Hugging Face's logo

Library-Mutsumi
/
imgutils-models

ONNX
Model card Files
xet
 Community
Plana-Archive commited on
Commit
16a534b
·
verified ·
1 Parent(s): f586dea

Migrasi otomatis

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. README.md +51 -0
  2. anime_cls/anime_cls_mobilenetv3_large_100.ckpt +3 -0
  3. anime_cls/anime_cls_mobilenetv3_large_100.onnx +3 -0
  4. anime_cls/anime_cls_mobilenetv3_large_100_cm.png +0 -0
  5. anime_cls/anime_cls_mobilenetv3_large_100_f1.png +0 -0
  6. anime_cls/anime_cls_mobilenetv3_large_100_pr.png +0 -0
  7. anime_cls/anime_cls_mobilevitv2_150.ckpt +3 -0
  8. anime_cls/anime_cls_mobilevitv2_150.onnx +3 -0
  9. anime_cls/anime_cls_mobilevitv2_150_cm.png +0 -0
  10. anime_cls/anime_cls_mobilevitv2_150_f1.png +0 -0
  11. anime_cls/anime_cls_mobilevitv2_150_pr.png +0 -0
  12. ccip/ccip-caformer-23_randaug_fp32_feat.onnx +3 -0
  13. ccip/ccip-caformer-23_randaug_fp32_metrics.onnx +3 -0
  14. ccip/ccip-caformer-23_randaug_fp32_safe_metrics.onnx +3 -0
  15. ccip/ccip-caformer-2_fp32_feat.onnx +3 -0
  16. ccip/ccip-caformer-2_fp32_metrics.onnx +3 -0
  17. ccip/ccip-caformer-2_fp32_safe_metrics.onnx +3 -0
  18. ccip/ccip-caformer-4_fp32_feat.onnx +3 -0
  19. ccip/ccip-caformer-4_fp32_metrics.onnx +3 -0
  20. ccip/ccip-caformer-4_fp32_safe_metrics.onnx +3 -0
  21. ccip/ccip-caformer-5_fp32_feat.onnx +3 -0
  22. ccip/ccip-caformer-5_fp32_metrics.onnx +3 -0
  23. ccip/ccip-caformer-5_fp32_safe_metrics.onnx +3 -0
  24. deepdanbooru/deepdanbooru.onnx +3 -0
  25. deepdanbooru/deepdanbooru_tags.csv +0 -0
  26. face_detect/face_detect_best_n.onnx +3 -0
  27. face_detect/face_detect_best_n.pt +3 -0
  28. face_detect/face_detect_best_s.onnx +3 -0
  29. face_detect/face_detect_best_s.pt +3 -0
  30. face_detect/face_detect_v1_best_n.onnx +3 -0
  31. face_detect/face_detect_v1_best_n.pt +3 -0
  32. face_detect/face_detect_v1_best_s.onnx +3 -0
  33. face_detect/face_detect_v1_best_s.pt +3 -0
  34. head_detect/head_detect_best_n.onnx +3 -0
  35. head_detect/head_detect_best_n.pt +3 -0
  36. head_detect/head_detect_best_s.onnx +3 -0
  37. head_detect/head_detect_best_s.pt +3 -0
  38. lineart/hed.onnx +3 -0
  39. lineart/lineart.onnx +3 -0
  40. lineart/lineart_anime.onnx +3 -0
  41. lineart/lineart_coarse.onnx +3 -0
  42. lineart/pidi.onnx +3 -0
  43. lpips/lpips_diff.onnx +3 -0
  44. lpips/lpips_feature.onnx +3 -0
  45. manbits_detect/manbits_detect_best_m.onnx +3 -0
  46. manbits_detect/manbits_detect_best_m.pt +3 -0
  47. mldanbooru/mldanbooru_tags.csv +0 -0
  48. monochrome/monochrome-alexnet-480.ckpt +3 -0
  49. monochrome/monochrome-alexnet-480.onnx +3 -0
  50. monochrome/monochrome-caformer-110.ckpt +3 -0
README.md ADDED
@@ -0,0 +1,51 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ license: mit
3
+ datasets:
4
+ - deepghs/chafen_arknights
5
+ - deepghs/monochrome_danbooru
6
+ metrics:
7
+ - accuracy
8
+ ---
9
+
10
+ # imgutils-models
11
+
12
+ This repository includes all the models in [deepghs/imgutils](https://github.com/deepghs/imgutils).
13
+
14
+ ## LPIPS
15
+
16
+ This model is used for clustering anime images (named `差分` in Chinese), based on [richzhang/PerceptualSimilarity](https://github.com/richzhang/PerceptualSimilarity), trained with dataset [deepghs/chafen_arknights(private)](https://huggingface.co/datasets/deepghs/chafen_arknights).
17
+
18
+ When threshold is `0.45`, the [adjusted rand score](https://scikit-learn.org/stable/modules/generated/sklearn.metrics.adjusted_rand_score.html) can reach `0.995`.
19
+
20
+ File lists:
21
+ * `lpips_diff.onnx`, feature difference.
22
+ * `lpips_feature.onnx`, feature extracting.
23
+
24
+ ## Monochrome
25
+
26
+ These model is used for monochrome image classification, based on CNNs and Transformers, trained with dataset [deepghs/monochrome_danbooru(private)](https://huggingface.co/datasets/deepghs/monochrome_danbooru).
27
+
28
+ The following are the checkpoints that have been formally put into use, all based on the Caformer architecture:
29
+
30
+ | Checkpoint | Algorithm | Safe Level | Accuracy | False Negative | False Positive |
31
+ |:----------------------------:|:---------:|:----------:|:----------:|:--------------:|:--------------:|
32
+ | monochrome-caformer-40 | caformer | 0 | 96.41% | 2.69% | 0.89% |
33
+ | **monochrome-caformer-110** | caformer | 0 | **96.97%** | 1.57% | 1.46% |
34
+ | monochrome-caformer_safe2-80 | caformer | 2 | 94.84% | **1.12%** | 4.03% |
35
+ | monochrome-caformer_safe4-70 | caformer | 4 | 94.28% | **0.67%** | 5.04% |
36
+
37
+ **`monochrome-caformer-110` has the best overall accuracy** among them, but considering that this model is often used to screen out monochrome images
38
+ and we want to screen out as many as possible without omission, we have also introduced weighted models (`safe2` and `safe4`).
39
+ Although their overall accuracy has been slightly reduced, the probability of False Negative (misidentifying a monochrome image as a colored one) is lower,
40
+ making them more suitable for batch screening.
41
+
42
+ ## Deepdanbooru
43
+
44
+ `deepdanbooru` is a model used to tag anime images. Here, we provide a table for tag classification called `deepdanbooru_tags.csv`,
45
+ as well as an ONNX model (from [chinoll/deepdanbooru](https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags)).
46
+
47
+ It's worth noting that due to the poor quality of the deepdanbooru model itself and the relatively old dataset,
48
+ it is only for testing purposes and is not recommended to be used as the main classification model. We recommend using the `wd14` model instead, see:
49
+
50
+ * https://huggingface.co/spaces/SmilingWolf/wd-v1-4-tags
51
+
anime_cls/anime_cls_mobilenetv3_large_100.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0acba52703bc7421089c96daa72d5d313647ae46adb864b641ef2fbb64c6542e
3
+ size 27733899
anime_cls/anime_cls_mobilenetv3_large_100.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:003d9b264cb586cb548e6ef46716da1e54c4d1b8c619f176d28903613ef33a21
3
+ size 16832684
anime_cls/anime_cls_mobilenetv3_large_100_cm.png ADDED
anime_cls/anime_cls_mobilenetv3_large_100_f1.png ADDED
anime_cls/anime_cls_mobilenetv3_large_100_pr.png ADDED
anime_cls/anime_cls_mobilevitv2_150.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a1b92b1a2a967c68d2d266fe22b5a91ee0a56dfeafd4fbdff542d7a354ad862a
3
+ size 50238654
anime_cls/anime_cls_mobilevitv2_150.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:587e3fd3f155ca53a590bb95d934c39b6f547927bfc29b461a5aa9e40e5d8ad7
3
+ size 39426567
anime_cls/anime_cls_mobilevitv2_150_cm.png ADDED
anime_cls/anime_cls_mobilevitv2_150_f1.png ADDED
anime_cls/anime_cls_mobilevitv2_150_pr.png ADDED
ccip/ccip-caformer-23_randaug_fp32_feat.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:50f0916415237174ec116b119b0746ed5b62b755128b0ba966e88920dff263f6
3
+ size 150248245
ccip/ccip-caformer-23_randaug_fp32_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7276de446020f6c9e32aa829d0cce40cedc44c5467966ee5865ec0aa23cd9e80
3
+ size 1776
ccip/ccip-caformer-23_randaug_fp32_safe_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:256c3b40b3de4548d080fc560f542cb9f61d575727293c9a158a3850aa32f460
3
+ size 1776
ccip/ccip-caformer-2_fp32_feat.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dedc0753729eeb64b9d1813a02c343d28d4b68ff2c0c798a6850770ab41e485e
3
+ size 150248245
ccip/ccip-caformer-2_fp32_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4e17116bf070b6633e0e2d1d54b18df261b96b349e77a4f134b812d7d9bca20f
3
+ size 1776
ccip/ccip-caformer-2_fp32_safe_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:364b1caedd1a56891ce72f24634351fca1427cc9c63b35ffbfa497d40ea141a4
3
+ size 1776
ccip/ccip-caformer-4_fp32_feat.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6fdf2464b242e598c1f0bee9691564010f136218bcb739764b9fe6c353f92f86
3
+ size 150248245
ccip/ccip-caformer-4_fp32_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7f1772bb0bd2a75f169b758e7f912b97905fd2b90fa6c8519ac308684453fce9
3
+ size 1776
ccip/ccip-caformer-4_fp32_safe_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e056ce7793a846520c8d89d2c1e00b7d9b9bd9035fc83c1f119b717955fbc7a4
3
+ size 1776
ccip/ccip-caformer-5_fp32_feat.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:885f91acf5e77907c023b798d9250dfd11cf9b8960a5bd5af338d7160a9309ea
3
+ size 150248245
ccip/ccip-caformer-5_fp32_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:953ec103fdeebe2bc0e3d6365ad3a7fcb245b9a87350e730f61c9809b1c5252e
3
+ size 1776
ccip/ccip-caformer-5_fp32_safe_metrics.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:419c7c97229f3ac3237921abbf907a0ca32ad8bf51a394226b7252a03486637b
3
+ size 1776
deepdanbooru/deepdanbooru.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aeec8238fbd8f5e7e159408f84034adc41117aca65794b8a10fb5e967fc7398f
3
+ size 643993025
deepdanbooru/deepdanbooru_tags.csv ADDED
The diff for this file is too large to render. See raw diff
 
face_detect/face_detect_best_n.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d200a5be6a0836eaf71a0b782c81f82fefbe90cd155ad055d7b09991321247d
3
+ size 12103710
face_detect/face_detect_best_n.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:22c4db319644ce7fd3c1ebe17d2e6743cc6575d4903d8e70f8c846ef30b0bd9c
3
+ size 6229432
face_detect/face_detect_best_s.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e2c37b281bb0cf4310d9c58450bcbca4c64b7c67d197f0f3c51e9ad3128f78ed
3
+ size 44584381
face_detect/face_detect_best_s.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c2be793f34546561e15e93656622d58a30b655981ecb0fd730b287ae166923d7
3
+ size 22498424
face_detect/face_detect_v1_best_n.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:42f7ac57e815adfda3d3937804ead763fdb09f09a6f7393c445f25dd8ec5822c
3
+ size 12103713
face_detect/face_detect_v1_best_n.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8a6c1747d2adf7ceae53445fc67bebcd9992d406b8227dc7d98801fd386aea3b
3
+ size 6229432
face_detect/face_detect_v1_best_s.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4661a4a9a606059ba83eb97320c8a6c722f87ad54f61b24791184a49e88e5c7c
3
+ size 44584384
face_detect/face_detect_v1_best_s.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:eb46253698e91f40d88252674bbd230767681772e7f4d38da181b02dc5a31aa1
3
+ size 22498424
head_detect/head_detect_best_n.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3efaee5c5868e06c8098644fdacb7f82e646ffd80065c6eacdc26d4a0aea2a0d
3
+ size 12103709
head_detect/head_detect_best_n.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4d20309c8034262be0b23f11fb3df0a35948d93c39209c52a968f5ddf855a86b
3
+ size 24492066
head_detect/head_detect_best_s.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da2fd23f5191bbcfff4a5940ef96fca51255df57ff535bb6ab2f04a59e328133
3
+ size 44584380
head_detect/head_detect_best_s.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7f053e60d373c74f599fbdd95821cae0809422a004ec2c2fe66934e42071efa
3
+ size 22498616
lineart/hed.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c82bf74a9e1f2eeb428ff9f3be168931487eada6db68496dbb5e8124071cdac
3
+ size 59054159
lineart/lineart.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14570bc70981c7cab28dbd06938b7b25f4b3e969476e816f99cc39ecd8a1c820
3
+ size 17327508
lineart/lineart_anime.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7d0ae15de36f510b307eef3b2bce261f260286a025177f55c6f61c4e8992f709
3
+ size 217961700
lineart/lineart_coarse.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e32fc7b9ffd219ac38f6bd770c5d537c92f1038f81a6a258db03f4d0d501a64c
3
+ size 17327508
lineart/pidi.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:adcbba81749e9fb57a6340503482f0bcfad353bf34aed989f639a8e2436a350e
3
+ size 3384286
lpips/lpips_diff.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48372f400d1821eb8f39b49902c374b69a3a91ec5fd49e0401d666be1871c261
3
+ size 77096
lpips/lpips_feature.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fc131a6c6525e6f74e0cf8577046449312920e18d73f377900cd485dfe260051
3
+ size 9988398
manbits_detect/manbits_detect_best_m.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe92fbadaf682dfb5782130b2d2b0fc5317adae69149ab9c2b6b1e6bfa7be31
3
+ size 103472535
manbits_detect/manbits_detect_best_m.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16d9a51b5c5350809c44f42f6a62dc60f98bb61097ceea4e125e43586e8aa697
3
+ size 52012832
mldanbooru/mldanbooru_tags.csv ADDED
The diff for this file is too large to render. See raw diff
 
monochrome/monochrome-alexnet-480.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e61e4e88f79c5d371f1f6bf3a6693f5f2eb2f1f63c7f2568ccc458040fde6fde
3
+ size 88596035
monochrome/monochrome-alexnet-480.onnx ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:244a4b0bee5f9f654e6a1b8fe29ac319b0bf96cdc40656dd85242fe70ce8ef37
3
+ size 88661614
monochrome/monochrome-caformer-110.ckpt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:307e3d7d98e8606b25533cfdd94b7bf7b84a6ba3068f531f99c04cd45d2b49b4
3
+ size 149177147