Aller au contenu
ModelPrésentéExterne
Télécharger

VideoMAE BdSLW60 FrameRate Corrected With Augment 20 Epoch

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on BdSLW60 dataset. It achieves the following results on the evaluation set (Val): Loss: 0.0299 Accuracy: 0.9965 Precision: 0.9967...

Sourcehuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch/tree/d8124540a887d1d7bcb7d6079a9bf8b8e685fd9d
TypeOtherModèle de baseMCG-NJU/videomae-base-finetuned-kineticsVersionRevision d812454BClasse

Source du modèle

Type
Other
Taille du fichier
329 MB
Modèle de base
MCG-NJU/videomae-base-finetuned-kinetics
Version
vRevision d812454
Mis à jour
3 nov. 2026
Téléchargements
9
Source
Hugging Face

Description de la source

VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch

This model is a fine-tuned version of MCG-NJU/videomae-base-finetuned-kinetics on BdSLW60 dataset. It achieves the following results on the evaluation set (Val):

  • Loss: 0.0299
  • Accuracy: 0.9965
  • Precision: 0.9967
  • Recall: 0.9965
  • F1: 0.9965

Model description

More information needed

Intended uses & limitations

More information needed

Training and evaluation data

More information needed

Training procedure

Training hyperparameters

The following hyperparameters were used during training:

  • learning_rate: 5e-05
  • train_batch_size: 2
  • eval_batch_size: 2
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 8
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • training_steps: 17940
  • mixed_precision_training: Native AMP

Training results

Training LossEpochStepValidation LossAccuracyPrecisionRecallF1
2.45650.058971.87060.59880.61860.59880.5527
0.59921.050017950.58770.84470.88210.84470.8382
0.16532.050026930.21130.94350.95390.94350.9428
0.1533.050035910.18340.95410.96150.95410.9543
0.05524.0544880.08520.98120.98340.98120.9812
0.08035.050053860.08950.97530.97750.97530.9753
0.04576.050062840.09840.97880.98060.97880.9788
0.04637.050071820.16750.96120.96580.96120.9614
0.00398.0580790.05450.98820.98910.98820.9882
0.01629.050089770.08910.98120.98270.98120.9809
0.032610.050098750.07420.98940.99040.98940.9895
0.027811.0500107730.08320.98120.98280.98120.9811
0.007812.05116700.06590.98820.98870.98820.9882
0.000413.0500125680.06930.98820.98890.98820.9882
0.002414.0500134660.05170.99410.99460.99410.9942
0.009415.0500143640.03270.99410.99440.99410.9941
0.000116.05152610.03420.99530.99560.99530.9953
0.000117.0500161590.03200.99530.99560.99530.9953
0.002518.0500170570.03170.99530.99550.99530.9953
0.000119.0492179400.02990.99650.99670.99650.9965

Framework versions

  • Transformers 4.44.2
  • Pytorch 2.4.1+cu121
  • Datasets 2.19.2
  • Tokenizers 0.19.1

Sources

1 source
Hugging FacePrincipalVersion d8124540a887d1d7bcb7d6079a9bf8b8e685fd9d
huggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch/tree/d8124540a887d1d7bcb7d6079a9bf8b8e685fd9d

Vérifié 3 nov.

Download files

Repository files

File inventory only; completeness is unverified.

Artefacts du modèle

1 artefact

model.safetensors

safetensors · FP32 (unverified) · 329 MB · SHA-256 4ed337bb5305…cb94 · Hugging Face

Download file

Extraits de sources

3 extraits
Readme21 aoûthuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch

--- library_name: transformers license: cc-by-nc-4.0 base_model: - MCG-NJU/videomae-base-finetuned-kinetics tags: - generated_from_trainer metrics: - accuracy - precision - recall - f1 model-index: - name: VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch results: [] --- <!-- This model card has been generated automatically according to the information the Trainer had access to. You should probably proofread and complete it, then remove this comment. --> # VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch This model is a fine-tuned version of [MCG-NJU/videomae-base-finetuned-kinetics](https://huggingface.co/MCG-NJU/videomae-base-finetuned-kinetics) on BdSLW60 dataset. It achieves the following results on the evaluation set (Val): - Loss: 0.0299 - Accuracy: 0.9965 - Precision: 0.9967 - Recall: 0.9965 - F1: 0.9965 ## Model description More information needed ## Intended uses & limitations More information needed ## Training and evaluation data More information needed ## Training procedure ### Training hyperparameters The following hyperparameters were used during training: - learning_rate: 5e-05 - train_batch_size: 2 - eval_batch_size: 2 - seed: 42 - gradient_accumulation_steps: 4 - total_train_batch_size: 8 - optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 - lr_scheduler_type: linear - lr_scheduler_warmup_ratio: 0.1 - training_steps: 17940 - mixed_precision_training: Native AMP ### Training results | Training Loss | Epoch | Step | Validation Loss | Accuracy | Precision | Recall | F1 | |:-------------:|:-------:|:-----:|:---------------:|:--------:|:---------:|:------:|:------:| | 2.4565 | 0.05 | 897 | 1.8706 | 0.5988 | 0.6186 | 0.5988 | 0.5527 | | 0.5992 | 1.0500 | 1795 | 0.5877 | 0.8447 | 0.8821 | 0.8447 | 0.8382 | | 0.1653 | 2.0500 | 2693 | 0.2113 | 0.9435 | 0.9539 | 0.9435 | 0.9428 | | 0.153 | 3.0500 | 3591 | 0.1834 | 0.9541 | 0.9615 | 0.9541 | 0.9543 | | 0.0552 | 4.05 | 4488 | 0.0852 | 0.9812 | 0.9834 | 0.9812 | 0.9812 | | 0.0803 | 5.0500 | 5386 | 0.0895 | 0.9753 | 0.9775 | 0.9753 | 0.9753 | | 0.0457 | 6.0500 | 6284 | 0.0984 | 0.9788 | 0.9806 | 0.9788 | 0.9788 | | 0.0463 | 7.0500 | 7182 | 0.1675 | 0.9612 | 0.9658 | 0.9612 | 0.9614 | | 0.0039 | 8.05 | 8079 | 0.0545 | 0.9882 | 0.9891 | 0.9882 | 0.9882 | | 0.0162 | 9.0500 | 8977 | 0.0891 | 0.9812 | 0.9827 | 0.9812 | 0.9809 | | 0.0326 | 10.0500 | 9875 | 0.0742 | 0....

Note3 nov.huggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch

Source context: 9 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch

Note21 aoûthuggingface.co/Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch

Source context: 5 downloads · 0 likes · Pipeline video-classification · Library transformers · Repo Shawon16/VideoMAE_BdSLW60_FrameRate_Corrected_with_Augment_20_epoch