Downloads · 30 days
159
5% of all-time downloads
ConvNeXt-FaceMask-Finetuned
AkshatSurolia/ConvNeXt-FaceMask-Finetuned
ConvNeXt-FaceMask-Finetuned is a image classification model from AkshatSurolia. 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.
ConvNeXt model pre-trained and fine-tuned on Self Currated Custom Face-Mask18K Dataset (18k images, 2 classes) at resolution 224x224. It was introduced in the paper A ConvNet for the 2020s by Zhuang Liu, Hanzi Mao et al.
All-time downloads
2.9K
Public
Parameters
27.8M
223 MB on disk
Likes
7
Public
Repo makeup
Click a slice to open those files.
.bin111 MB · 50%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- convnext
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- May 5, 2023
- SHA
- 8e57e9c4
Datasets
Model card
From the Hugging Face model README
ConvNeXt for Face Mask Detection
ConvNeXt model pre-trained and fine-tuned on Self Currated Custom Face-Mask18K Dataset (18k images, 2 classes) at resolution 224x224. It was introduced in the paper A ConvNet for the 2020s by Zhuang Liu, Hanzi Mao et al.
Training Metrics
epoch = 3.54
total_flos = 1195651761GF
train_loss = 0.0079
train_runtime = 1:08:20.25
train_samples_per_second = 14.075
train_steps_per_second = 0.22
Evaluation Metrics
epoch = 3.54
eval_accuracy = 0.9961
eval_loss = 0.0151
eval_runtime = 0:01:23.47
eval_samples_per_second = 43.079
eval_steps_per_second = 5.391
- Task
- Image Classification
- Library
- transformers
- Type
- convnext
- License
- apache-2.0
- Created
- Mar 2, 2022
- Updated
- May 5, 2023