Update README.md
Browse files
README.md
CHANGED
@@ -11,8 +11,8 @@ tags:
|
|
11 |
|
12 |
The models used for determining whether an anime image is monochrome have a training size of 384.
|
13 |
|
14 |
-
| Model | FLOPs |
|
15 |
-
|
16 |
-
| caformer_s36 | 22.10G |
|
17 |
-
| mobilenetv3_large_100 | 0.63G |
|
18 |
-
| mobilenetv3_large_100_safe2 | 0.63G |
|
|
|
11 |
|
12 |
The models used for determining whether an anime image is monochrome have a training size of 384.
|
13 |
|
14 |
+
| Model | FLOPs | Accuracy | Confusion Matrix | Description |
|
15 |
+
|:---------------------------:|:------:|:--------:|:--------------------------------------------------------------------------------------------------------------------------------:|-----------------------------------------------------------------------------------------------------------------|
|
16 |
+
| caformer_s36 | 22.10G | 95.63% | [Confusion Matrix](https://huggingface.co/deepghs/monochrome_detect/resolve/main/caformer_s36/plot_confusion.png) | Model: caformer_s36 from timm |
|
17 |
+
| mobilenetv3_large_100 | 0.63G | 95.40% | [Confusion Matrix](https://huggingface.co/deepghs/monochrome_detect/resolve/main/mobilenetv3_large_100/plot_confusion.png) | Model: mobilenetv3_large_100 from timm |
|
18 |
+
| mobilenetv3_large_100_safe2 | 0.63G | 94.62% | [Confusion Matrix](https://huggingface.co/deepghs/monochrome_detect/resolve/main/mobilenetv3_large_100_safe2/plot_confusion.png) | Model: mobilenetv3_large_100 from timm, which have better precision and lower recall than mobilenetv3_large_100 |
|