Har_Finetuned-ViT-Hybrid

Kartik14Singh/Har_Finetuned-ViT-Hybrid

Har_Finetuned-ViT-Hybrid is a image classification model from Kartik14Singh. Use it when you need a label for an image. It is set up for transformers. The card lists the license as apache-2.0.

should probably proofread and complete it, then remove this comment. --

Downloads · 30 days

2% of all-time downloads

All-time downloads

391

Public

Repo size

2.8 GB

Likes

Public

Hugging Face

Repo makeup

Click a slice to open those files.

.bin393 MB · 100%

At a glance

Task: Image Classification
Library: transformers
License: apache-2.0
Model type: vit-hybrid
Access: Public
Created: Apr 10, 2023
Updated: Apr 10, 2023
SHA: 688f085d

Datasets

image_folder

Model card

From the Hugging Face model README

Har_Finetuned-ViT-Hybrid

This model is a fine-tuned version of google/vit-hybrid-base-bit-384 on the image_folder dataset. It achieves the following results on the evaluation set:

Loss: 0.3383
Accuracy: 0.8995

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: 16
eval_batch_size: 16
seed: 42
gradient_accumulation_steps: 4
total_train_batch_size: 64
optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
lr_scheduler_type: linear
lr_scheduler_warmup_ratio: 0.1
num_epochs: 6

Training results

Training Loss	Epoch	Step	Validation Loss	Accuracy
0.7923	1.0	167	0.4420	0.8698
0.5555	2.0	334	0.3811	0.8820
0.4734	3.0	501	0.3448	0.8958
0.4019	4.0	668	0.3521	0.8926
0.3622	5.0	835	0.3505	0.8926
0.2921	6.0	1002	0.3383	0.8995

Framework versions

Transformers 4.26.1
Pytorch 1.13.0
Datasets 2.1.0
Tokenizers 0.13.2

Task: Image Classification
Library: transformers
Type: vit-hybrid
License: apache-2.0
Created: Apr 10, 2023
Updated: Apr 10, 2023