Ccip Onnx
| Model | F1 Score | Precision | Recall | Threshold | Cluster2 | ClusterFree | | ccip-caformerb36-24 | 0.940925 | 0.938254 | 0.943612 | 0.213231 | 0.89508 | 0.957017 | | ccip-caformer-24-randaug-pruned | 0.917211 |...
Source du modèle
- Type
- Other
- Taille du fichier
- 1,58 KB–375 MB
- Modèle de base
- deepghs/ccip
- Version
- vRevision 1bf18c3
- Mis à jour
- 17 sept. 2026
- Téléchargements
- 0
- Source
- Hugging Face
Description de la source
| Model | F1 Score | Precision | Recall | Threshold | Cluster_2 | Cluster_Free |
|---|---|---|---|---|---|---|
| ccip-caformer_b36-24 | 0.940925 | 0.938254 | 0.943612 | 0.213231 | 0.89508 | 0.957017 |
| ccip-caformer-24-randaug-pruned | 0.917211 | 0.933481 | 0.901499 | 0.178475 | 0.890366 | 0.922375 |
| ccip-v2-caformer_s36-10 | 0.906422 | 0.932779 | 0.881513 | 0.207757 | 0.874592 | 0.89241 |
| ccip-caformer-6-randaug-pruned_fp32 | 0.878403 | 0.893648 | 0.863669 | 0.195122 | 0.810176 | 0.897904 |
| ccip-caformer-5_fp32 | 0.864363 | 0.90155 | 0.830121 | 0.183973 | 0.792051 | 0.862289 |
| ccip-caformer-4_fp32 | 0.844967 | 0.870553 | 0.820842 | 0.18367 | 0.795565 | 0.868133 |
| ccip-caformer_query-12 | 0.823928 | 0.871122 | 0.781585 | 0.141308 | 0.787237 | 0.809426 |
| ccip-caformer-23_randaug_fp32 | 0.81625 | 0.854134 | 0.781585 | 0.136797 | 0.745697 | 0.8068 |
| ccip-caformer-2-randaug-pruned_fp32 | 0.78561 | 0.800148 | 0.771592 | 0.171053 | 0.686617 | 0.728195 |
| ccip-caformer-2_fp32 | 0.755125 | 0.790172 | 0.723055 | 0.141275 | 0.64977 | 0.718516 |
- The calculation of
F1 Score,Precision, andRecallconsiders "the characters in both images are the same" as a positive case.Thresholdis determined by finding the maximum value on the F1 Score curve. Cluster_2represents the approximate optimal clustering solution obtained by tuning the eps value in DBSCAN clustering algorithm with min_samples set to2, and evaluating the similarity between the obtained clusters and the true distribution using therandom_adjust_score.Cluster_Freerepresents the approximate optimal solution obtained by tuning themax_epsandmin_samplesvalues in the OPTICS clustering algorithm, and evaluating the similarity between the obtained clusters and the true distribution using therandom_adjust_score.
Sources
1 source
Sources
1 sourceVérifié 3 sept.
Download files
Artefacts du modèle
30 artefacts
Artefacts du modèle
30 artefactsccip-caformer_b36-24/model_feat.onnx
onnx · 366 MB · SHA-256 c1e7333a55c2…ee51 · Hugging Face
Download fileccip-caformer_b36-24/model_metrics.onnx
onnx · 1,58 KB · SHA-256 816f291e385e…b8e3 · Hugging Face
Download fileccip-caformer_b36-24/model.ckpt
ckpt · 375 MB · SHA-256 59697c30407e…bc6e · Hugging Face
Download fileccip-caformer_query-12/model_feat.onnx
onnx · 147 MB · SHA-256 6f25626eb6d8…481f · Hugging Face
Download fileccip-caformer_query-12/model_metrics.onnx
onnx · 1,58 KB · SHA-256 1cb2f3799555…e878 · Hugging Face
Download fileccip-caformer_query-12/model.ckpt
ckpt · 151 MB · SHA-256 0dca380c0895…a0f8 · Hugging Face
Download fileccip-caformer-2_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 dedc0753729e…485e · Hugging Face
Download fileccip-caformer-2_fp32/model_metrics.onnx
onnx · 1,61 KB · SHA-256 198c03a4fbb3…a7fc · Hugging Face
Download fileccip-caformer-2_fp32/model.ckpt
ckpt · 147 MB · SHA-256 da3f2259194f…76a6 · Hugging Face
Download fileccip-caformer-2-randaug-pruned_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 e872215c3485…b0b0 · Hugging Face
Download fileccip-caformer-2-randaug-pruned_fp32/model_metrics.onnx
onnx · 1,58 KB · SHA-256 fe02ef58b65e…8b4a · Hugging Face
Download fileccip-caformer-2-randaug-pruned_fp32/model.ckpt
ckpt · 147 MB · SHA-256 54e852a076b8…a593 · Hugging Face
Download fileccip-caformer-23_randaug_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 50f091641523…63f6 · Hugging Face
Download fileccip-caformer-23_randaug_fp32/model_metrics.onnx
onnx · 1,61 KB · SHA-256 78f063dfe283…021f · Hugging Face
Download fileccip-caformer-23_randaug_fp32/model.ckpt
ckpt · 147 MB · SHA-256 1d4be57ea1c6…e48e · Hugging Face
Download fileccip-caformer-24-randaug-pruned/model_feat.onnx
onnx · 143 MB · SHA-256 4ea118d16496…ac5f · Hugging Face
Download fileccip-caformer-24-randaug-pruned/model_metrics.onnx
onnx · 1,61 KB · SHA-256 7e4646fdfbe3…25c1 · Hugging Face
Download fileccip-caformer-24-randaug-pruned/model.ckpt
ckpt · 147 MB · SHA-256 c5fdd52d2086…170d · Hugging Face
Download fileccip-caformer-4_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 6fdf2464b242…2f86 · Hugging Face
Download fileccip-caformer-4_fp32/model_metrics.onnx
onnx · 1,58 KB · SHA-256 22694914204a…c594 · Hugging Face
Download fileccip-caformer-4_fp32/model.ckpt
ckpt · 147 MB · SHA-256 20358dc50565…124a · Hugging Face
Download fileccip-caformer-5_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 885f91acf5e7…09ea · Hugging Face
Download fileccip-caformer-5_fp32/model_metrics.onnx
onnx · 1,58 KB · SHA-256 b1d3bda200fa…2b77 · Hugging Face
Download fileccip-caformer-5_fp32/model.ckpt
ckpt · 147 MB · SHA-256 0d81470ab074…5d1c · Hugging Face
Download fileccip-caformer-6-randaug-pruned_fp32/model_feat.onnx
onnx · 143 MB · SHA-256 a0003a68df9b…599f · Hugging Face
Download fileccip-caformer-6-randaug-pruned_fp32/model_metrics.onnx
onnx · 1,61 KB · SHA-256 78b8c2d82385…6bf3 · Hugging Face
Download fileccip-caformer-6-randaug-pruned_fp32/model.ckpt
ckpt · 147 MB · SHA-256 30379b074304…33b3 · Hugging Face
Download fileccip-v2-caformer_s36-10/model_feat.onnx
onnx · 143 MB · SHA-256 484ad463f569…2628 · Hugging Face
Download fileccip-v2-caformer_s36-10/model_metrics.onnx
onnx · 1,58 KB · SHA-256 272eef9fe10b…44a5 · Hugging Face
Download fileccip-v2-caformer_s36-10/model.ckpt
ckpt · 147 MB · SHA-256 04e5c6636cdb…a410 · Hugging Face
Download fileExtraits de sources
2 extraits
Extraits de sources
2 extraits--- license: openrail datasets: - deepghs/character_similarity metrics: - f1 pipeline_tag: zero-shot-image-classification tags: - art base_model: deepghs/ccip --- | Model | F1 Score | Precision | Recall | Threshold | Cluster_2 | Cluster_Free | |:-----------------------------------:|:----------:|:-----------:|:--------:|:-----------:|:-----------:|:--------------:| | ccip-caformer_b36-24 | 0.940925 | 0.938254 | 0.943612 | 0.213231 | 0.89508 | 0.957017 | | ccip-caformer-24-randaug-pruned | 0.917211 | 0.933481 | 0.901499 | 0.178475 | 0.890366 | 0.922375 | | ccip-v2-caformer_s36-10 | 0.906422 | 0.932779 | 0.881513 | 0.207757 | 0.874592 | 0.89241 | | ccip-caformer-6-randaug-pruned_fp32 | 0.878403 | 0.893648 | 0.863669 | 0.195122 | 0.810176 | 0.897904 | | ccip-caformer-5_fp32 | 0.864363 | 0.90155 | 0.830121 | 0.183973 | 0.792051 | 0.862289 | | ccip-caformer-4_fp32 | 0.844967 | 0.870553 | 0.820842 | 0.18367 | 0.795565 | 0.868133 | | ccip-caformer_query-12 | 0.823928 | 0.871122 | 0.781585 | 0.141308 | 0.787237 | 0.809426 | | ccip-caformer-23_randaug_fp32 | 0.81625 | 0.854134 | 0.781585 | 0.136797 | 0.745697 | 0.8068 | | ccip-caformer-2-randaug-pruned_fp32 | 0.78561 | 0.800148 | 0.771592 | 0.171053 | 0.686617 | 0.728195 | | ccip-caformer-2_fp32 | 0.755125 | 0.790172 | 0.723055 | 0.141275 | 0.64977 | 0.718516 | * The calculation of `F1 Score`, `Precision`, and `Recall` considers "the characters in both images are the same" as a positive case. `Threshold` is determined by finding the maximum value on the F1 Score curve. * `Cluster_2` represents the approximate optimal clustering solution obtained by tuning the eps value in DBSCAN clustering algorithm with min_samples set to `2`, and evaluating the similarity between the obtained clusters and the true distribution using the `random_adjust_score`. * `Cluster_Free` represents the approximate optimal solution obtained by tuning the `max_eps` and `min_samples` values in the OPTICS clustering algorithm, and evaluating the similarity between the obtained clusters and the true distribution using the `random_adjust_score`.
Source context: 0 downloads · 0 likes · Pipeline zero-shot-image-classification · Repo Library-Mutsumi/ccip_onnx
