Shadowgraph
About
Sign in

jayanta/vit-base-patch16-224-in21k-face-recognition

Model

13

stars

14

commits

3

repos using this model

1

linked in READMEs

Oct 31, 2023

updated

endpoints_compatible
generated_from_trainer
image-classification
model-index
pytorch
tensorboard
transformers
vit
Browse cluster: Multilingual Legal NLP Models →

README

vit-base-patch16-224-in21k-face-recognition

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0015
  • Accuracy: 1.0000

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: 0.00012
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 8

Training results

Training LossEpochStepValidation LossAccuracy
0.03681.03720.03461.0000
0.00942.07440.00921.0000
0.00463.011160.00471.0000
0.00294.014880.00291.0
0.00225.018600.00230.9999
0.00176.022320.00171.0
0.00157.026040.00151.0
0.00148.029760.00151.0000

Framework versions

  • Transformers 4.30.2
  • Pytorch 1.13.1+cu117
  • Datasets 2.13.2
  • Tokenizers 0.11.0

Contributors

jayanta

14 commits

Similar repos

antonioglass/real-or-anime-age

Model

0

shared topics

1aurent/vit_base_patch16_224.kaiko_ai_towards_large_pathology_fms

Model

2

shared topics

1aurent/vit_base_patch8_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_small_patch16_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_small_patch8_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_large_patch14_reg4_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_large_patch14_reg4_dinov2.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

Falconsai/nsfw_image_detection

Model

1,178

shared topics

Used in code

mindadeepam/face_rec

0

2 files

Jawerchy/Face-Recognition-Attendance-System

Implement a dual-mode attendance system using face recognition and card-based methods with a modern…

4

1 file

DominikTruchly/Face_Detection_Recognition_framework

0

1 file

Linked in READMEs

qinghew/StableIdentity

[TMM 2025] StableIdentity: Inserting Anybody into Anywhere at First Sight

257

README badge

jayanta/vit-base-patch16-224-in21k-face-recognition

Model

13

stars

14

commits

3

repos using this model

1

linked in READMEs

Oct 31, 2023

updated

endpoints_compatible
generated_from_trainer
image-classification
model-index
pytorch
tensorboard
transformers
vit
Browse cluster: Multilingual Legal NLP Models →

README

vit-base-patch16-224-in21k-face-recognition

This model is a fine-tuned version of google/vit-base-patch16-224-in21k on the imagefolder dataset. It achieves the following results on the evaluation set:

  • Loss: 0.0015
  • Accuracy: 1.0000

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: 0.00012
  • train_batch_size: 64
  • eval_batch_size: 64
  • seed: 42
  • gradient_accumulation_steps: 4
  • total_train_batch_size: 256
  • optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
  • lr_scheduler_type: linear
  • lr_scheduler_warmup_ratio: 0.1
  • num_epochs: 8

Training results

Training LossEpochStepValidation LossAccuracy
0.03681.03720.03461.0000
0.00942.07440.00921.0000
0.00463.011160.00471.0000
0.00294.014880.00291.0
0.00225.018600.00230.9999
0.00176.022320.00171.0
0.00157.026040.00151.0
0.00148.029760.00151.0000

Framework versions

  • Transformers 4.30.2
  • Pytorch 1.13.1+cu117
  • Datasets 2.13.2
  • Tokenizers 0.11.0

Similar repos

antonioglass/real-or-anime-age

Model

0

shared topics

1aurent/vit_base_patch16_224.kaiko_ai_towards_large_pathology_fms

Model

2

shared topics

1aurent/vit_base_patch8_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_small_patch16_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_small_patch8_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_large_patch14_reg4_224.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

1aurent/vit_large_patch14_reg4_dinov2.kaiko_ai_towards_large_pathology_fms

Model

0

shared topics

Falconsai/nsfw_image_detection

Model

1,178

shared topics

Used in code

mindadeepam/face_rec

0

2 files

Jawerchy/Face-Recognition-Attendance-System

Implement a dual-mode attendance system using face recognition and card-based methods with a modern…

4

1 file

DominikTruchly/Face_Detection_Recognition_framework

0

1 file

Linked in READMEs

qinghew/StableIdentity

[TMM 2025] StableIdentity: Inserting Anybody into Anywhere at First Sight

257

README badge

Contributors

jayanta

14 commits