r\nThe task is object detection of both regular print elements and typical printing defects.\r\n\r\nThe dataset is provided in standard YOLO format and can be used directly with Ultralytics YOLO.\r\n\r\n---\r\n\r\n## Content\r\n\r\nThe plattform camera captures:\r\n\r\n- Nozzle\r\n- Printed Object\r\n- Purge Line\r\n- Typical 3D printing defects\r\n- Spaghetti\r\n\r\n\r\n### Classes\r\n\r\n1. Nozzle\r\n2. Object\r\n3. Purge Line\r\n4. Spaghetti\r\n5. Stringing\r\n6. Unterextrusion\r\n7. Warping\r\n8. schlechte erste Schicht\r\n9. Double Print\r\n\r\nNumber of classes: 9\r\n\r\n---\r\n\r\n### Structure\r\n\r\n```\r\n\r\nErrors_Additive_Manufacturing_Plattform_Cam/\r\n│\r\n├── images/\r\n│   ├── train/\r\n│   ├── val/\r\n│   └── test/\r\n│\r\n├── labels/\r\n│   ├── train/\r\n│   ├── val/\r\n│   └── test/\r\n│\r\n├── dataset.yaml\r\n├── summary_classes.csv\r\n└── summary_splits.csv\r\n\r\n```\r\n\r\n---\r\n\r\n## YOLO Label Format\r\n\r\nEach image has a corresponding `.txt` annotation file.\r\n\r\n### Format per row\r\n\r\n```\r\n\r\n<class_id> <x_center> <y_center> <width> <height>\r\n\r\n```\r\n\r\n### Details\r\n\r\n- Coordinates are **normalized to [0,1]**\r\n- `class_id` corresponds to the class index defined in `dataset.yaml`\r\n- Multiple objects are stored as multiple rows in one file\r\n\r\n### Example\r\n\r\n```\r\n\r\n0 0.512 0.423 0.120 0.085\r\n3 0.621 0.558 0.210 0.175\r\n\r\n````\r\n\r\n---\r\n\r\n## Training with Ultralytics YOLO\r\n\r\nExample training script:\r\n\r\n```python\r\nfrom ultralytics import YOLO\r\n\r\nmodel = YOLO(\"yolov8n.pt\")  # or your pretrained checkpoint\r\n\r\ndata_path = \"dataset/dataset.yaml\"\r\n\r\nresults = model.train(\r\n    data=data_path,\r\n    epochs=100,\r\n    imgsz=640,\r\n    patience=15,\r\n    device=\"cuda\",\r\n    seed=42,\r\n    save=True,\r\n    name=\"model_finetuned\"\r\n)\r\n````\r\n\r\n---\r\n\r\n## Installation\r\n\r\n```bash\r\npip install ultralytics\r\n```\r\n\r\n---\r\n\r\n## Example dataset.yaml\r\n\r\n```yaml\r\npath: Errors_Additive_Manufacturing_Plattform_Cam\r\ntrain: images/train\r\nval: images/val\r\ntest: images/test\r\n\r\nnames:\r\n  0: error_type_1\r\n  1: error_type_2\r\n  2: error_type_3\r\n  3: error_type_4\r\n```\r\n\r\n---\r\n\r\n\r\n\r\n## Statistics\r\n\r\nIncluded summary files:\r\n\r\n- summary_splits.csv (images and boxes per split)\r\n- summary_classes.csv (class distribution)\r\n\r\n---\r\n\r\n## License\r\n\r\nCreative Commons Attribution-ShareAlike 4.0 (CC BY-SA 4.0)","encoding":"utf8","key":"README.md","name":"README.md","size":2829,"truncated":false}],"sourceObjectKey":"summary_classes.csv","starterCell":"import pandas as pd\ndf = pd.read_csv(\"hf://datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam/summary_classes.csv\")\ndf.head()","starterSamplePath":"images/test/Profile_180.0_0.8_50.0_100_20.0_0.1_180.0__89baa596-frame_01459.png","totalObjects":6295},"summary":"Object detection images of fused filament fabrication (FFF) 3D printing captured by a camera viewing the whole build platform of the printer, released by SKZ (Das…","title":"SKZ 3D Printing Defect Detection, Platform Camera: YOLO-Labeled FFF Print Errors","updatedAt":"2026-11-18T04:34:00.003Z","visibility":"public","websiteUrl":"https://huggingface.co/datasets/DasKunststoffZentrumSKZ/Errors_Additive_Manufacturing_Plattform_Cam"}}