Migrasi otomatis

.gitattributes

@@ -33,3 +33,9 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+caformer_s36_v0_focal/plot_sample_corrupted.png filter=lfs diff=lfs merge=lfs -text
+caformer_s36_v0_focal/plot_sample_normal.png filter=lfs diff=lfs merge=lfs -text
+caformer_s36_v0_sce/plot_sample_corrupted.png filter=lfs diff=lfs merge=lfs -text
+caformer_s36_v0_sce/plot_sample_normal.png filter=lfs diff=lfs merge=lfs -text
+mobilenetv3_v0_focal_dist/plot_sample_corrupted.png filter=lfs diff=lfs merge=lfs -text
+mobilenetv3_v0_focal_dist/plot_sample_normal.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,56 @@
+---
+license: openrail
+metrics:
+- accuracy
+pipeline_tag: image-classification
+tags:
+- art
+datasets:
+- deepghs/ai_image_corrupted
+library_name: dghs-imgutils
+---
+
+This is the classifier model for predicting the anime-style stable-diffusion-generated images are corrupted or not.
+
+Trained on dataset [deepghs/ai_image_corrupted](https://huggingface.co/datasets/deepghs/ai_image_corrupted).
+
+## Models
+
+|           Name            |  FLOPS  |  Params  |  Accuracy  |  AUC   |                                                       Confusion                                                       |        Labels         |
+|:-------------------------:|:-------:|:--------:|:----------:|:------:|:---------------------------------------------------------------------------------------------------------------------:|:---------------------:|
+|   caformer_s36_v0_focal   | 22.10G  |  37.21M  |   95.65%   | 0.9916 |   [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/caformer_s36_v0_focal/plot_confusion.png)   | `corrupted`, `normal` |
+|    caformer_s36_v0_sce    | 22.10G  |  37.21M  |   95.77%   | 0.9894 |    [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/caformer_s36_v0_sce/plot_confusion.png)    | `corrupted`, `normal` |
+| mobilenetv3_v0_focal_dist |  0.63G  |  4.18M   |   94.02%   | 0.9842 | [confusion](https://huggingface.co/deepghs/ai_image_corrupted/blob/main/mobilenetv3_v0_focal_dist/plot_confusion.png) | `corrupted`, `normal` |
+
+## How to Use
+
+You can use this model with [dghs-imgutils](https://dghs-imgutils.deepghs.org/main/api_doc/generic/classify.html).
+
+```python
+from imgutils.generic import classify_predict_score
+
+classify_predict_score(
+    'sample_image.png',
+    repo_id='deepghs/ai_image_corrupted',
+    model_name='mobilenetv3_v0_focal_dist',
+)
+# {'corrupted': 0.7807788848876953, 'normal': 0.2192210853099823}
+```
+
+## Note
+
+This model is trained on SD1.5 images, generated by 8 different base models.
+
+So the better solution for this problem is to use some metrics like artstyle embeddings, 
+this model will be deprecated as soon as the artstyle embedding model for anime images is completed.
+
+## Citation
+
+```
+@misc{Citation,
+  title={AI-Corrupt Score for Anime Images},
+  author={narugo1992},
+  year={2023},
+  howpublished={\url{https://huggingface.co/deepghs/ai_image_corrupted}}
+}
+```

caformer_s36_v0_focal/meta.json

@@ -0,0 +1,8 @@
+{
+    "labels": [
+        "corrupted",
+        "normal"
+    ],
+    "name": "caformer_s36.sail_in22k_ft_in1k_384",
+    "pretrained": true
+}

caformer_s36_v0_focal/metrics.json

@@ -0,0 +1,7 @@
+{
+    "AUC": 0.9915877002300404,
+    "accuracy": 0.9565287458200717,
+    "loss": 0.05786754996883977,
+    "mAP": 0.9916107790832838,
+    "step": 15
+}

caformer_s36_v0_focal/model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3268bf90847025ada0cc41a417d3dcb1e07b688a8f15e71f25bc8a84a0d9d7e6
+size 164417583

caformer_s36_v0_focal/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ae63bb14ab822916f2aec79eaf376488c452b95f6e7abc0e02fad27b1a13b5b4
+size 149574704

caformer_s36_v0_sce/meta.json

@@ -0,0 +1,8 @@
+{
+    "labels": [
+        "corrupted",
+        "normal"
+    ],
+    "name": "caformer_s36.sail_in22k_ft_in1k_384",
+    "pretrained": true
+}

caformer_s36_v0_sce/metrics.json

@@ -0,0 +1,7 @@
+{
+    "AUC": 0.9893911724263327,
+    "accuracy": 0.9576568228516176,
+    "loss": 0.4203899436304823,
+    "mAP": 0.9892099839602968,
+    "step": 46
+}

caformer_s36_v0_sce/model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1e8d5d4946c776d441f26087b74f7ca488e5e929a2908421da54fdfc9a218fe1
+size 164432367

caformer_s36_v0_sce/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:42a6cbf35bc99bfe03ca8ad44c842cbef5be8f4fe5cc5dcf981ba9d1a0cb183f
+size 149574704

mobilenetv3_v0_focal_dist/meta.json

@@ -0,0 +1,8 @@
+{
+    "labels": [
+        "corrupted",
+        "normal"
+    ],
+    "name": "mobilenetv3_large_100",
+    "pretrained": true
+}

mobilenetv3_v0_focal_dist/metrics.json

@@ -0,0 +1,7 @@
+{
+    "AUC": 0.9841517762780874,
+    "accuracy": 0.940211917328069,
+    "cls_loss": 0.11884625564264313,
+    "mAP": 0.9840327226113071,
+    "step": 48
+}

mobilenetv3_v0_focal_dist/model.ckpt

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:51595a9c67e854ff9e9365875bf9e0bd8104af3194e29a9290d1701f17af7968
+size 32056971

mobilenetv3_v0_focal_dist/model.onnx

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b1b50ff2d97a3d67dd6d8dd3d88efed71514ae81c5769729d8a4ff5f9607b7d
+size 16822434