Skip to content
Kazuki Kyakuno edited this page Aug 9, 2024 · 247 revisions

History

  • 2024.08.09 Add mahalanobis-ad, t5_base_japanese_ner, hands_segmentation_pytorch
  • 2024.08.08 Add sdxl-turbo, sd-turbo
  • 2024.08.05 Migrate to ailia Tokenizer 1.3 from Transformers
  • 2024.07.16 Add grounded_sam
  • 2024.07.12 Add llava
  • 2024.07.09 Add GroundingDINO
  • 2024.06.26 Add g2p_en
  • 2024.06.24 Add soundchoice-g2p
  • 2024.06.11 Add gpt-sovits, reazon speech, reazon speech2 (ailia SDK 1.4.0)
  • 2024.05.28 Add kotoba-whisper
  • 2024.05.26 Add multilingual-e5 (LayerNorm version)
  • 2024.04.30 Add cross_encoder_mmarco
  • 2024.04.28 Add marigold
  • 2024.04.08 The ailia SDK can now be installed via pip.
  • 2024.04.02 Add zoe_depth, facefusion
  • 2024.04.01 Add pytorch-fcn (ailia SDK 1.3.0)
  • 2024.03.31 Add bert-network-packet-flow-header-payload
  • 2024.03.29 Add falcon-adapter-network-packet, pyannote-audio
  • 2024.03.08 Add did_m3d, damo_yolo, deep-music-enhancer, tusimple-DUC
  • 2024.03.05 Add polylanenet, rnnoise, audioset_tagging_cnn
  • 2024.03.04 Add Japanese Stable CLIP, msclap, glucose, informer2020, l2cs_net, deepsort_vehicle, narabas
  • 2024.03.03 Add yolov9 (Unification of line feed code to LF)
  • 2024.01.29 Add rife, layout_parsing
  • 2024.01.27 Add mivolo
  • 2023.12.09 Add riffusion
  • 2023.12.05 Add facenet-pytorch, centroids-reid, nafnet, daclip-sde
  • 2023.12.04 Add distil-whisper
  • 2023.11.24 Add Segment Anything, BLIP2, Whisper Large V2 and V3 (ailia SDK 1.2.16)
  • 2023.11.14 Add GFPGAN v1.4
  • 2023.11.09 Add t5_base_japanese_summarization
  • 2023.11.02 Add t5_whisper_medical
  • 2023.10.31 Add imagenet21k, Update weight of dis_seg
  • 2023.10.29 Add fugumt-ja-en, patchcore, 3ddfa, docshadow
  • 2023.10.25 Add use_sr option to sber-swap
  • 2023.10.24 Add hifigan
  • 2023.10.20 Add bert_insert_punctuation
  • 2023.10.19 Add multilingual-e5
  • 2023.10.08 Add japanese-clip
  • 2023.09.27 Add hat, lightglue
  • 2023.09.25 Add bertjsc
  • 2023.09.18 Add vall-e-x, facemeshv2
  • 2023.09.07 Add lipgan
  • 2023.08.23 Add crepe
  • 2023.08.17 Add control_net, basil_mix and sd_vae for StableDiffusion
  • 2023.08.08 Add rvc
  • 2023.08.03 Add qrcode_wechatqrcode, tacotron2, silero_vad, strong_sort (ailia SDK 1.2.15)
  • 2023.07.06 Add t5_base_japanese_title_generation
  • 2023.06.19 Add bert_maskedlm (bert-base-japanese-char-whole-word-masking, bert-base-japanese-v3, bert-base-japanese-char-v3)
  • 2023.06.06 Add yolov8, yolov8-seg (ailia SDK 1.2.14.1)
  • 2023.05.24 Add wespeaker, presumm
  • 2023.05.11 Add sentence-transformers-japanese
  • 2023.04.10 Add footandball
  • 2023.04.07 Add stable-diffusion, bert_sum_ext
  • 2023.03.23 Add fugumt-en-ja
  • 2023.03.15 Add hsemotion
  • 2023.03.02 Add anime-segmentation (ailia SDK 1.2.14)
  • 2023.02.19 Add translate mode to Whisper
  • 2023.02.14 Add CLIP-based-NSFW-Detector
  • 2023.02.13 Add person-attributes-recognition-crossroad, yolov, mtcnn
  • 2023.02.06 Add clip (ViTL14)
  • 2023.01.16 Add cnngeometric-pytorch
  • 2023.01.12 Add ndlocr_text_recognition, e2pose
  • 2023.01.11 Add face-detection-adas
  • 2023.01.06 Add clap, v2v-posenet, crowd_det
  • 2022.12.21 Add encoder4editing, posenet, cosface
  • 2022.12.05 Add ap-10k, realesr-animevideov3
  • 2022.12.04 Add pytorch-superpoint
  • 2022.11.23 Add whisper
  • 2022.11.14 Add film
  • 2022.10.24 Add crestereo、glip、dehamer、mobilestereonet (ailia SDK 1.2.13)
  • 2022.10.19 Add dfe
  • 2022.10.18 Add gfm
  • 2022.10.15 Add poly_yolo, group_vit
  • 2022.10.14 Add mediapipe_holistic
  • 2022.08.31 Add dis
  • 2022.08.29 Add mobileone, 6d_repnet
  • 2022.08.28 Update detic (opset=16 + grid_sampler)
  • 2022.08.17 Add action_clip
  • 2022.08.13 Add mediapipe_pose_world_landmarks, yolov6, yolov7, dfm
  • 2022.07.29 Add swinir, dab-detr, sber-swap (ailia SDK 1.2.12)
  • 2022.07.28 Add places365, gfpgan
  • 2022.07.19 Add rcan-it, fastest-det
  • 2022.06.30 Add LatentDiffusionModel-superresolution, txt2img, inpainting
  • 2022.06.19 Add yolact
  • 2022.06.07 Add picodet
  • 2022.05.17 Add qd-3dt
  • 2022.05.02 (ailia SDK 1.2.11)
  • 2022.04.25 Add PP-LiteSeg
  • 2022.04.22 Add d4lcn
  • 2022.04.13 Add NeRF, EgoNet, hybridnets
  • 2022.04.11 Add convnext
  • 2022.04.07 Add swin-transformer
  • 2022.04.05 Add yolov5s6, yolop, easyocr
  • 2022.04.04 Update launcher
  • 2022.03.31 Add pix2pixHD
  • 2022.03.15 Add spade-pytorch
  • 2022.03.09 Add ax_facial_features
  • 2022.03.02 Add detic, trafic-sign-detection (ailia SDK 1.2.10)
  • 2022.02.28 Add suim
  • 2022.02.22 Add resnet18, rembg, dexined
  • 2022.02.17 Add cascade_psp, yolov2-tiny
  • 2022.02.16 Add deepfillv2, weather-prediction-from-image, ultra-fast-lane-detection
  • 2022.02.14 Add yolox-ti-lite
  • 2022.02.03 Add real-esrgan
  • 2022.02.02 Add landmarks_classifier_asia
  • 2022.01.19 Add voicefilter
  • 2022.01.11 Add cain
  • 2022.01.05 Add lstr
  • 2022.01.04 Add agllnet
  • 2022.01.03 Add Alexnet, clip
  • 2021.12.30 Add invertible_denoising_network
  • 2021.12.28 Add paddleseg, face-anti-spoofing, cdnet
  • 2021.12.20 Add mobile_object_localizer, sku110k_densedet
  • 2021.12.03 Add anime-face-detector, mlp-mixer
  • 2021.11.25 Add LapDepth , SiamMot, HitNet, BackgroundMattingV2, RestyleEncoder, SAM (ailia SDK 1.2.9)
  • 2021.11.19 Add animeganv2
  • 2021.11.17 Add gpt2, rinna-gpt2
  • 2021.11.15 Add FerPlus
  • 2021.10.24 Add ByteTrack
  • 2021.10.09 Add in-shop retriever
  • 2021.10.05 Add RAFT
  • 2021.09.28 Add driver-action-recognition-adas-0002, yolox
  • 2021.09.24 Add wide_resnet50, auto_speech
  • 2021.09.21 Add road-segmentation-adas
  • 2021.09.13 Add vehicle-license-plate-detection-barrier
  • 2021.09.10 Add abd-net
  • 2021.09.09 Add vehicle-attributes-recognition-barrier
  • 2021.09.03 Add age-gender-recognition
  • 2021.08.28 Add minimal-hand, movenet, mlsd, mmfashion-tryon, pytorch-enet, 3d-object-detection.pytorch
  • 2021.08.25 Add mediapipe_objectron
  • 2021.08.19 Add transformer-cnn-emotion-recognition
  • 2021.08.06 Add inceptionv4
  • 2021.07.28 Add modnet
  • 2021.07.12 Add u2net_human_seg

Export script

mobilenetv2

inceptionv3

gazeml

3d-pose-baseline

facial_feature

partialconv

deep-image-matting

hand-detection.PyTorch

Server settings

cors

Tips for error

onnxruntime by macOS

Clone this wiki locally