Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/nachiket273/vistrans
Implementations of transformers based models for different vision tasks
https://github.com/nachiket273/vistrans
botnet computer-vision pretrained-models python3 pytorch transformers vision-transformers
Last synced: 23 days ago
JSON representation
Implementations of transformers based models for different vision tasks
- Host: GitHub
- URL: https://github.com/nachiket273/vistrans
- Owner: nachiket273
- License: mit
- Created: 2021-01-05T19:49:33.000Z (almost 4 years ago)
- Default Branch: main
- Last Pushed: 2021-06-30T18:01:13.000Z (over 3 years ago)
- Last Synced: 2024-10-14T21:40:50.804Z (23 days ago)
- Topics: botnet, computer-vision, pretrained-models, python3, pytorch, transformers, vision-transformers
- Language: Python
- Homepage:
- Size: 112 KB
- Stars: 1
- Watchers: 2
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# VisTrans
Implementations of transformers based models for different vision tasks
## Install
1) Install from PyPI
```Python
pip install vistrans
```
2) Install from Anaconda
```Python
conda install -c nachiket273 vistrans
```
## Version 0.003 (06/30/2021)
------------------------------
[](https://badge.fury.io/py/vistrans)
Minor fixes to fix issues with existing models.
## Version 0.002 (04/17/2021)
------------------------------
[](https://badge.fury.io/py/vistrans)
Pretrained Pytorch Bottleneck Transformers for Visual Recognition including following
* botnet50
* botnet101
* botnet152
Implementation based off Official Tensorflow Implementation
## Usage
---------------------
pip install vistrans
```
1) List Pretrained Models.
```Python
from vistrans import BotNet
BotNet.list_pretrained()
```
2) Create Pretrained Models.
```Python
from vistrans import BotNet
model = BotNet.create_pretrained(name, img_size, in_ch, num_classes,
n_heads, pos_enc_type)
```
3) Create Custom Model
```Python
from vistrans import BotNet
model = BotNet.create_model(layers, img_size, in_ch, num_classes, groups,
norm_layer, n_heads, pos_enc_type)
```
## Version 0.001 (03/04/2021)
-----------------------------
[](https://badge.fury.io/py/vistrans)
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
## Usage
---------------------
1) List Pretrained Models.
```Python
from vistrans import VisionTransformer
VisionTransformer.list_pretrained()
```
2) Create Pretrained Models.
```Python
from vistrans import VisionTransformer
model = VisionTransformer.create_pretrained(name, img_size, in_ch, num_classes)
```
3) Create Custom Model
```Python
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)
```