ailia-models

The collection of pre-trained, state-of-the-art models.

About ailia SDK

ailia SDK is a cross-platform high speed inference SDK. The ailia SDK provides a consistent C++ API on Windows, Mac, Linux, iOS, Android and Jetson. It supports Unity, Python and JNI for efficient AI implementation. The ailia SDK makes great use of the GPU via Vulkan and Metal to serve accelerated computing.

Supported models

Action recognition

	Model	Reference	Exported From	Supported Ailia Version
	mars	MARS: Motion-Augmented RGB Stream for Action Recognition	Pytorch	1.2.4 and later
	st-gcn	ST-GCN	Pytorch	1.2.5 and later

Audio Processing

	Model	Reference	Exported From	Supported Ailia Version
	crnn_audio_classification	crnn-audio-classification	Pytorch	1.2.5 and later
	deepspeech2	deepspeech.pytorch	Pytorch	1.2.2 and later

Crowd counting

	Model	Reference	Exported From	Supported Ailia Version
	crowdcount-cascaded-mtl	CNN-based Cascaded Multi-task Learning of High-level Prior and Density Estimation for Crowd Counting (Single Image Crowd Counting)	Pytorch	1.2.1 and later
	c-3-framework	C-3-Framework	Pytorch	1.2.5 and later

Deep fashion

Model	Reference	Exported From	Supported Ailia Version
clothing-detection	Clothing-Detection	Pytorch	1.2.1 and later
mmfashion	MMFashion	Pytorch	1.2.5 and later
fashionai-key-points-detection	A Pytorch Implementation of Cascaded Pyramid Network for FashionAI Key Points Detection	Pytorch	1.2.5 and later

Depth estimation

	Model	Reference	Exported From	Supported Ailia Version
	monodepth2	Monocular depth estimation from a single image	Pytorch	1.2.2 and later
	midas	Towards Robust Monocular Depth Estimation: Mixing Datasets for Zero-shot Cross-dataset Transfer	Pytorch	1.2.4 and later

Face detection

Model	Reference	Exported From	Supported Ailia Version
yolov1-face	YOLO-Face-detection	Darknet	1.1.0 and later
yolov3-face	Face detection using keras-yolov3	Keras	1.2.1 and later
blazeface	BlazeFace-PyTorch	Pytorch	1.2.1 and later
face-mask-detection	Face detection using keras-yolov3	Keras	1.2.1 and later
dbface	DBFace : real-time, single-stage detector for face detection, with faster speed and higher accuracy	Pytorch	1.2.2 and later

Face identification

Model	Reference	Exported From	Supported Ailia Version
vggface2	VGGFace2 Dataset for Face Recognition	Caffe	1.1.0 and later
arcface	pytorch implement of arcface	Pytorch	1.2.1 and later
insightface	InsightFace: 2D and 3D Face Analysis Project	Pytorch	1.2.5 and later

Face recognition

Model	Reference	Exported From	Supported Ailia Version
face_classification	Real-time face detection and emotion/gender classification	Keras	1.1.0 and later
facial_feature	kaggle-facial-keypoints	Pytorch	1.2.0 and later
face_alignment	2D and 3D Face alignment library build using pytorch	Pytorch	1.2.1 and later
prnet	Joint 3D Face Reconstruction and Dense Alignment with Position Map Regression Network	TensorFlow	1.2.2 and later
gazeml	A deep learning framework based on Tensorflow for the training of high performance gaze estimation	TensorFlow	1.2.0 and later
facemesh	facemesh.pytorch	Pytorch	1.2.2 and later
mediapipe_iris	irislandmarks.pytorch	Pytorch	1.2.2 and later

Generative adversarial networks

	Model	Reference	Exported From	Supported Ailia Version
	pytorch-gan	Code repo for the Pytorch GAN Zoo project (used to train this model)	Pytorch	1.2.4 and later
	council-GAN	Council-GAN	Pytorch	1.2.4 and later

Hand detection

Model	Reference	Exported From	Supported Ailia Version
yolov3-hand	Hand detection branch of Face detection using keras-yolov3	Keras	1.2.1 and later
hand_detection_pytorch	hand-detection.PyTorch	Pytorch	1.2.2 and later
blazepalm	MediaPipePyTorch	Pytorch	1.2.5 and later

Hand recognition

	Model	Reference	Exported From	Supported Ailia Version
	blazehand	MediaPipePyTorch	Pytorch	1.2.5 and later

Image captioning

	Model	Reference	Exported From	Supported Ailia Version
	illustration2vec	Illustration2Vec	Caffe	1.2.2 and later
	image_captioning_pytorch	Image Captioning pytorch	Pytorch	1.2.5 and later

Image classification

Model	Reference	Exported From	Supported Ailia Version
vgg16	Very Deep Convolutional Networks for Large-Scale Image Recognition	Keras	1.1.0 and later
googlenet	Going Deeper with Convolutions	Pytorch	1.2.0 and later
resnet50	Deep Residual Learning for Image Recognition	Chainer	1.2.0 and later
inceptionv3	Rethinking the Inception Architecture for Computer Vision	Pytorch	1.2.0 and later
mobilenetv2	PyTorch Implemention of MobileNet V2	Pytorch	1.2.0 and later
mobilenetv3	PyTorch Implemention of MobileNet V3	Pytorch	1.2.1 and later
partialconv	Partial Convolution Layer for Padding and Image Inpainting	Pytorch	1.2.0 and later
efficientnet	A PyTorch implementation of EfficientNet	Pytorch	1.2.3 and later

Image manipulation

Model	Reference	Exported From	Supported Ailia Version
noise2noise	Learning Image Restoration without Clean Data	Pytorch	1.2.0 and later
dewarpnet	DewarpNet: Single-Image Document Unwarping With Stacked 3D and 2D Regression Networks	Pytorch	1.2.1 and later
illnet	Document Rectification and Illumination Correction using a Patch-based CNN	Pytorch	1.2.2 and later
colorization	Colorful Image Colorization	Pytorch	1.2.2 and later
u2net_portrait	U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection	Pytorch	1.2.2 and later

Image segmentation

Model	Reference	Exported From	Supported Ailia Version
deeplabv3	Xception65 for backbone network of DeepLab v3+	Chainer	1.2.0 and later
hrnet_segmentation	High-resolution networks (HRNets) for Semantic Segmentation	Pytorch	1.2.1 and later
hair_segmentation	hair segmentation in mobile device	Keras	1.2.1 and later
pspnet-hair-segmentation	pytorch-hair-segmentation	Pytorch	1.2.2 and later
U-2-Net	U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection	Pytorch	1.2.2 and later
deep-image-matting	Deep Image Matting	Keras	1.2.3 and later
human_part_segmentation	Self Correction for Human Parsing	Pytorch	1.2.4 and later
semantic-segmentation-mobilenet-v3	Semantic segmentation with MobileNetV3	TensorFlow	1.2.5 and later
pytorch-unet	Pytorch-Unet	Pytorch	1.2.5 and later

Natural language processing

Model	Reference	Exported From	Supported Ailia Version
bert	pytorch-pretrained-bert	Pytorch	1.2.2 and later
bert_maskedlm	huggingface/transformers	Pytorch	1.2.5 and later
bert_ner	huggingface/transformers	Pytorch	1.2.5 and later
bert_question_answering	huggingface/transformers	Pytorch	1.2.5 and later
bert_sentiment_analysis	huggingface/transformers	Pytorch	1.2.5 and later
bert_zero_shot_classification	huggingface/transformers	Pytorch	1.2.5 and later
bert_tweets_sentiment	huggingface/transformers	Pytorch	1.2.5 and later

Object detection

Model	Reference	Exported From	Supported Ailia Version
yolov1-tiny	YOLO: Real-Time Object Detection	Darknet	1.1.0 and later
yolov2	YOLO: Real-Time Object Detection	Pytorch	1.2.0 and later
yolov3	YOLO: Real-Time Object Detection	ONNX Runtime	1.2.1 and later
yolov3-tiny	YOLO: Real-Time Object Detection	ONNX Runtime	1.2.1 and later
yolov4	Pytorch-YOLOv4	Pytorch	1.2.4 and later
yolov4-tiny	Pytorch-YOLOv4	Pytorch	1.2.5 and later
yolov5	yolov5	Pytorch	1.2.5 and later
mobilenet_ssd	MobileNetV1, MobileNetV2, VGG based SSD/SSD-lite implementation in Pytorch	Pytorch	1.2.1 and later
maskrcnn	Mask R-CNN: real-time neural network for object instance segmentation	Pytorch	1.2.3 and later
m2det	M2Det: A Single-Shot Object Detector based on Multi-Level Feature Pyramid Network	Pytorch	1.2.3 and later
centernet	CenterNet : Objects as Points	Pytorch	1.2.1 and later
pedestrian_detection	Pedestrian-Detection-on-YOLOv3_Research-and-APP	Pytorch	1.2.1 and later

Object tracking

	Model	Reference	Exported From	Supported Ailia Version
	deepsort	Deep Sort with PyTorch	Pytorch	1.2.3 and later

Pose estimation

Model	Reference	Exported From	Supported Ailia Version
openpose	Code repo for realtime multi-person pose estimation in CVPR'17 (Oral)	Caffe	1.2.1 and later
lightweight-human-pose-estimation	Fast and accurate human pose estimation in PyTorch. Contains implementation of "Real-time 2D Multi-Person Pose Estimation on CPU: Lightweight OpenPose" paper.	Pytorch	1.2.1 and later
lightweight-human-pose-estimation-3d	Real-time 3D multi-person pose estimation demo in PyTorch. OpenVINO backend can be used for fast inference on CPU.	Pytorch	1.2.1 and later
3d-pose-baseline	A simple baseline for 3d human pose estimation in tensorflow. Presented at ICCV 17.	TensorFlow	1.2.3 and later
pose_resnet	Simple Baselines for Human Pose Estimation and Tracking	Pytorch	1.2.1 and later
blazepose	MediaPipePyTorch	Pytorch	1.2.5 and later

Rotation prediction

	Model	Reference	Exported From	Supported Ailia Version
	rotnet	CNNs for predicting the rotation angle of an image to correct its orientation	Keras	1.2.1 and later

Style transfer

	Model	Reference	Exported From	Supported Ailia Version
	adain	Arbitrary Style Transfer in Real-time with Adaptive Instance Normalization	Pytorch	1.2.1 and later

Super resolution

	Model	Reference	Exported From	Supported Ailia Version
	srresnet	Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network	Pytorch	1.2.0 and later

Text detection

	Model	Reference	Exported From	Supported Ailia Version
	craft_pytorch	CRAFT: Character-Region Awareness For Text detection	Pytorch	1.2.2 and later

Text recognition

	Model	Reference	Exported From	Supported Ailia Version
	etl	Japanese Character Classification	Keras	1.1.0 and later

Commercial model

	Model	Reference	Exported From	Supported Ailia Version
	acculus-pose	Acculus, Inc.	Caffe	1.2.3 and later

Launcher

You can display a list of models and select them with the mouse by using the command below.

python3 launcher.py

Setup

Tutorial

ailia SDK tutorial (Python API) (EN)

ailia SDK tutorial (Python API) (JP)

Requirements

Python 3.6 and later

Install ailia SDK

Download a free evaluation version of ailia SDK
Unzip ailia SDK
Run the following command

cd ailia_sdk/python
python3 bootstrap.py
pip3 install ./

In the evaluation version, place the license file in the same folder as libailia.dll ([python_path]/site_packages/ailia) on Windows and in ~/Library/SHALO/ on Mac.
You can find the location of Python site-packages directory using the following command.

python -c "import site; print (site.getsitepackages())"

Install required libraries for Python

For Windows, Mac and Linux

pip install -r requirements.txt

For Jetson

sudo apt install python3-pip
sudo apt install python3-matplotlib
sudo apt install python3-scipy
pip3 install cython
pip3 install numpy

OpenCV for python3 is pre-installed on Jetson. You only need to run this command if you get a cv2 import error.

sudo apt install nvidia-jetpack

For Raspberry Pi

pip3 install numpy
pip3 install opencv-python
pip3 install matplotlib
pip3 install scikit-image
sudo apt-get install libatlas-base-dev

Other languages

unity version

c++ version

Files

README.md

Latest commit

History