Downloads · 30 days
7
1% of all-time downloads
pvt_v2_b0
FoamoftheSea/pvt_v2_b0
pvt_v2_b0 is a image classification model from FoamoftheSea. 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.
This is the Hugging Face PyTorch implementation of the PVTv2 model.
All-time downloads
742
Public
Parameters
3.7M
58.8 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors14.7 MB · 100%
At a glance
- Task
- Image Classification
- Library
- transformers
- License
- apache-2.0
- Model type
- pvt_v2
- Access
- Public
- Created
- Oct 14, 2023
- Updated
- Mar 12, 2024
- SHA
- 0d4231ff
Model card
From the Hugging Face model README
PVTv2
This is the Hugging Face PyTorch implementation of the PVTv2 model.
Model Description
The Pyramid Vision Transformer v2 (PVTv2) is a powerful, lightweight hierarchical transformer backbone for vision tasks. PVTv2 infuses convolution operations into its transformer layers to infuse properties of CNNs that enable them to learn image data efficiently. This mix transformer architecture requires no added positional embeddings, and produces multi-scale feature maps which are known to be beneficial for dense and fine-grained prediction tasks.
Vision models using PVTv2 for a backbone:
- Segformer for Semantic Segmentation.
- GLPN for Monocular Depth.
- Deformable DETR for 2D Object Detection.
- Panoptic Segformer for Panoptic Segmentation.
- Task
- Image Classification
- Library
- transformers
- Type
- pvt_v2
- License
- apache-2.0
- Created
- Oct 14, 2023
- Updated
- Mar 12, 2024