Hugging Face's logo

Shawon16
/
ViViT_BdSLW60_FrameRate_Corrected_with_Augment_20_epch

Video Classification
Transformers
Safetensors
vivit
Generated from Trainer
Model card Files
xet
 Community
Shawon16 commited on
Commit
bc86918
·
verified ·
1 Parent(s): f6c9a7f

Model save

Browse files
Files changed (2) hide show
  1. README.md +18 -20
  2. model.safetensors +1 -1
README.md CHANGED
@@ -21,11 +21,11 @@ should probably proofread and complete it, then remove this comment. -->
21
 
22
  This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
- - Loss: 0.4692
25
- - Accuracy: 0.875
26
- - Precision: 0.8880
27
- - Recall: 0.875
28
- - F1: 0.8618
29
 
30
  ## Model description
31
 
@@ -60,21 +60,19 @@ The following hyperparameters were used during training:
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
- | 4.2927 | 0.0501 | 929 | 1.3962 | 0.7483 | 0.7445 | 0.7483 | 0.7073 |
64
- | 0.5715 | 1.0501 | 1858 | 0.7387 | 0.76 | 0.7849 | 0.76 | 0.7316 |
65
- | 0.1143 | 2.0501 | 2787 | 0.5069 | 0.8567 | 0.8745 | 0.8567 | 0.8379 |
66
- | 0.1201 | 3.0501 | 3716 | 0.4372 | 0.8717 | 0.9010 | 0.8717 | 0.8671 |
67
- | 0.1384 | 4.0501 | 4645 | 0.8167 | 0.805 | 0.8275 | 0.805 | 0.7785 |
68
- | 0.0708 | 5.0501 | 5574 | 0.6928 | 0.8333 | 0.8539 | 0.8333 | 0.8178 |
69
- | 0.0305 | 6.0501 | 6503 | 0.6383 | 0.8467 | 0.8903 | 0.8467 | 0.8334 |
70
- | 0.074 | 7.0501 | 7432 | 0.8458 | 0.8383 | 0.8776 | 0.8383 | 0.8257 |
71
- | 0.1235 | 8.0501 | 8361 | 0.6183 | 0.8767 | 0.9065 | 0.8767 | 0.8666 |
72
- | 0.0735 | 9.0501 | 9290 | 0.6341 | 0.8883 | 0.9061 | 0.8883 | 0.8822 |
73
- | 0.0151 | 10.0501 | 10219 | 0.6098 | 0.8583 | 0.8840 | 0.8583 | 0.8457 |
74
- | 0.1384 | 11.0501 | 11148 | 0.9685 | 0.8233 | 0.8543 | 0.8233 | 0.7973 |
75
- | 0.0316 | 12.0501 | 12077 | 0.5841 | 0.8717 | 0.9142 | 0.8717 | 0.8558 |
76
- | 0.0196 | 13.0501 | 13006 | 0.5936 | 0.8583 | 0.8762 | 0.8583 | 0.8422 |
77
- | 0.0001 | 14.0501 | 13935 | 0.4692 | 0.875 | 0.8880 | 0.875 | 0.8618 |
78
 
79
 
80
  ### Framework versions
 
21
 
22
  This model is a fine-tuned version of [google/vivit-b-16x2-kinetics400](https://huggingface.co/google/vivit-b-16x2-kinetics400) on an unknown dataset.
23
  It achieves the following results on the evaluation set:
24
+ - Loss: 1.0009
25
+ - Accuracy: 0.8117
26
+ - Precision: 0.8529
27
+ - Recall: 0.8117
28
+ - F1: 0.7868
29
 
30
  ## Model description
31
 
 
60
 
61
  | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 |
62
  |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:|
63
+ | 4.1133 | 0.0501 | 929 | 1.3796 | 0.785 | 0.7920 | 0.785 | 0.7528 |
64
+ | 0.457 | 1.0501 | 1858 | 0.6823 | 0.805 | 0.8022 | 0.805 | 0.7825 |
65
+ | 0.127 | 2.0501 | 2787 | 0.4044 | 0.875 | 0.9070 | 0.875 | 0.8649 |
66
+ | 0.1407 | 3.0501 | 3716 | 0.5490 | 0.8817 | 0.9039 | 0.8817 | 0.8715 |
67
+ | 0.1246 | 4.0501 | 4645 | 0.7160 | 0.835 | 0.8687 | 0.835 | 0.8213 |
68
+ | 0.2027 | 5.0501 | 5574 | 0.7256 | 0.8383 | 0.8751 | 0.8383 | 0.8290 |
69
+ | 0.0732 | 6.0501 | 6503 | 0.5921 | 0.8533 | 0.8551 | 0.8533 | 0.8276 |
70
+ | 0.1227 | 7.0501 | 7432 | 0.4519 | 0.9133 | 0.9339 | 0.9133 | 0.9038 |
71
+ | 0.008 | 8.0501 | 8361 | 0.5257 | 0.8817 | 0.8921 | 0.8817 | 0.8718 |
72
+ | 0.0305 | 9.0501 | 9290 | 0.4730 | 0.875 | 0.9054 | 0.875 | 0.8693 |
73
+ | 0.0408 | 10.0501 | 10219 | 0.5418 | 0.8983 | 0.9046 | 0.8983 | 0.8842 |
74
+ | 0.1458 | 11.0501 | 11148 | 0.4162 | 0.9083 | 0.9324 | 0.9083 | 0.9006 |
75
+ | 0.0402 | 12.0501 | 12077 | 1.0009 | 0.8117 | 0.8529 | 0.8117 | 0.7868 |
 
 
76
 
77
 
78
  ### Framework versions
model.safetensors CHANGED
@@ -1,3 +1,3 @@
1
  version https://git-lfs.github.com/spec/v1
2
- oid sha256:525157efa30b68c1f934b6295bb8ab1214c0226aa0112750587b49638f02d229
3
  size 354793800
 
1
  version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b74fd13ae694d2bc49b5924b92dbeba85896ce38d6a47aa72b63db3904dfff2a
3
  size 354793800