fastervit 0.9.1

FasterViT: Fast Vision Transformers with Hierarchical Attention

FasterViT: Fast Vision Transformers with Hierarchical Attention

Official PyTorch implementation of FasterViT: Fast Vision Transformers with Hierarchical Attention.

Ali Hatamizadeh, Greg Heinrich, Hongxu (Danny) Yin, Andrew Tao, Jose M. Alvarez, Jan Kautz, Pavlo Molchanov.

For business inquiries, please visit our website and submit the form: NVIDIA Research Licensing

---

FasterViT achieves a new SOTA Pareto-front in terms of accuracy vs. image throughput without extra training data !

We introduce a new self-attention mechanism, denoted as Hierarchical Attention (HAT), that captures both short and long-range information by learning cross-window carrier tokens.

Quick Start

We can import pre-trained FasterViT models with 1 line of code. First, FasterViT can be simply installed by:

pip install fastervit

A pretrained FasterViT model with default hyper-parameters can be created as in the following:

>>> from fastervit import create_model

# Define fastervit-0 model with 224 x 224 resolution

>>> model = create_model('faster_vit_0_224', 
                          pretrained=True,
                          model_path="/tmp/faster_vit_0.pth.tar")

We can adjust where to download the above FasterViT-0 model by passing model_path.

We can also simply test the model by passing a dummy input image. The output is the logits:

>>> import torch

>>> image = torch.rand(1, 3, 224, 224)
>>> output = model(image) # torch.Size([1, 1000])

We can also use the any-resolution FasterViT model to accommodate arbitrary image resolutions. In the following, we define an any-resolution FasterViT-0 model with input resolution of 576 x 960, window sizes of 12 and 6 in 3rd and 4th stages, carrier token size of 2 and embedding dimension of 128:

>>> from fastervit import create_model

# Define any-resolution FasterViT-0 model with 576 x 960 resolution
>>> model = create_model('faster_vit_0_any_res', 
                          resolution=[576, 960],
                          window_size=[7, 7, 12, 6],
                          ct_size=2,
                          dim=64,
                          pretrained=True)

Note that the above model is intiliazed from the original ImageNet pre-trained FasterViT with original resolution of 224 x 224. As a result, missing keys and mis-matches could be expected since we are addign new layers (e.g. addition of new carrier tokens, etc.)

We can simply test the model by passing a dummy input image. The output is the logits:

>>> import torch

>>> image = torch.rand(1, 3, 576, 960)
>>> output = model(image) # torch.Size([1, 1000])

💥 News 💥

• [07.04.2023] 🔥🔥 ImageNet pretrained FasterViT models can now be imported with 1 line of code. Please install the latest FasterViT pip package to use this functionality (also supports Any-resolution FasterViT models).
• [06.30.2023] 🔥 We have further improved the TensorRT throughput of FasterViT models by 10-15% on average across different models.
• [06.29.2023] Any-resolution FasterViT model can now be intitialized from pre-trained ImageNet resolution (224 x 244) models.
• [06.18.2023] We have released the FasterViT pip package !
• [06.17.2023] 🔥 Any-resolution FasterViT model is now available ! the model can be used for variety of applications such as detection and segmentation or high-resolution fine-tuning with arbitrary input image resolutions.
• [06.09.2023] 🔥🔥 We have released source code and ImageNet-1K FasterViT-models !

Catalog

• ImageNet-1K training code
• ImageNet-1K pre-trained models
• Any-resolution FasterViT
• FasterViT pip-package release
• Add capablity to initialize any-resolution FasterViT from ImageNet-pretrained weights.
• ImageNet-21K pre-trained models
• Detection code (DINO) + models
• Segmentation code + models

---

Results + Pretrained Models

ImageNet-1K

FasterViT ImageNet-1K Pretrained Models

Name	Acc@1(%)	Acc@5(%)	Throughput(Img/Sec)	Resolution	#Params(M)	FLOPs(G)	Download
FasterViT-0	82.1	95.9	5802	224x224	31.4	3.3	model
FasterViT-1	83.2	96.5	4188	224x224	53.4	5.3	model
FasterViT-2	84.2	96.8	3161	224x224	75.9	8.7	model
FasterViT-3	84.9	97.2	1780	224x224	159.5	18.2	model
FasterViT-4	85.4	97.3	849	224x224	424.6	36.6	model
FasterViT-5	85.6	97.4	449	224x224	975.5	113.0	model
FasterViT-6	85.8	97.4	352	224x224	1360.0	142.0	model

Robustness (ImageNet-A - ImageNet-R - ImageNet-V2)

All models use crop_pct=0.875. Results are obtained by running inference on ImageNet-1K pretrained models without finetuning.

Name	A-Acc@1(%)	A-Acc@5(%)	R-Acc@1(%)	R-Acc@5(%)	V2-Acc@1(%)	V2-Acc@5(%)
FasterViT-0	23.9	57.6	45.9	60.4	70.9	90.0
FasterViT-1	31.2	63.3	47.5	61.9	72.6	91.0
FasterViT-2	38.2	68.9	49.6	63.4	73.7	91.6
FasterViT-3	44.2	73.0	51.9	65.6	75.0	92.2
FasterViT-4	49.0	75.4	56.0	69.6	75.7	92.7
FasterViT-5	52.7	77.6	56.9	70.0	76.0	93.0
FasterViT-6	53.7	78.4	57.1	70.1	76.1	93.0

A, R and V2 denote ImageNet-A, ImageNet-R and ImageNet-V2 respectively.

Training

Please see TRAINING.md for detailed training instructions of all models.

Evaluation

The FasterViT models can be evaluated on ImageNet-1K validation set using the following:

python validate.py \
--model <model-name>
--checkpoint <checkpoint-path>
--data_dir <imagenet-path>
--batch-size <batch-size-per-gpu

Here --model is the FasterViT variant (e.g. faster_vit_0_224_1k), --checkpoint is the path to pretrained model weights, --data_dir is the path to ImageNet-1K validation set and --batch-size is the number of batch size. We also provide a sample script here.

ONNX Conversion

We provide ONNX conversion script to enable dynamic batch size inference. For instance, to generate ONNX model for faster_vit_0_any_res with resolution 576 x 960 and ONNX opset number 17, the following can be used.

python onnx_convert --model-name faster_vit_0_any_res --resolution-h 576 --resolution-w 960 --onnx-opset 17

Installation

The dependencies can be installed by running:

pip install -r requirements.txt

Star History

Third-party Extentions

We always welcome third-party extentions/implementations and usage for other purposes. If you would like your work to be listed in this repository, please raise and issue and provide us with detailed information.

Citation

Please consider citing FasterViT if this repository is useful for your work.

@article{hatamizadeh2023fastervit,
  title={FasterViT: Fast Vision Transformers with Hierarchical Attention},
  author={Hatamizadeh, Ali and Heinrich, Greg and Yin, Hongxu and Tao, Andrew and Alvarez, Jose M and Kautz, Jan and Molchanov, Pavlo},
  journal={arXiv preprint arXiv:2306.06189},
  year={2023}
}

Licenses

Copyright © 2023, NVIDIA Corporation. All rights reserved.

This work is made available under the NVIDIA Source Code License-NC. Click here to view a copy of this license.

For license information regarding the timm repository, please refer to its repository.

For license information regarding the ImageNet dataset, please see the ImageNet official website.

Acknowledgement

This repository is built on top of the timm repository. We thank Ross Wrightman for creating and maintaining this high-quality library.