Hugging Face's logo

deepghs
/
ccip_onnx

Zero-Shot Image Classification
ONNX
art
Model card Files Community
narugo commited on
Commit
f086c37
·
1 Parent(s): 5ff000f

Update README.md

Browse files
Files changed (1) hide show
  1. README.md +6 -5
README.md CHANGED
@@ -11,14 +11,15 @@ tags:
11
 
12
  | Model | F1 Score | Precision | Recall | Threshold | Cluster_2 | Cluster_Free |
13
  |:-----------------------------------:|:----------:|:-----------:|:--------:|:-----------:|:-----------:|:--------------:|
14
- | ccip-caformer-2-randaug-pruned_fp32 | 0.78561 | 0.800148 | 0.771592 | 0.171053 | 0.686617 | 0.728195 |
15
- | ccip-caformer-23_randaug_fp32 | 0.81625 | 0.854134 | 0.781585 | 0.136797 | 0.745697 | 0.8068 |
16
  | ccip-caformer-24-randaug-pruned | 0.917211 | 0.933481 | 0.901499 | 0.178475 | 0.890366 | 0.922375 |
17
- | ccip-caformer-2_fp32 | 0.755125 | 0.790172 | 0.723055 | 0.141275 | 0.64977 | 0.718516 |
18
- | ccip-caformer-4_fp32 | 0.844967 | 0.870553 | 0.820842 | 0.18367 | 0.795565 | 0.868133 |
19
- | ccip-caformer-5_fp32 | 0.864363 | 0.90155 | 0.830121 | 0.183973 | 0.792051 | 0.862289 |
20
  | ccip-caformer-6-randaug-pruned_fp32 | 0.878403 | 0.893648 | 0.863669 | 0.195122 | 0.810176 | 0.897904 |
 
 
21
  | ccip-caformer_query-12 | 0.823928 | 0.871122 | 0.781585 | 0.141308 | 0.787237 | 0.809426 |
 
 
 
22
 
23
  * 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.
24
  * `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`.
 
11
 
12
  | Model | F1 Score | Precision | Recall | Threshold | Cluster_2 | Cluster_Free |
13
  |:-----------------------------------:|:----------:|:-----------:|:--------:|:-----------:|:-----------:|:--------------:|
14
+ | ccip-caformer_b36-24 | 0.940925 | 0.938254 | 0.943612 | 0.213231 | 0.89508 | 0.957017 |
 
15
  | ccip-caformer-24-randaug-pruned | 0.917211 | 0.933481 | 0.901499 | 0.178475 | 0.890366 | 0.922375 |
 
 
 
16
  | ccip-caformer-6-randaug-pruned_fp32 | 0.878403 | 0.893648 | 0.863669 | 0.195122 | 0.810176 | 0.897904 |
17
+ | ccip-caformer-5_fp32 | 0.864363 | 0.90155 | 0.830121 | 0.183973 | 0.792051 | 0.862289 |
18
+ | ccip-caformer-4_fp32 | 0.844967 | 0.870553 | 0.820842 | 0.18367 | 0.795565 | 0.868133 |
19
  | ccip-caformer_query-12 | 0.823928 | 0.871122 | 0.781585 | 0.141308 | 0.787237 | 0.809426 |
20
+ | ccip-caformer-23_randaug_fp32 | 0.81625 | 0.854134 | 0.781585 | 0.136797 | 0.745697 | 0.8068 |
21
+ | ccip-caformer-2-randaug-pruned_fp32 | 0.78561 | 0.800148 | 0.771592 | 0.171053 | 0.686617 | 0.728195 |
22
+ | ccip-caformer-2_fp32 | 0.755125 | 0.790172 | 0.723055 | 0.141275 | 0.64977 | 0.718516 |
23
 
24
  * 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.
25
  * `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`.