Moveread OCR model, in tensorflow
Project description
Moveread OCR
CLIs
Data Exporting
ocr records boxes 'data/ocr-dataset/**/*' -vo path/to/tfrecords
ocr records samples 'data/ocr-dataset/**/*' -vo path/to/tfrecords
Inference
ocr predict -v --weights model.weights.h5 --data path/to/tfrecords > top-preds.ndjson
Finetuning
ocr finetune -vw model.weights.h5 --train path/to/tfrecords --val path/to/tfrecords \
--epochs 20 --batch-size 32 --lr 0.001
Evaluation
ocr evaluate -vw model.weights.h5 -d path/to/tfrecords
Serving Export
ocr export -vw model.weights.h5 -o path/to/SavedModel
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
moveread_ocr-0.1.11.tar.gz
(11.5 kB
view hashes)
Built Distribution
Close
Hashes for moveread_ocr-0.1.11-py3-none-any.whl
Algorithm | Hash digest | |
---|---|---|
SHA256 | f0457ac46f65f6878afca4f5e7b8cc4ed06ede1c4f7c0fa06ec6a89e1c775a79 |
|
MD5 | 63cdc95c8f5315cc9bd63de28050871b |
|
BLAKE2b-256 | 0fa7e94a720d87e4b8d5ac632b6a673afb72d43bcb76d6d1cfbe1b2f18ece429 |