nameplate
motor-nameplate
Motor Nameplate
A small image dataset of electric motor nameplates collected from public Google Images results, intended for tasks such as:
Training OCR / document-understanding models to extract nameplate text fields (manufacturer, HP, RPM, voltage, frame, etc.)
Image classification by manufacturer (ABB, Siemens, Baldor-Reliance, WEG, Hyundai, etc.)
Object detection (locating the plate on the motor body)
Few-shot learning / evaluation baselines for industrial vision tasks
The… See the full description on the dataset page: https://huggingface.co/datasets/sergiudanstan/motor-nameplate.motor-nameplate-labels
Motor Nameplate — Auto-Labeled (OCR + Qwen2.5-1.5B)
Motor Nameplate — Auto-Labeled (OCR + Qwen2.5-1.5B)
A derived dataset that adds structured field annotations to the
sergiudanstan/motor-nameplate
image collection (286 motor-nameplate photos from Google Images).
The original upstream dataset ships images only. This repo adds an
auto-labeling pipeline output, ready for downstream fine-tuning of a
vision-language model for nameplate field extraction.… See the full description on the dataset page: https://huggingface.co/datasets/sergiudanstan/motor-nameplate-labels.nameplate1
Nameplate Detection Dataset
This dataset contains 1000 images for object detection of nameplates and related warning signs.
Dataset Details
Total Images: 1000
Classes: 4 (nameplate, w, warning, yellow)
Train: 702 images
Validation: 149 images
Test: 149 images
Usage
from datasets import load_dataset
# Load the dataset
dataset = load_dataset("kahua-ml/nameplate1")
# Access splits
train_data = dataset["train"]
val_data = dataset["valid"]
test_data =… See the full description on the dataset page: https://huggingface.co/datasets/kahua-ml/nameplate1.nameplate_datasetnameplates-v2nameplate_sample2
Nameplates OCR
Image-to-text dataset of nameplates, merged from local folders and/or Hugging
Face datasets and built with create_dataset.py. Text-less images were
auto-captioned with EasyOCR; sources with a text/metadata column use that text
(flattened to plain-text lines for consistency).
Dataset structure
Split
Images
train
24
test
6
Each row: {"image": <PIL.Image>, "text": "..."}.
Usage
from datasets import load_dataset
dataset… See the full description on the dataset page: https://huggingface.co/datasets/darjja/nameplate_sample2.