deepghs/monochrome_detect
By deepghs · ↓ 0 · ♥ 0 · Updated 2023-06-07
What's in this repo
This page lists the files in deepghs/monochrome_detect, including model.onnx and more.
- 8 ONNX models (.onnx files)
- 82 files, including 48 .png, 16 .json, 8 .ckpt, 8 .onnx, 1 .md
- Last updated 2023-06-07
ONNX files
| File | Size | Download |
|---|---|---|
| caformer_s36/model.onnx | — | Download |
| caformer_s36_plus/model.onnx | — | Download |
| caformer_s36_plus_safe2/model.onnx | — | Download |
| caformer_s36_safe2/model.onnx | — | Download |
| mobilenetv3_large_100/model.onnx | — | Download |
| mobilenetv3_large_100_dist/model.onnx | — | Download |
| mobilenetv3_large_100_dist_safe2/model.onnx | — | Download |
| mobilenetv3_large_100_safe2/model.onnx | — | Download |
How to use
These ONNX files can be loaded with ONNX Runtime. To inspect a model graph, upload the file to the Netron viewer. Download links point to the original files on Hugging Face.
README
The models used for determining whether an anime image is monochrome have a training size of 384.
| Model | FLOPs | Accuracy | Confusion Matrix | Description |
|---|---|---|---|---|
| caformer_s36 | 22.10G | 95.63% | Confusion Matrix | Model: caformer_s36 from timm |
| caformer_s36_safe2 | 22.10G | 95.52% | Confusion Matrix | Model: caformer_s36 from timm, which have better precision and lower recall than caformer_s36 |
| caformer_s36_plus | 22.10G | 97.31% | Confusion Matrix | Model: caformer_s36.sail_in22k_ft_in1k_384 pratrained from timm |
| caformer_s36_plus_safe2 | 22.10G | 97.09% | Confusion Matrix | Model: caformer_s36.sail_in22k_ft_in1k_384 pratrained from timm, which have better precision and lower recall than caformer_s36.sail_in22k_ft_in1k_384 |
| mobilenetv3_large_100 | 0.63G | 95.40% | Confusion Matrix | Model: mobilenetv3_large_100 from timm |
| mobilenetv3_large_100_dist | 0.63G | 96.30% | Confusion Matrix | Distillated from caformer_s36_plus, using mobilenetv3_large_100 |
| mobilenetv3_large_100_safe2 | 0.63G | 94.62% | Confusion Matrix | Model: mobilenetv3_large_100 from timm, which have better precision and lower recall than mobilenetv3_large_100 |
| mobilenetv3_large_100_dist_safe2 | 0.63G | 95.85% | Confusion Matrix | Distillated from caformer_s36_plus_safe2, using mobilenetv3_large_100 |
Model info
onnx
art
image-classification
dataset:deepghs/monochrome_danbooru
license:mit
region:us
↓ 0
♥ 0
Created: 2023-06-02
Updated: 2023-06-07
View on Hugging FaceFiles (82)
.gitattributes
README.md
caformer_s36/meta.json
caformer_s36/metrics.json
caformer_s36/model.ckpt
caformer_s36/model.onnx
ONNX
caformer_s36/plot_confusion.png
caformer_s36/plot_f1_curve.png
caformer_s36/plot_p_curve.png
caformer_s36/plot_pr_curve.png
caformer_s36/plot_r_curve.png
caformer_s36/plot_roc_curve.png
caformer_s36_plus/meta.json
caformer_s36_plus/metrics.json
caformer_s36_plus/model.ckpt
caformer_s36_plus/model.onnx
ONNX
caformer_s36_plus/plot_confusion.png
caformer_s36_plus/plot_f1_curve.png
caformer_s36_plus/plot_p_curve.png
caformer_s36_plus/plot_pr_curve.png
caformer_s36_plus/plot_r_curve.png
caformer_s36_plus/plot_roc_curve.png
caformer_s36_plus_safe2/meta.json
caformer_s36_plus_safe2/metrics.json
caformer_s36_plus_safe2/model.ckpt
caformer_s36_plus_safe2/model.onnx
ONNX
caformer_s36_plus_safe2/plot_confusion.png
caformer_s36_plus_safe2/plot_f1_curve.png
caformer_s36_plus_safe2/plot_p_curve.png
caformer_s36_plus_safe2/plot_pr_curve.png
caformer_s36_plus_safe2/plot_r_curve.png
caformer_s36_plus_safe2/plot_roc_curve.png
caformer_s36_safe2/meta.json
caformer_s36_safe2/metrics.json
caformer_s36_safe2/model.ckpt
caformer_s36_safe2/model.onnx
ONNX
caformer_s36_safe2/plot_confusion.png
caformer_s36_safe2/plot_f1_curve.png
caformer_s36_safe2/plot_p_curve.png
caformer_s36_safe2/plot_pr_curve.png
caformer_s36_safe2/plot_r_curve.png
caformer_s36_safe2/plot_roc_curve.png
mobilenetv3_large_100/meta.json
mobilenetv3_large_100/metrics.json
mobilenetv3_large_100/model.ckpt
mobilenetv3_large_100/model.onnx
ONNX
mobilenetv3_large_100/plot_confusion.png
mobilenetv3_large_100/plot_f1_curve.png
mobilenetv3_large_100/plot_p_curve.png
mobilenetv3_large_100/plot_pr_curve.png
mobilenetv3_large_100/plot_r_curve.png
mobilenetv3_large_100/plot_roc_curve.png
mobilenetv3_large_100_dist/meta.json
mobilenetv3_large_100_dist/metrics.json
mobilenetv3_large_100_dist/model.ckpt
mobilenetv3_large_100_dist/model.onnx
ONNX
mobilenetv3_large_100_dist/plot_confusion.png
mobilenetv3_large_100_dist/plot_f1_curve.png
mobilenetv3_large_100_dist/plot_p_curve.png
mobilenetv3_large_100_dist/plot_pr_curve.png
mobilenetv3_large_100_dist/plot_r_curve.png
mobilenetv3_large_100_dist/plot_roc_curve.png
mobilenetv3_large_100_dist_safe2/meta.json
mobilenetv3_large_100_dist_safe2/metrics.json
mobilenetv3_large_100_dist_safe2/model.ckpt
mobilenetv3_large_100_dist_safe2/model.onnx
ONNX
mobilenetv3_large_100_dist_safe2/plot_confusion.png
mobilenetv3_large_100_dist_safe2/plot_f1_curve.png
mobilenetv3_large_100_dist_safe2/plot_p_curve.png
mobilenetv3_large_100_dist_safe2/plot_pr_curve.png
mobilenetv3_large_100_dist_safe2/plot_r_curve.png
mobilenetv3_large_100_dist_safe2/plot_roc_curve.png
mobilenetv3_large_100_safe2/meta.json
mobilenetv3_large_100_safe2/metrics.json
mobilenetv3_large_100_safe2/model.ckpt
mobilenetv3_large_100_safe2/model.onnx
ONNX
mobilenetv3_large_100_safe2/plot_confusion.png
mobilenetv3_large_100_safe2/plot_f1_curve.png
mobilenetv3_large_100_safe2/plot_p_curve.png
mobilenetv3_large_100_safe2/plot_pr_curve.png
mobilenetv3_large_100_safe2/plot_r_curve.png
mobilenetv3_large_100_safe2/plot_roc_curve.png