Unofficial implementations of transfomers models for vision.
Project description
VisTrans
Implementations of transformers based models for different vision tasks
Version 0.001 (03/04/2021)
Pretrained Pytorch Vision Transformer Models including following
- vit_s16_224
- vit_b16_224
- vit_b16_384
- vit_b32_384
- vit_l16_224
- vit_l16_384
- vit_l32_384
Implementation based off official jax repository and timm's implementation
Install
pip install vistrans
- List Pretrained Models.
from vistrans import VisionTransformer
VisionTransformer.list_pretrained()
- Create Pretrained Models.
from vistrans import VisionTransformer
model = VisionTransformer.create_pretrained(name, img_size, in_ch, num_classes)
- Create Custom Model
from vistrans import VisionTransformer
model = VisionTransformer.create_model(img_size, patch_size, in_ch, num_classes,
embed_dim, depth, num_heads, mlp_ratio,
drop_rate, attention_drop_rate, hybrid,
norm_layer, bias)
Project details
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
vistrans-0.0.1.tar.gz
(8.3 kB
view hashes)