Downloads · 30 days
0
Kanji_ETL8G
LT8/Kanji_ETL8G
Kanji_ETL8G is a machine learning model from LT8. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as creativeml-openrail-m.
Please use LT8/japanese-handwriting-onnx instead. It is a full rebuild from the raw ETL binaries, not a retrain of this model.
Access
Public
Updated Sep 17, 2026
Repo size
56.5 MB
Likes
1
Public
Repo makeup
Click a slice to open those files.
.pth28.2 MB · 50%
At a glance
- License
- creativeml-openrail-m
- Access
- Public
- Created
- Oct 27, 2023
- Updated
- Sep 17, 2026
- SHA
- 4aa8a31c
Model card
From the Hugging Face model README
Deprecated — superseded by LT8/japanese-handwriting-onnx
Please use LT8/japanese-handwriting-onnx instead. It is a full rebuild from the raw ETL binaries, not a retrain of this model.
| this model | the replacement | |
|---|---|---|
| classes | 956 | 3,082 — all JIS X 0208 Level 1 kanji, plus hiragana and katakana |
| preprocessing | yours to reimplement | compiled into the ONNX graph |
| evaluation | random split | writer-disjoint, plus a second corpus never trained on |
| accuracy | — | 99.79 % unseen writers · 98.98 % unseen corpus |
| batching | fixed at 1 | dynamic batch axis |
Why these files are kept but not recommended
Both artifacts here have problems that are awkward to work around:
kanji_ETL8G.pthdoes not load on current PyTorch. It was saved as a pickled whole model rather than astate_dict, sotorch.loadrefuses it under theweights_only=Truedefault and it depends on the original class definitions being importable.kanji_ETL8G.onnxtakes a flattened[1, 4096]vector, so the caller has to resize to 64×64, flatten, and match the original normalisation exactly — and the batch size is fixed at 1.
The replacement addresses both directly: weights are stored as plain tensors,
and the exported graph accepts an ordinary (N, 1, 128, 128) grayscale image
and does its own contrast normalisation, bounding box, padding and resize. There
is no preprocessing left for a caller to get wrong.
The files below are left in place so existing references keep resolving.
- License
- creativeml-openrail-m
- Created
- Oct 27, 2023
- Updated
- Sep 17, 2026